{
  "$schema": "https://www.yerel.ai/schemas/external-benchmarks-v1.json",
  "version": "external-benchmarks-v1",
  "generatedAt": "2026-06-08T09:56:55.228Z",
  "description": "Third-party benchmark evidence imported for comparison context. These records must be labeled as external and should not be mixed into YerelAI native benchmark leaderboards without provenance badges.",
  "globalCaveat": "External benchmark records use different datasets, languages, prompts, scoring rules, and anti-contamination policies. They are useful context, not proof that a model is best for Turkish users or regulated workflows.",
  "sources": [
    {
      "id": "openevals-leaderboard-data",
      "title": "OpenEvals leaderboard-data",
      "dataset": "OpenEvals/leaderboard-data",
      "config": "default",
      "split": "train",
      "homepage": "https://huggingface.co/datasets/OpenEvals/leaderboard-data",
      "status": "complete",
      "rowsImported": 105,
      "rowsTotal": 105,
      "partial": false,
      "method": "Imported model-level leaderboard rows from the Hugging Face generated Parquet snapshot.",
      "caveat": "Coverage varies by model. Scores are third-party external context, not YerelAI Turkish benchmark runs.",
      "snapshot": {
        "provider": "huggingface-parquet",
        "fileName": "0000.parquet",
        "sizeBytes": 17894,
        "url": "https://huggingface.co/datasets/OpenEvals/leaderboard-data/resolve/refs%2Fconvert%2Fparquet/default/train/0000.parquet",
        "fingerprint": "d2fef3319cf2745d6d1bab28"
      }
    },
    {
      "id": "lmarena-text-style-control-latest",
      "title": "LMArena leaderboard dataset — text style control latest",
      "dataset": "lmarena-ai/leaderboard-dataset",
      "config": "text_style_control",
      "split": "latest",
      "homepage": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset",
      "status": "complete",
      "rowsImported": 8902,
      "rowsTotal": 8902,
      "partial": false,
      "method": "Imported latest Arena rating rows from the Hugging Face generated Parquet snapshot, including rank, rating bounds, vote count, category, and publish date.",
      "caveat": "Arena ratings are human preference signals and should not be described as factual accuracy or Turkish domain competence.",
      "snapshot": {
        "provider": "huggingface-parquet",
        "fileName": "0000.parquet",
        "sizeBytes": 486474,
        "url": "https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/resolve/refs%2Fconvert%2Fparquet/text_style_control/latest/0000.parquet",
        "fingerprint": "066089341d9dad87fd89c187"
      }
    },
    {
      "id": "livebench-model-judgment",
      "title": "LiveBench model_judgment",
      "dataset": "livebench/model_judgment",
      "config": "default",
      "split": "leaderboard",
      "homepage": "https://huggingface.co/datasets/livebench/model_judgment",
      "status": "complete",
      "rowsImported": 60372,
      "rowsTotal": 60372,
      "partial": false,
      "method": "Imported row-level judgments and aggregated task, category, and overall means locally.",
      "caveat": "LiveBench aggregation here is for evidence browsing only and is not a YerelAI-native Turkish benchmark score.",
      "snapshot": {
        "provider": "huggingface-parquet",
        "fileName": "0000.parquet",
        "sizeBytes": 737444,
        "url": "https://huggingface.co/datasets/livebench/model_judgment/resolve/refs%2Fconvert%2Fparquet/default/leaderboard/0000.parquet",
        "fingerprint": "54da7aec6c8b198e7105f264"
      }
    }
  ],
  "summary": {
    "sourceCount": 3,
    "recordCount": 11094,
    "partialSourceCount": 0,
    "liveBenchRowsLimited": false,
    "contentHash": "aa4ccd49fe62ef6afe66eb97ad2fdaac128601ce230663225aaabdc1d3f18e56"
  },
  "records": [
    {
      "id": "9e1a01688b9acfccf965452c",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.39052631578947367,
      "unit": "mean task score",
      "sampleCount": 88,
      "asOf": "2024-12-10T18:50:09.232Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0a0c69d3c83708c4e9a87dd6",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7772435897435899,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-25T19:40:34.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2f726f194f4cb231b3159259",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3003005568570479,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:02.167Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8aadc1e3da2ed7d1a46bb92f",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.48935682079670384,
      "unit": "mean category score",
      "sampleCount": 254,
      "asOf": "2024-12-10T19:31:02.167Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2128f2f734d8a5c39c99cb4c",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.42105263157894735,
      "unit": "mean score",
      "sampleCount": 38,
      "asOf": "2024-12-10T18:50:09.232Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5fdbef7a4a485200c93f5534",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.36,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-25T19:40:34.071Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1e0417f630e8fab6e8f80bfb",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7772435897435899,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-25T19:40:34.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0e5b44252a3ed10a3e660913",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-25T20:16:39.122Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1f0ddcc9a75513c7c10d8bac",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3009016705711437,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:02.167Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c46c6591af2ed55c9ce88ef2",
      "sourceId": "livebench-model-judgment",
      "model": "acm_rewrite_qwen2-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "71490a362a2549be54673d30",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2746153846153846,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:21.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8e75eac5e0d23a721c4d292d",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.571,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.798Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1a9b6ec0ffef92908cdaf166",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.267580746815322,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:55.287Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fc927782fb8e0cad8f423699",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.37106537714356885,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:55.287Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "10bdb818137a35e321cb06a9",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.052Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "86b6570d90b87e11d0fe1c29",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2692307692307692,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:21.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6cecf2b4ec375c727efa466e",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.571,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.798Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c6bb2128e09529c2fcaef9b1",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.19,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ca91189caf4d9bd56551e34f",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.20274224044596603,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:55.287Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d672c13c714e5cfb7355a9a4",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-lite-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.41,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.162Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "448e475626d843b64ae57936",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2017948717948718,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:15.030Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "47fb06b8bb091edbe3b3c9de",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.412,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c58621af5800d4ce96a2e80f",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.19934279271733157,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:02.383Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cf1fb8377eec2ae7a8286691",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.27104588817073444,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:02.383Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "27f2c9984c2486a34c004052",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.704Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "570e081a279cc89076e4112f",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.24358974358974358,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:15.030Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cd565ed6bf717037995331d5",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.412,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1b1f81a32d2f38ae881d8926",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.11,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "53a49825a208a259b9a948b1",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.1480283781519947,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:02.383Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "734e3c98ad3981ba0b243da3",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-micro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.240Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "146c57bd507c7c332e3825b2",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.38153846153846155,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:32.027Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "83abba5e411530f115f3dfe4",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7013333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.323Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "df22dbfb97b91523bcc3da20",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.37874357824928234,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:04.616Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8fff06f620aeff862c255dfa",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4872051243736924,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:04.616Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dcee9751d731b48d59515c4f",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.376Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cb1a8718fa1f2ffbf6629ac9",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4230769230769231,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:32.027Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2ee76027d96f7aee23a89dd0",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7013333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.323Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cb16932da3fff8e17ede80bb",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.23833333333333337,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1deded7f467c8272fea366d1",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3078974014145138,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:04.616Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "405c00965a0c669a6a56cb87",
      "sourceId": "livebench-model-judgment",
      "model": "amazon.nova-pro-v1:0",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.59,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.267Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f0b7aaa8f33e6e528397f792",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3138461538461539,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-03T16:59:27.682Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b0b5a1384922bd485be122de",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6104999999999999,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-01T00:03:47.839Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "589862f759901aa4e7cb4176",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.26605459242072654,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-03T18:13:06.747Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c74126e894372b5e2b0aed23",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.39680024875562675,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-03T18:13:06.747Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b5734bba7c334eddd3d29311",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-03T16:59:27.682Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "641faf1a2280cfe6148f9929",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-01T00:03:46.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "be05ff5d18fde9157ea3067d",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6104999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-01T00:03:47.839Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7d33c820bc14b5c653610e8b",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.19666666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-03T16:59:56.223Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2e6bd6ab2248e72e5202691a",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2614971105955129,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-03T18:13:06.747Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd24e50bb5b62f8a24527442",
      "sourceId": "livebench-model-judgment",
      "model": "azerogpt",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-03T18:12:41.800Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cd31a1b4cc716573419940e7",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6056410256410256,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:28.185Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ce935393b37f0cf882a57946",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6611666666666665,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-05T16:02:45.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4be84928b517b70e410f2af5",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.49688120914019435,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:55.913Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cd6e2bf514600ac348bed38f",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5878963004826289,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:55.913Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "e09f40674a6a74bfe96efbcb",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.66,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T15:55:28.997Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d1f6e3c47e5fa157e151bc9b",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5512820512820513,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:28.185Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "00a0407acb397d4d904e45d1",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6611666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T16:02:45.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3c9aedccd3fc20235c20971b",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5216666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T15:59:44.872Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c4915cfc871df4f652fa3cca",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4389769607539164,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:55.913Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95ad0e807d7e9a03a8375627",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-29",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.53,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.175Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "43803771a3fb28e89cfcdc2c",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.47717948717948716,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:33.060Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1468040ea6d8bafd8c07798a",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6388333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-30T16:56:10.069Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cfd1cfa0f99171d56e9fd943",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4793576614515203,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-01-30T16:42:53.642Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "02be31484a35cc776926e77f",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5317901606547802,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-06T18:32:33.060Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b6127dc34d49a2367d6047b3",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T16:43:43.771Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c2f70478613d47b8b0a7a334",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.47435897435897434,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:33.060Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "93a98958706eb68758377b16",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6388333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T16:56:10.069Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f8c971a58a840b1b3b24b502",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4216666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T16:42:29.901Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f1d76754dd866ee2d02b8afc",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4364063176878942,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-01-30T16:42:52.698Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0d6e8e7f65e1cd3849e4a101",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-01-30",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T16:42:53.642Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "376e497d703e90c3ece877a4",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6497435897435897,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-27T21:38:15.608Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b82b97b6d65d86beddffbd53",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7686794871794872,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2025-03-27T21:34:05.976Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8835cffff9eaa913cbb916e9",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5112536738825973,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-04-01T22:08:21.681Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4b7723deb3980a0bcc6f970e",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6432255836018914,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-04-01T22:08:21.681Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "699cea87afa9c75e41ad9593",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-27T21:37:14.306Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "401920b4144fd78189e9a634",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6794871794871795,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-27T21:38:15.608Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f647b8248e5fcbbf96ec9eda",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7296666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-27T21:34:05.976Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f0266574a4195768488d48af",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8076923076923077,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-19T14:13:23.100Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7906ca55963a7728180e3df3",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4566666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:08:21.681Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64068eae7085aa4f7cb37b1f",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4370943549811254,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:08:20.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "68d29000d6480cf595b458d3",
      "sourceId": "livebench-model-judgment",
      "model": "chatgpt-4o-latest-2025-03-27",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.64,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:05:09.251Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "750a126fcf640395330ecbb2",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5135897435897436,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:33.693Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ebb88a350e6585967da2d422",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6879102564102564,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.064Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1155268c681c6ea38f21f738",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.39149152167507034,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:22:01.096Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "17d3728a6ff75738da4c2906",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5309971738916901,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-02-06T20:22:01.096Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "fae3fd663f7b9c07d05f1e9d",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.375Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "161ac532063c8417eb653195",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.48717948717948717,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:33.693Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c5609e78b3369ec449355e47",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5921666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.064Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "271e3e737dec04273c666ec6",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7836538461538461,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-11-05T06:02:00.487Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a866048f5dd2c25cbef3a4ca",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3149999999999999,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c9f03b3028cca82d82d786bb",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2894745650252112,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:01.096Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c72adf6457a1956b68a202f1",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-haiku-20241022",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.57,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.227Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c812f397200bc11eba700b3b",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-opus-20240229",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.014154704944178614,
      "unit": "mean task score",
      "sampleCount": 4,
      "asOf": "2025-02-06T20:11:23.068Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0fae2f3341ab7faeabf2581a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-opus-20240229",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.014154704944178614,
      "unit": "mean category score",
      "sampleCount": 4,
      "asOf": "2025-02-06T20:11:23.068Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "833010df7a00f27fcd44eefb",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.02830940988835723,
      "unit": "mean score",
      "sampleCount": 2,
      "asOf": "2025-02-06T20:10:21.413Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8340d71648dd34b81ea296c8",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 2,
      "asOf": "2025-02-06T20:11:23.068Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4047238423cf75dda8db3fd5",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6084615384615384,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:22.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d974cfea61e9ebebe8c6337f",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7186730769230769,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "07f8cdb85de932b55c7f6f80",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5507573958974694,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3396743cd912b334ff836210",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6259640037606949,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2024-12-10T19:31:50.213Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "19b07e2c56477b42d9de2c3a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.64,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "adde346fc55e262e2932eaa0",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5769230769230769,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:24.301Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3ebd9d8202075750ac62dcf3",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6793333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0becf1ee24f6e3fc9c814358",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7580128205128206,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-20T18:05:02.067Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "be2f2e2e4bb8f58ed947e587",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.44083333333333335,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b5e9be885e4b3c5b9c0719ce",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5514388543590749,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:34.346Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2a100947963ca0ff6c28bf7b",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20240620",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.66,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "554f891af78384a319e7c187",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6712820512820512,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:52.245Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d663f58dbf1d1cf31211472d",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7025897435897435,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.782Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b2bd6a685ab1c16cc9aeb056",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5621366956435607,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:21:54.931Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "61d00d40e528ae7dd0297358",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6453361635051185,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-02-06T20:21:54.931Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "45e0ba95d07334e869256e72",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.74,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.969Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5fa071c58f2ad939eb3a98ab",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6025641025641025,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:52.245Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "63d4fb84b524e97ed806a673",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6679999999999998,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.782Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "02070ed5d0230fb8670ed3aa",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7371794871794872,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-10-22T18:12:04.499Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dd72b1846f46b41fb7743d79",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.49666666666666665,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d4b52a388783bae79202aa57",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5197434202640157,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:54.931Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2719759ad60e5d839b08129f",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-5-sonnet-20241022",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.67,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.157Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "47648f068a32b28c2e4a9194",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6748717948717948,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-24T21:32:03.431Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7cdcbfc99a4bfe73012f8e68",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7788333333333334,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-24T21:32:06.285Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b44075aaeff96eabe2e3a82a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5988878581845517,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T22:10:26.923Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e488f192436b91b5646f8562",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6841976621298933,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T22:10:26.923Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "807131d074fe3a7706ab842c",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.76,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T21:31:41.835Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d93bdd72ae9a750b07412fae",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5897435897435898,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-24T21:32:03.431Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5a284a64f5eb1cd54b92375a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7788333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T21:32:06.285Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d1577a80ca1a6e1f0a3b0162",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5583333333333332,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-01T22:10:26.923Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7c01d1bb56ea04cf1c56c6a8",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5583302412203217,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:10:26.285Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bc2e46e4c79a786a3fe3b663",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-base",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.68,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:08:14.046Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a34afa44d109ab81a8ea6621",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.7153846153846153,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-24T23:09:55.270Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d83714b59852d59021f192ff",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8315,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-24T22:46:53.100Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1070a8e30f8ea3f201cdb052",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6096253596662211,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-02-24T22:43:30.276Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "48077f4d8804e27481bf9090",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.7188366583502788,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-24T23:09:55.270Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "61ef1a041d3ecd5c18838215",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.7,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T23:09:55.270Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6ba092d92e1475ff7925d1a1",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.7307692307692307,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-24T22:46:52.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8eda212a755b1bf67992cf85",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8315,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T22:46:53.100Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64dde65601313a13a8d08bfd",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.7016666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T22:43:07.192Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8dd1f20ca23a4c842eda7017",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5472094123319967,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-02-24T22:43:29.427Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "252f3a42e2989026e9784bea",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-25k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T22:43:30.276Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a78eac77763d97b16e46ebda",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.7453846153846153,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-25T00:23:19.631Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1e70185a776128daccd0a66e",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8568333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-24T23:55:16.262Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "878077dfbb6675b828e9a1ed",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6408129380176556,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T22:08:11.471Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b78e15d67d806adb98efe1e8",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.7476769622452014,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T22:08:11.471Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "413d75fc6aa034d223c9d4fd",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.76,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-25T00:22:33.789Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "488f3652493e6ba283543dc5",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.7307692307692307,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-25T00:23:19.631Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2f3cc8fa2a04fc4d0dd91b0a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8568333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-24T23:55:16.262Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5cfc6dc3eda2f3ba61b2519b",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.7133333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-01T22:08:11.471Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d0276019e43c28d3bcb616cc",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5591054807196336,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:08:10.622Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f9bcefe5a1b9cef61bc176e9",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-7-sonnet-20250219-thinking-64k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.65,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:05:04.408Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "61fa6d91bb23c1344a2f5761",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.24461538461538462,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:22.684Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f467cdebe166e5de79080237",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5698717948717948,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-12T19:21:56.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e10e74862f13752a4e6fbbc8",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2960118132067821,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5cc11f92488fcaf622a6ea8e",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3701663308979872,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:31:22.684Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ed8744a23ae33bb98a8fc082",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.22,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.113Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8fdae8337b519e216845bbac",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2692307692307692,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:22.684Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "54e00667ddc7bc5f790a654f",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5291666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.171Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0bfe43bb641b789874e29583",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6105769230769231,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-12-12T19:21:56.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7372f38c0194398d1ebf94ac",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.17083333333333336,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "78a78da5b96dc6c3ef83167b",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.23720210628701288,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:32.382Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "67b2948c0946cb9c9cc74afa",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-haiku-20240307",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a70e0f512a1da05778586ef2",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3858974358974359,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:33.286Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d771f72acab26116606f5478",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6562884615384617,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.987Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2ab596110e96f346d216e450",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5256510572929382,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:21:58.999Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "923c395450ae967ce3ae986d",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5226123182429453,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-02-06T20:21:58.999Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ea3102c998fdedf586df59fc",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.295Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1868c5b2f8d1d98fef7c4cfb",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3717948717948718,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:33.286Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a4b5a528c0d78e71b5c3ce0a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6395000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.987Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c5ed1920f88b35de276303d6",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6730769230769231,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.219Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b1bd9b051d3b50780037811",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3499999999999999,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e8d6275b253d7c87913ff3c6",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4769531718788148,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:58.999Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5a0d3d749221d1d02619f0c4",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-opus-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.75,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.206Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "277293eb807834e36b127cc6",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.26384615384615384,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:31.427Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "29a17ff3202e86d180ad9065",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6362179487179488,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:38.914Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5c211f6e220e8a53cea43045",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3808330525959844,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:37.705Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "74356720fccfc553d455983e",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.42696571838669567,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2025-02-06T18:31:31.427Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "6cdf8a63f6538a5e4a4ad951",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.22,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.873Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "96dbfadc9ffff0407ccacf88",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:31.427Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b5ee5f81f7ea724f756e34be",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6362179487179488,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:38.914Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dbb09c1e21f6a90e28064b99",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.26166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6ce381ce5e9044c99e9ea1c8",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3408324911212864,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:37.705Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a0f252e39cd88f56959fa3a",
      "sourceId": "livebench-model-judgment",
      "model": "claude-3-sonnet-20240229",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6fae7e846ac28fc60cced34d",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5664102564102564,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:30.028Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6b9fbcdffdfe46372ddee35b",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.921474358974359,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-10-02T18:45:15.222Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fc74644d6c4389cfc7bafd7e",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3714555513298383,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:38.270Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "51f10517e7d6e9665d37a5db",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6197800555714846,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2025-02-06T18:32:30.028Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "42b5401cd5e458daa80a0a14",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.040Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1cbc1f93bf190d4519cbdae",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5128205128205128,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:30.028Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6592823fc9136b7f5d0be191",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.921474358974359,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-10-02T18:45:15.222Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c5d5443e5c7606edd67c5ef8",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.38666666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-10-02T18:45:14.623Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "efca14e8e27696e53be564ae",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.34769998732284846,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:38.270Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9b6d57322a01e78b5f7dcf27",
      "sourceId": "livebench-model-judgment",
      "model": "codegen3_5k-qwen2.5-72b-instruct-2-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "80eb632d1690363ec047eb92",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3523076923076923,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-16T18:11:13.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f065e4fd8d3c6b7e8167f6ba",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8685897435897435,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-16T18:11:14.189Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fdb1b477476f132a9c930f1e",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4176679716680938,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:12.070Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "70d28ea2b2b4ca07308a6fd1",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5461884691885098,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:12.070Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c28ef949793f2d4a03f5ea48",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-16T18:11:13.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a6f32c3185205e26d937370",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.38461538461538464,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-16T18:10:59.507Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "15f9ba4ab0da9043b4b53fbf",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8685897435897435,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-16T18:11:14.189Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "db8fc7d8273a9fa8294ec1df",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3866666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-16T18:11:25.239Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a789276489a14c4cd41e78d0",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.40633724833761464,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:12.070Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "94d0d697a7533ccb3513c28c",
      "sourceId": "livebench-model-judgment",
      "model": "coding-meta-llama-3.1-70b-instruct-chk-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1b06b91bf907656f66ba3763",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3630769230769231,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:40.964Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3d68f175b88ac7f2b053f958",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8397435897435899,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-09-27T05:26:16.152Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "97531d7f5f238d5837a15dff",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4154425242669488,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:05.346Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e670971a4f183c4a6eaea497",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5394210123624873,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2025-02-06T18:32:40.964Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "8d97ea5b1570db68750607e0",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.299Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "97e92efce3057689509a07c7",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:40.964Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0e005a363f8af3f683793977",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8397435897435899,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-27T05:26:16.152Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1a9788f48dd0a2591b2c0c27",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4016666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-09-27T05:26:15.132Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "204e567453aae74026bd998c",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.40466090613417977,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:05.346Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5fb684941057cc979c294646",
      "sourceId": "livebench-model-judgment",
      "model": "coding2-amcfull-apifull-mmlu12k-meta-llama-3.1-70b-instruct-chk-150",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "98dd034973fef0edba924c87",
      "sourceId": "livebench-model-judgment",
      "model": "command-a-03-2025",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3669621182182429,
      "unit": "mean task score",
      "sampleCount": 150,
      "asOf": "2025-04-03T17:39:43.348Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1923c7c274632b1d0782cb36",
      "sourceId": "livebench-model-judgment",
      "model": "command-a-03-2025",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3669621182182429,
      "unit": "mean category score",
      "sampleCount": 150,
      "asOf": "2025-04-03T17:39:43.348Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "5f941824ad7fd17179815d47",
      "sourceId": "livebench-model-judgment",
      "model": "command-a-03-2025",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.23333333333333328,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T17:39:43.348Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4e48c2aeda7edc820d7caff6",
      "sourceId": "livebench-model-judgment",
      "model": "command-a-03-2025",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3475530213213953,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T17:39:42.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "51d34bf71c95247feade5f47",
      "sourceId": "livebench-model-judgment",
      "model": "command-a-03-2025",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T17:39:15.753Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d4ebf9166c7c1971fc2577df",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.15256410256410258,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:42.287Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5bd73ebd99d02e6557a09894",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5769230769230769,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.162Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1ca9fc87c8ffba343e69b997",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1469968204486094,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:10.907Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "551388e4a7f8d4ceb2b814d6",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2921613333119296,
      "unit": "mean category score",
      "sampleCount": 344,
      "asOf": "2025-02-06T18:32:42.287Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c169f8d88269ebbd06176a25",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.211Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b22b85280412266a2f67f6f7",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.20512820512820512,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:42.287Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f02de94aebc2c361d7e8a455",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5769230769230769,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.162Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "502d423334129cdee56bffc9",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.07833333333333332,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-11-27T22:18:39.495Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2bd09121beea3f079f158b13",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14265712801249492,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:10.907Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "546129078ff457c181679583",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-03-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.22,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e2d0f3f59a5588dfcc576079",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.17897435897435898,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-09-03T17:01:02.762Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "83db3c6d5aa1c01596f82da9",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.640826923076923,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.904Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8c9e0c9233a79bff89a8fb1c",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2245866531984306,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-04-02T22:13:09.862Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "469bc82488fc549a0941c024",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.34812931174990425,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-04-02T22:13:09.862Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "e0a0c0c6fdd3fee6166da432",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-09-03T17:01:02.762Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "61731ebdcb8bad440a506b94",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.21794871794871795,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-09-03T17:00:56.352Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6b075d5407f74445e9280e08",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6021666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.904Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b824b147b44e61f08db921b",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6794871794871795,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-03T17:01:03.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e9d72ce5c92236a415639cc2",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.12416666666666668,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0b7b6cb8afcc29857f1286c7",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.17959329292862514,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T22:13:09.862Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "473fe28ea7535775a965d80c",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.37,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T22:12:47.006Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0cd0647e883e241ee0158b45",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.20102564102564102,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:19.228Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bb6de04900eca086ad2ef481",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6756410256410256,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.865Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bbbb25cf6f41db05ea32701e",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.21810646760431993,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "85f081606f9d8357f8308bd3",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.36492437809032885,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:32:19.228Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c4e8dfc6ac3682aee194c036",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.801Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "027707a4561bf09f72a26450",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.28205128205128205,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:19.228Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "df37bf391f2736c1b8549dc2",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5499999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.865Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "24c02dcfc6df632bcd1eb959",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8012820512820512,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.081Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7baa62a1cf165b3d9641b80a",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9021dd56f054e17ffda02758",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2543194028129598,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:07.950Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e0b9d61c78be8d77eb2086e6",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-04-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e2558d5545c578a5baf46329",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.1914102564102564,
      "unit": "mean task score",
      "sampleCount": 256,
      "asOf": "2025-02-06T18:32:31.428Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "81f84ae5d39728a06bc85ec7",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6189102564102563,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.714Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3493aab2a65007e9e4617cba",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.30857588943254105,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-04-03T16:06:02.492Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4738142780586b5b73ee6196",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3729654674176846,
      "unit": "mean category score",
      "sampleCount": 622,
      "asOf": "2025-04-03T16:06:02.492Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "e37fa147bd04018f246e69d0",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:07:17.149Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c78d1ea81a6bd1aa4ef6eccc",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.26282051282051283,
      "unit": "mean score",
      "sampleCount": 156,
      "asOf": "2025-02-06T18:32:31.428Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6611bbde0063b4700b96a9a6",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5583333333333332,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.714Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "73c43729bf05e744ac44e86a",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6794871794871794,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-03T03:46:55.016Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "90527619d3579deaeac6d778",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.21833333333333332,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "28f28429696d729efae0a484",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.23739433496429002,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-03T16:06:02.492Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "88767eb1a775be265b6b66e5",
      "sourceId": "livebench-model-judgment",
      "model": "command-r-plus-08-2024",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.47,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-03T16:05:34.036Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "943e64f06b13b5e13ae9be7a",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4609375,
      "unit": "mean task score",
      "sampleCount": 178,
      "asOf": "2024-12-11T00:50:59.859Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0a491e5916ac841d61c1c26c",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6782435897435897,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-11T01:28:27.655Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "20e38c1575b4abaf15809628",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.32089329947283657,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-11T01:19:16.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2a7d56fec30f86e346b522dd",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4866914630721421,
      "unit": "mean category score",
      "sampleCount": 444,
      "asOf": "2024-12-11T01:28:27.655Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "25be9d9e38e50d2400789a45",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-11T00:50:59.859Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "804b18d5905a4cea3812a73d",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.421875,
      "unit": "mean score",
      "sampleCount": 128,
      "asOf": "2024-12-11T00:50:58.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a910c56dc11ba7dfefa8b0ea",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5936666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-11T01:28:27.655Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a09522a34582883d1db9d526",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7628205128205129,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-07T03:57:03.246Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5786637ce23547efe8ed17d2",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2533333333333333,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-11T01:19:16.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "940fda9262224bb9bd786999",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3493465650851764,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-11T01:19:16.207Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "659b225d45a0d794dd2a601b",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.36,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-11T01:19:01.928Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6e88d75608114304e9563d6d",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.24743589743589745,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.498Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8e2925816e68a697006c86a0",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5576923076923077,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-24T22:35:44.742Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ca646147233800736fd57cfa",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.10635225440581297,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:49.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1b0dbd71be9b7dda98a81bd0",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3038268198446727,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:49.368Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "27bdc8e83771a0750712836f",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.498Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ec3e2f5f65cf7bfe766aaf79",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8883b5c00a79b0eb18d02e46",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5576923076923077,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-24T22:35:44.742Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "295ed531d01dd26621abb1c4",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.005,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-24T22:36:35.550Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7a2b25d0b37969dbf5a8caed",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.11405676321743892,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:49.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e11678fd4ce3231f9de81136",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-Coder-V2-Lite-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1cf96f8b38aa81fdc49e35cf",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.41512820512820514,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:19.883Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bc1ff94ae1421676d3987875",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7580128205128206,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-23T05:39:34.662Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b07c38f6e5e0fa8105eaf5ab",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.33043961259269233,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:15.976Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "035da4b153634bac6bac37b5",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5011935460779061,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:15.976Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9b6b6a70ae6eabcfc171753d",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.883Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3f0f3b20d924989188193c86",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.41025641025641024,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:21.773Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0866d1ffeccb19ab6cad39cb",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7580128205128206,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-23T05:39:34.662Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8e55d9d41de40af86b4415ad",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2583333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-23T05:39:56.639Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9d9c52fded755e8b8ad77a99",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3129855044447437,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:15.976Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0cffb0645bad7c4f4445fec8",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-coder",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ee2b690d100013083ace2154",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5161538461538462,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:01.320Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1bfb535ffc9c5f52d2b4d382",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7021666666666665,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-13T16:13:24.886Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0ae9429f7374cc59296e185d",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3035066582910469,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-02T20:53:51.637Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3f843febe7b82aa7abed5d77",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5072757237038532,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-02T20:53:51.637Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b78b1d3ac1f7c3313f925a64",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-28T21:56:54.738Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "18156dc51adbff7f3c7e2d28",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6923076923076923,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:01.320Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c24fa2e04b66f161a7edece0",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7021666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-13T16:13:24.886Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "639593a2bd5d6d8a5187fbee",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.35166666666666674,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-28T21:57:06.980Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e1e9bac13d2d18ecf5373d34",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.27885330820647386,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T20:53:51.637Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "990fa1ec5a86a8ed6bc84a6a",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-llama-70b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T20:53:27.234Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4363a07922a7d0d620104f51",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.34487179487179487,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:37:39.676Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "951c52876326ef090b3aba56",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3284615384615384,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-01-21T11:01:05.519Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "04d1e8ac5479358d82dbde53",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6961666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-13T16:13:25.518Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "884b767d54ad324a4b8bebf0",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.3481666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-21T12:57:53.696Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3869924557ce3874945d2f9d",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.26592880469728003,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-01-21T15:02:57.936Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d6887a1fcde38d529baf42da",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.28865373832364044,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-04T16:14:44.063Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4fe0571fba314fc7a54412aa",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4432307332873673,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-04T16:14:44.063Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "82ad215ea158798e2fb78ed9",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.31418566994182834,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-01-21T15:02:57.936Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0dab5e177338e04c53a6fd8e",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.08,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-21T11:00:47.779Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "436af331ef9302d61c54a725",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T18:37:39.676Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0d256b29011982ca28d99167",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5897435897435898,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:32.619Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "209b9607ffd2eb41effffa0e",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5769230769230769,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-01-21T11:01:05.519Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b6ef17ce74250d76ada581d",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.3481666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-21T12:57:53.696Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8f8744149b1743200a388dc",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6961666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-13T16:13:25.518Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8c3f0848b8d338e1d6c14621",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2583333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-21T15:02:39.076Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b48592f2b1849e49cdd31e3f",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2583333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-04T16:14:44.063Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e67f19c88de0aac4a1ec47eb",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.21945308075850675,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-01-21T15:02:55.980Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "eb6ea7b9c251b05c6ddaa134",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.19762788163758813,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-04T16:14:43.529Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "40115a8843bd34c1538571e9",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-R1-Distill-Qwen-32B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-21T15:02:57.936Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "701a6bc0fd1381ced52304be",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-distill-qwen-32b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.41,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-04T16:10:17.534Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a7e1b1106153f9178acb9233",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6730769230769231,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-13T15:48:54.956Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d2df272355265bd5ed473d72",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8571666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-13T16:13:24.226Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d554542dc6d12b73691719df",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.49926906428786594,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-02-13T15:45:06.378Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cbdf48e4d7d5901a265874dd",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6765042180104852,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-13T16:13:24.226Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0ef1339e5699b648da3f7bee",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-13T15:48:09.570Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bfd82653058b1bee8df80e55",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8461538461538461,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-13T15:48:54.956Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "136c082c135f5c1ab139a9ef",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8571666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-13T16:13:24.226Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b6daf83ca3c2ee3a61a280f",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.6866666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-13T15:44:29.238Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3d9d241142b9d62138ed90dc",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4311405261969313,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-02-13T15:45:04.917Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "664cafe69969fd9633412775",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local-2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-13T15:45:06.378Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a3b62d8a85df90d0d2e19807",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.8787878787878788,
      "unit": "mean task score",
      "sampleCount": 33,
      "asOf": "2025-01-30T16:10:07.854Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "91d0a14f039324936ed488c0",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4653645709471664,
      "unit": "mean task score",
      "sampleCount": 37,
      "asOf": "2025-01-30T15:53:02.421Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d98b84dae49f74d46e6ac027",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6720762248675226,
      "unit": "mean category score",
      "sampleCount": 70,
      "asOf": "2025-01-30T16:10:07.854Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f8f8cbf61e27292732899dd6",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8787878787878788,
      "unit": "mean score",
      "sampleCount": 33,
      "asOf": "2025-01-30T16:10:07.854Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8ff90b3ae4df3b2815ab5d9f",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1-local",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4653645709471664,
      "unit": "mean score",
      "sampleCount": 37,
      "asOf": "2025-01-30T15:53:02.421Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b453205dce6554e07ced1e46",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6738461538461539,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:54.341Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6dd87d51125bec107e8af780",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.806,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-20T17:06:27.813Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9fd6a166c664d0c7cdd0ac34",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5209469225030823,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-03T18:25:01.090Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "45c7cf200b72651ac9b88d8b",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6669310254497454,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-03T18:25:01.090Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "aabb94c4972380db3b7a371b",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-20T19:34:54.187Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3e632e06048ca78ad90ec6ae",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:54.341Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5e274a1b3d9f36326e150526",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.806,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-20T17:06:27.813Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "008adef63dcb9a5bb2f83c04",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.675,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T18:25:01.090Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "037aefd50b76077bc96bcd5c",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4078407675092468,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-03T18:25:00.554Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ea753ce28e7730d6d0c4c508",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-r1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-03T18:24:35.393Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f78fefbc8e32f2c2132d1b16",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.07128205128205128,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:18.380Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dacb8ca1e961bb08ec4e1ebf",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5673076923076923,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-24T22:35:44.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1f6eb1a8687e0f580e524b30",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.09204442661895802,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:06.045Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d93b839952d4bcca7608098d",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.24354472340290054,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:06.045Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "7638eb6a1667f80580acda67",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.380Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4aa02dc24ce0bd9a50b123bf",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.10256410256410256,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:20.268Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "98bfc08f9f9c7704cffb69ff",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5673076923076923,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-24T22:35:44.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "437a493aea63fe9086a26fcd",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.02,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-24T22:36:35.561Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2adb101ae17409dbcdbd0fa7",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.0961332798568741,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:06.045Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "656a4f4a522d79aca2a8f354",
      "sourceId": "livebench-model-judgment",
      "model": "DeepSeek-V2-Lite-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "afaf64f100f49eaa2073a497",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.7089743589743589,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-24T21:27:01.956Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b1dfe195069df62f359f6bc",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8678333333333335,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-24T21:27:03.706Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4283df7cf30eceedebe40315",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4782109979039202,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T22:00:47.885Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c229807f2ce9967f1f815ae1",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6850062300705376,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T22:00:47.885Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d929fd6e745de72517eeb20a",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.7,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-24T21:25:56.651Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3590730dbc9e7837ffe5ad0c",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.717948717948718,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-24T21:27:01.956Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "780129dfc2170f38e0fbadc2",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8678333333333335,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-24T21:27:03.706Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ee6c3c44f40b2047b203e2b7",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.44166666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-24T21:22:01.618Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f4543a90063a329dfcc9b861",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.452966327045094,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:00:47.885Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d73c9d8f890accb9010fe1c1",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3-0324",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T21:58:56.727Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6b7778b0e6c9d3ce8fe6be7c",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6176923076923078,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:24.389Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4fa8a74a37724698d173c2da",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7551666666666667,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-27T02:54:14.415Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ef590ce0c11649da24c2408c",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4414360033881666,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T21:57:19.993Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ef89204997add702265a1f3f",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6047649925823803,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T21:57:19.993Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f016b5761fe77d2da2127b75",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-26T23:43:45.851Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0b481b3679099cda1f0908c7",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6153846153846154,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:24.389Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fde2945ca307a3328655f8ce",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7551666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-27T02:54:14.415Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1f42eb3f3119fd28cc35d3ce",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.32833333333333337,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-27T00:05:37.941Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b7943bcee948a372622b281",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.42597467683116647,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:56.241Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0d8d0bb95fc261487cc7305e",
      "sourceId": "livebench-model-judgment",
      "model": "deepseek-v3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.57,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T21:57:19.993Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5d8ec58fa08fae387eea480e",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5892307692307692,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:22.047Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2a20ebf0f589f9b96ad9f792",
      "sourceId": "livebench-model-judgment",
      "model": "Dracarys2-72B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.645,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.282Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "56b6071e9d4c54a5f1e035ca",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6359999999999999,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-29T19:29:14.514Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1c1194dc581d8dde26827fc0",
      "sourceId": "livebench-model-judgment",
      "model": "Dracarys2-72B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2766666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "62a5a271d0c1d4491ec4093e",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3351118789462624,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:03.966Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4cfb700a22c72db7bc79b46a",
      "sourceId": "livebench-model-judgment",
      "model": "Dracarys2-72B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4608333333333333,
      "unit": "mean category score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:50.282Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ac9ed8460de5f91012785fbc",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5201142160590105,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:03.966Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d5f8c8160e85e5dc7a5b7175",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.64,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-29T18:39:31.719Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7bea67239b060c7c5416ee1f",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5384615384615384,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:22.047Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2768ce917a1b1bcec57b2706",
      "sourceId": "livebench-model-judgment",
      "model": "Dracarys2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.645,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.282Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ba65d47b475b6f0cbeaa038c",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6359999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-29T19:29:14.514Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8e9820a111601407351ac011",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-29T20:02:39.070Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8eb63547f2e651f3b405f94a",
      "sourceId": "livebench-model-judgment",
      "model": "Dracarys2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2766666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8206841738528d03090cb96a",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.325335636838787,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:03.966Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bc8ff9c65b41dda67c464c0e",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.258Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d9c483e5502941f5e7845be",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3630769230769231,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:15.348Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8baf0a64b45782bed98d07d7",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6671666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-30T03:35:46.360Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "366c4a5ce4cf327ddbbc63ea",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4047568367639918,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-03T17:57:51.026Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d154f1a9feac35f04852ab8c",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4783334755025271,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-03T17:57:51.026Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "bb9bc7bfd35007a903de61ec",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T03:35:32.838Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "31b209ff5e87e0c7167117ab",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:15.348Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a0f93971d07c3b933ed5dc16",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6671666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T03:35:46.360Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1fe801a5cf99bbf34e79083",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3016666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-30T03:33:54.448Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "68f2780998530bce5cd7db32",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.37260384362530885,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-03T17:57:51.026Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2c5bb0f8f108bec04c21eab3",
      "sourceId": "livebench-model-judgment",
      "model": "dracarys2-llama-3.1-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-03T17:57:22.155Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "604b9de55d60dc628f2d1a09",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.34307692307692306,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-12T18:18:57.515Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2f91c3ade72070774180e222",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6361153846153846,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.852Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f99f726ac58b040f1f569a8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.31266576229951304,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-12T18:18:58.583Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c61f97d033a079ed34ed4732",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.43061935666394024,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2024-12-12T18:18:58.583Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2233899aab9e3cfc67165db5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.550Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ffbf7bc2468464e7bcf989d0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-12T18:18:57.515Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95ba63a94e0e912d5458ad86",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5446666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.852Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "89635f5ff76c743ef88fb434",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7275641025641024,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-14T19:20:42.269Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1a294bcba22a47e25e1e37dd",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "96dd5c976835c8cf51f6afec",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.29799728689853905,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-12T18:18:58.583Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7072eb5bfeb72b25aeca5593",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-12T18:18:58.083Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "170f55c938f8e833d8ecbe6b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4187179487179487,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:33.635Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c27f926f69642ba3c56dd09e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8375448717948717,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "292e7e1d8797346113092212",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.28728322609360313,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6a95f0498657ddd10e27eb57",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5145153488688078,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:31:33.635Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "e4e52650c81094a3f32ba7a4",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.416Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9743c0bc51931317bb7993aa",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3974358974358974,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:33.635Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "434f0066936b0dbcb5dc6b3d",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8064999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "283b2109763eba2eec27ab72",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8685897435897435,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-25T00:46:38.655Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "28974e838c519998d040481d",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.26249999999999996,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4201fe9e0a9513908e227f61",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.31934967828080935,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:49.202Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0e216eaf6b73009106b68203",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-002",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a0a093567a25978ca284d351",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-001",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2286784109007867,
      "unit": "mean task score",
      "sampleCount": 150,
      "asOf": "2025-04-03T15:59:13.845Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e2eebfb0a4410574f5b7d11a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-001",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2286784109007867,
      "unit": "mean category score",
      "sampleCount": 150,
      "asOf": "2025-04-03T15:59:13.845Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9d076fd814f7358fa3a6bbde",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.11833333333333332,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T15:59:13.845Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a208514428560b9c45c19dc8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.18770189936902681,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T15:59:13.341Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3b152d040acb37f24e4f54e0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T15:58:47.578Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "16793ece32fadaa6a901e0b3",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2874358974358975,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-30T16:43:09.865Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "44dede21dc4c34534535e80c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.768474358974359,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.078Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a9be90b7fd875858c48e8beb",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.21659350354460405,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "19d568b5b623c749f6208490",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4241679199849535,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2024-12-10T19:31:50.078Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "425886988aaf518d21117e56",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-30T16:43:09.865Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "334117d46586977e6ce2a6c9",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-30T16:42:56.114Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7a71b64bd8397c0bc6867a37",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7356666666666668,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.078Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c19582f656dd4f97abd82149",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8012820512820513,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-30T16:43:11.094Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9e5cdc7bc6f59befe7b1bc95",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.17916666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "61117bc22c19926a87dbc8ee",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.17061384396714557,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:26.670Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "90cd38812abc29b66a10255e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.3,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f042711dbdc5ad0f6b06966a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2866666666666666,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:04.454Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e7cde8d47897291d541a0124",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7343333333333334,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.742Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3cf437c94ab073fe46fe5e65",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1912985495349778,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5bb0faeb9fe84c56c21e5671",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.40409951651165926,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-06T18:32:04.454Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4c864787612384d6979f613c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.473Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "951346719d68a38fa5617a49",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3333333333333333,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:04.454Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5a09a25fe7c9c7d023ae6335",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7343333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.742Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "539b85db3e7c7186e0ae99b9",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.14833333333333332,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a4a5cadfcc948f689a441ae7",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.24556231527160005,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:56.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1c6ea77e914034563da356d0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-8b-exp-0924",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7f105df756f3542abee45082",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.40354430379746836,
      "unit": "mean task score",
      "sampleCount": 129,
      "asOf": "2024-12-12T18:59:01.968Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "56358148a01cd9de8450e8e2",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7999743589743589,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.826Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c8c06c7e4230216ac5a20d36",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.30320934164672736,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "31e0861b0238e66dcae7a342",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5022426681395182,
      "unit": "mean category score",
      "sampleCount": 395,
      "asOf": "2024-12-12T18:59:01.968Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "19c88433619299e6c672bcad",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-30T03:42:42.419Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "00f81a12364055701e8d4542",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3670886075949367,
      "unit": "mean score",
      "sampleCount": 79,
      "asOf": "2024-12-12T18:59:01.968Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e9c2f028e171ed09a097b6f5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7361666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.826Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b7838bc124d44e03f3a2682",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8637820512820512,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-30T03:42:43.350Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "76c9591c3c55731fd772cef7",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.28333333333333327,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "86c06c04b0207690b56e406a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3462946916068488,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:03.329Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "49dc8a2202e7d532756d341b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-flash-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ced7af668c2cec78f67f05cf",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.32307692307692304,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:53.964Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "86855cadca41f2c021eb9880",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.681775641025641,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.241Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9bef5ac636b077f3558eb101",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.39307443152816646,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ac8e077374e403ca2e77a650",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.46597566521024353,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:31:53.964Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0ea00f3a9fd76374f15a7a58",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.3,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.708Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ce5192ce81df33d7a686dd83",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:53.964Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "04d99e8a7fe8ebfa843ffc7c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6439999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.241Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d3bf2b22b2463608fe8f95c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.719551282051282,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.015Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8e285ff8387c2d5e9170077",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.22,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "54686b33da1bd039afd9e5e4",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3992232945844993,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:36.541Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fe80e50a711fad53ffc9e20e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "de5020639b246b7d930029ee",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.48794871794871797,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:39.028Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1e5cc47e3d48e4508497c652",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7721410256410255,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.027Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b18c90325f5882fe3266616",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4309920241278662,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:21:59.583Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "be8871e47bf22c11a6723c31",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5636939225725365,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-02-06T20:21:59.583Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0f3576d42e1208e246c829c9",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.958Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "54b9238d9ad71e393f8e549b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:39.028Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "51964e2c3ca913bec0d08ff1",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7429999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.027Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "687491ae19617e20b0c843cc",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8012820512820512,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-24T22:51:57.351Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "91582c04ad5ab7acb305d646",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.38833333333333336,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "701fd782346a91af7b0c5f05",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4246427390502652,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:59.583Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3ad22331b42f488b53a40e0c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-002",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.210Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "17e628d5bdd8e55bf2574d70",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.409873417721519,
      "unit": "mean task score",
      "sampleCount": 129,
      "asOf": "2024-12-12T18:57:05.893Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cb8e1caba3029d9e1df61feb",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.782051282051282,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-03T03:08:49.558Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a68950db258c04fc91ae956e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.46957258149718645,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:01.199Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c188757ae5d9b94d264f82e9",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5538324270899958,
      "unit": "mean category score",
      "sampleCount": 295,
      "asOf": "2024-12-12T18:57:05.893Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d0dd0e8a362128d598f00512",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-03T03:40:49.548Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bdf1510c85e542c2db2fa97b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.379746835443038,
      "unit": "mean score",
      "sampleCount": 79,
      "asOf": "2024-12-12T18:57:05.893Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "557435e3aa2c8afd856a4b5e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.782051282051282,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-03T03:08:49.558Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a205b585305b842571ffb39",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.37000000000000005,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-03T03:09:00.204Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6401fa37f6440ef274896d93",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4187177444915591,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:01.199Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "387f2d49d22863bee9be2599",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0801",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9124481c7c821a7c2fc7a47e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.41430646332607113,
      "unit": "mean task score",
      "sampleCount": 132,
      "asOf": "2024-12-12T19:20:47.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3fd6f35223c5f2576b0b6b23",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.736301282051282,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.351Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a9278c117abe8de25a9db417",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4772953028718783,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "089ca3d43afadc6397639db5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5426343494164104,
      "unit": "mean category score",
      "sampleCount": 398,
      "asOf": "2024-12-12T19:20:47.336Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d2a3d266f3b60bdfaed96e37",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.47058823529411764,
      "unit": "mean score",
      "sampleCount": 51,
      "asOf": "2024-12-12T19:20:47.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1a15655d8a75b28ce49f8181",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.35802469135802467,
      "unit": "mean score",
      "sampleCount": 81,
      "asOf": "2024-12-12T19:20:46.722Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e72d846ff09f2b56e92a8ba5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.721,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.351Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "29ac620ab0b5c6215ccc982e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.751602564102564,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-28T02:14:14.518Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "92b4b50e9bba633d1e48e2ce",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.37749999999999995,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "961bbbf55c5c28384c5faed6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.43438590861563514,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:42.189Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c33e1266f6432e5db4df2c8b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-1.5-pro-exp-0827",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c2f1ee618d3f802601717fad",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5392307692307692,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:27.873Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8640bb6976126e40b0711172",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8553333333333335,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-04-07T17:24:31.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "31001f7b5dbe7233789724a5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.41371745206135424,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-07T17:27:52.860Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a3885bb6eb401fe23005b737",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6027605182084856,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-07T17:27:52.860Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4378c8930529bc69e7003922",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T20:00:49.678Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6da414bfe7f79ad2ce2c55dc",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5384615384615384,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:27.873Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "afd26db5cb9865a1df5299d5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8553333333333335,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-07T17:24:31.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95097d05d9afe6e2f2375738",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.23,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-07T17:27:52.860Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2cb43832e2bd24ec491c0a31",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.42115235618406266,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-07T17:27:52.377Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6019c2918acf931a60d38dd3",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.59,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-07T17:27:26.576Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0380f64bd147f3ca259ec35b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5435897435897435,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:44.290Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f8de0db1532a5449ffdd5142",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.805,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-11T21:42:47.656Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e52ff046687b8c62fe50b99d",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3868700182022427,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:04.946Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "730f38b0736c3c0a66b8d7b9",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5784865872639955,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:04.946Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "1a5e29f2a67642c9c602f344",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.6,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-11T21:42:37.253Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9f0910d1faa523c3a74acb6d",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.48717948717948717,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:44.290Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4acd14b27e0dd153263b4de6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.805,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-11T21:42:47.656Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cfade9ffa1c203ec8a773cef",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.17666666666666664,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-11T21:42:47.285Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "23c153fa63ca2e808f4627bf",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.39394338794006145,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:04.946Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e7973b3a3e688059494e2be6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-exp",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.59,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.271Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "670c6ea35dae5823ce6e4e46",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4707692307692308,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-27T16:22:55.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6deeb1864854c19b25e49053",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7844999999999999,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-27T16:20:49.775Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d5b8c2ed519ece287baac6aa",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3360258035788119,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-02T18:28:49.515Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a80124acbb41dc4dc57e6a4e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5304316781160142,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-02T18:28:49.515Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "eb48cc5f4f643ba58a6a6cd3",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-27T16:22:26.452Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "759fee1008770d17e51655b2",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.46153846153846156,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-27T16:22:55.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "82c87a8710652555a598ad43",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7844999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-27T16:20:49.775Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a5f2a4bee8b52e4be7bc2113",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2516666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-27T16:20:19.110Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7e79931d5f5a16cb927f5088",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.28641074406976885,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T18:28:49.515Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a91a173cd43129d6954c87e8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-001",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.47,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T18:28:13.110Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "767b3d685f51c96f29370341",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4379487179487179,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:23.697Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aa44c81b6f9db084c5c26257",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8420000000000001,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-05T17:07:09.441Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5c6e4dbfec9d78a85035e6e5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3536685280859783,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:03.018Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fbf858efe4be4703c6ccf6dd",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5445390820115654,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:03.018Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c268f81328add88db8805778",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T20:05:04.461Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64a9b912597111d06abbcfc1",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:23.697Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "040116431cd378b38f82b5b8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8420000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T17:07:09.441Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b01c2049e407eb28579618c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2333333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T17:04:43.461Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "537eb45e11a253c31e532664",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2976722509246015,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:03.018Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f1a46ba634f4e7f6a3f8311b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.53,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.249Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9cdbca443f09a2b29cda1129",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5348717948717949,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:02.820Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3e676e25df496db05e6f962e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8168333333333334,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-23T03:19:15.060Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "424389b8abaf0304224e0d82",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.45169239010703927,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:00.494Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "da2195b2adca4b9f67ca00f0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6011325061040559,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:00.494Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "521086e92dfedb194ac5d36a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-23T15:13:02.712Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "721f164a1229e4a3e0df37d0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5897435897435898,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:02.820Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "91e2e3a1a97b425829643ca8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8168333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-23T03:19:15.060Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dff2b17ee034810cecf7167f",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4883333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-23T15:28:20.117Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "43b67ea7fbde26260b9c2f85",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.39674383698778437,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:00.494Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7f472760d7bb9ca01ee46230",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-01-21",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.47,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.219Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f167d3eadd7e0ec6da1e1d24",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5312820512820513,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:45.628Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d1bee60a05aeec6b0b8fd0b8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7591666666666668,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-20T22:39:35.605Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c023e30172255a269bc004db",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.41045045062403224,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:00.176Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "56710f2672072e60d72955b6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5669663895242502,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:00.176Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "57ea9d8b20cf7ab3539fee3c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-20T18:33:10.503Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e50f2744e107c75f3a1e7637",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6025641025641025,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:45.628Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a6af4db5c947d1d99eb2660f",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7591666666666668,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-20T22:39:35.605Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21d57ce67964f71b2947667c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3016666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-23T18:06:11.633Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "147eb561275631c328d1107e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.34968468520543006,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:00.176Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f62bf0ae381c6dfe08b907a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash-thinking-exp-1219",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.218Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "424f0aceb3846b0874292c3b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5208072318735761,
      "unit": "mean task score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:22:02.081Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1f5ec0f57b92548cf58a968",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5208072318735761,
      "unit": "mean category score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:22:02.081Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "6824b62af85a4dfab286a357",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.38161446374715224,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:22:02.081Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d39e0c5957d0ba8f15f8526",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-flash",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.66,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:11:27.236Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bf1d699915b1de1aa665e37c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6348717948717949,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:37.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5889a7e6dcc07d6fa1159247",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8275,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-05T19:07:02.706Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd8f672fee2f16f833b9dea2",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4854294640230547,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T22:08:39.309Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aa3e9f520eae85d4b10a8fc3",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6492670862982832,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T22:08:39.309Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9808f7a448f0be55fd906902",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.68,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T19:04:51.271Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "76fd159af09e9f22e179650d",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5897435897435898,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:37.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f2b311a9a0a1eae128bcf7ce",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8275,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-05T19:07:02.706Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2297dd588c7b5947947a029e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3583333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-01T22:08:39.309Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5f864ad9165b764522c438fe",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5079550587358306,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:08:38.495Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2eceff44ddd9d59091668dc0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.0-pro-exp-02-05",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.59,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:05:20.533Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "26a71997ff163419ca610f0a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.8587179487179487,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-25T23:05:58.594Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "956168a8a4ccb3de2205cf18",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8095,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-25T22:59:57.611Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bdbe5f15327fefeba60fde44",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6846474286619509,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T21:59:47.639Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "57f2264e53986abbe40b9e24",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.7842884591266333,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T21:59:47.639Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a7f5890d72d24129b3ce1d79",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.82,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-25T23:04:35.345Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1fc12bee8c6052d353bb4666",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8974358974358975,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-25T23:05:58.594Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "877eea2ac1a196ac499c2fb3",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8095,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-25T22:59:57.611Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c21f7f458f55fa60816bda0c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.8183333333333335,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-25T23:01:51.749Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7d8ab2c504d09c502351a554",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.6256089526525195,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T21:59:47.639Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0df2909f958fd619fcd74b27",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-2.5-pro-exp-03-25",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.61,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T21:56:41.902Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b9ce41e99a701864dac244cc",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5175000000000001,
      "unit": "mean task score",
      "sampleCount": 130,
      "asOf": "2024-12-12T19:14:33.494Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "88d0d0480f97f14e29d6021c",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8248589743589745,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.132Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4efdb3c653e525ea7cf1a568",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.41993972813781166,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-12T19:14:34.511Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f4351152af853ff77323c8f0",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5874329008322621,
      "unit": "mean category score",
      "sampleCount": 396,
      "asOf": "2024-12-12T19:14:34.511Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4ca816b4bb234ef6ba260fd5",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-11-15T23:53:48.146Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e680b5d0f15cc4fc685776c6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.475,
      "unit": "mean score",
      "sampleCount": 80,
      "asOf": "2024-12-12T19:14:33.494Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aad4cb3de48c5a1e25d289e6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8051666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.132Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "675b13094cea7636d5fe6783",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8445512820512822,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-11-15T23:56:14.866Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "162588b8ad3a2d12376eb606",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3883333333333333,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "997091ac43159ba057ff8bb6",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.45148585108010175,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-12T19:14:34.511Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "871a5a9cae101f9bb1dc5861",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1114",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "050e0caffcec29a84887518e",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4975,
      "unit": "mean task score",
      "sampleCount": 130,
      "asOf": "2024-12-12T18:56:46.421Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d6d7d71713ce5cac98e1902a",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8630833333333333,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.702Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "080b88f4b1e90c39d08b141b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4107718731258679,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-12T18:56:47.394Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3b86d1b841f8a30a72f7383b",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5904517354864004,
      "unit": "mean category score",
      "sampleCount": 396,
      "asOf": "2024-12-12T18:56:47.394Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0b111785ba0157f969e88eea",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-05T21:59:35.949Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2341b9bb3d14cb71003f41f2",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.475,
      "unit": "mean score",
      "sampleCount": 80,
      "asOf": "2024-12-12T18:56:46.421Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cd200681472446c3cd6e3c1f",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8095,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.702Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3e4b4d74aa102a10bbf70788",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.9166666666666666,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-11-21T22:02:03.886Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5a7d842a13555b0dc4514f6d",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.33166666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "747e2b7975ece312b4a9eb39",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.440648952710937,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-12T18:56:47.394Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "294442c5e1ca83912fcba3bf",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1121",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "48537ddf3d5ac5f6e3c262f2",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6341025641025642,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:32.742Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4d1a93f639bd42f231079315",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8320000000000001,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.934Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d3c010807b7348e5d6d144b2",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5215833690899208,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:58.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d241f81ab319aad151cad342",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6625619777308284,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:58.336Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2b1b5e1cbdaa434c99b73579",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.64,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.800Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "51f3cf7a145964878ec02c93",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6282051282051282,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:32.742Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9ae6fe0eb30b873026fbacee",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8320000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.934Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "79d10b4791f33d9fcd300a68",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3766666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cada252f2ac9905933a03022",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5180834406030956,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:58.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4c42562bca2e9340ab5275a8",
      "sourceId": "livebench-model-judgment",
      "model": "gemini-exp-1206",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.67,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.201Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "18cc86321d779457606e0721",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.09615384615384616,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:21.122Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b4493a5ce140e08af86cc209",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5336538461538461,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-07-08T13:39:11.449Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5986a6cc7e52ad594dd24688",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1064737325057765,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:24.974Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f6ee3b8d6069c2d17dbdec0f",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2454271416044896,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:24.974Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f80bf2434075d52d9c8a8602",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.122Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "107abaf3c89fe10223be9c45",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.19230769230769232,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:23.040Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e97517bb1e14a004e3156d83",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5336538461538461,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-08T13:39:11.449Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "32e64aa3ee3895afb88d6b42",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.07166666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-08T13:40:02.917Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ecbc82dc1123db66c98d1fbe",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.12775453085066285,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:24.974Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aec04578138fba9368a36f39",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-1.1-7b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f432a3c34d6809f8bc8e1165",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.35948717948717945,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.333Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e1a8e0578aae7dbd5dfb600f",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7126153846153845,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.659Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "42fd1396db5264cdf7e1ed4b",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3384132908875835,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:21:52.929Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "569b562e96df4f099efef23c",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.47017195166338244,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-02-06T20:21:52.929Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "99d93f5328af2607d83178bf",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.36,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.333Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "16b1301115b6ba37b9d60d0c",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.165Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64ada8420cafeb0925dcd72f",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6351666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.659Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "50f619d7ac2661daa6299982",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7900641025641024,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-01T17:58:01.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "696d2c9ea48df0ef82dbd04d",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.25499999999999995,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.595Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0be5f93ea8b16d7139e8de3c",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2802398726627505,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:52.929Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "52ef0568505d40d08cdfb21c",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.136Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b802451f5f26543a7f232154",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2246153846153846,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.627Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dee9ee728716eb0527e7e60a",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5872564102564102,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.999Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e188d3168d1a444a7342e872",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2658658903530416,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0f506cd1e548801c95bc19cb",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3592458950749455,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2024-12-10T19:31:49.999Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2e7f906e8ea0979eb39fc7be",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.627Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fde979429fa123c7d2d8da00",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2692307692307692,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:22.533Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8bc836ba819792bc4607a18f",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5206666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.999Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "401528bf4737ba18bfa94534",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6538461538461539,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-01T17:59:20.617Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "26ae4824d8137e662feb8674",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.19833333333333333,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1efe290dc860b5c0893d54f0",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2192643377257915,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:19.912Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e309026dfd7fbe0a8b3365de",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-2-9b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1150dbde14b30ee4c959d78",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-12b-it",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3126965618661763,
      "unit": "mean task score",
      "sampleCount": 150,
      "asOf": "2025-04-03T16:32:12.274Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8517a7ac71daa30e97e4617",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-12b-it",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3126965618661763,
      "unit": "mean category score",
      "sampleCount": 150,
      "asOf": "2025-04-03T16:32:12.274Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2bc820b442b3882b51062be8",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-12b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.26,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:32:12.274Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "228ddaae8e7b35365cd77da8",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-12b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2380896855985289,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:32:11.762Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a25e0c14873395bec64983fe",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-12b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:31:31.126Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "86a5829d0fd28f72501ffe73",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.39871794871794874,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-17T16:57:40.746Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8ac826f9d7d409513c675dc6",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.715,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-17T16:57:42.893Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "53feb40b0146757f278849e5",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3788170080303231,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-02T20:01:05.169Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1277401f882f0148868d3c3e",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4975116522494239,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-02T20:01:05.169Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d6af571048d8d5bbdc6ad979",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-17T16:57:04.471Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9ec43fee2e62d05882dbcaf7",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3974358974358974,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-17T16:57:40.746Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1b8d6afd4d79068467c32144",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.715,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-17T16:57:42.893Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f7c144d8dee396b3b6324395",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2733333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-17T16:53:06.776Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2d48d5d6e74c87016eab277c",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3031176907576359,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T20:01:05.169Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9b7c8aae70e8f06de89b0b3f",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-27b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T20:00:45.781Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "11ae988cacbcd973b96fec89",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-4b-it",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1505925822197743,
      "unit": "mean task score",
      "sampleCount": 150,
      "asOf": "2025-04-03T16:54:09.932Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5aa03a188c52d3c68257d91f",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-4b-it",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.1505925822197743,
      "unit": "mean category score",
      "sampleCount": 150,
      "asOf": "2025-04-03T16:54:09.932Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4bab3afdcba12a9e26a61ddc",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-4b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.10166666666666668,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:54:09.932Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5dfef9d5f4857531c6c52086",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-4b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.11011107999265628,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:54:09.391Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "013ab53997a2a3a01b0be124",
      "sourceId": "livebench-model-judgment",
      "model": "gemma-3-4b-it",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:53:26.074Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2f7f417575a78315abeb1d4c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.27743589743589747,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:20.811Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0fc21a85698f4a522a76f21d",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7451923076923077,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.301Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "33fe2bd226cc7dcb41bdbd81",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.24216384728981635,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:10.632Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e946b20b1414c282c93b8bb5",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.42159735080600713,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2025-02-06T18:31:20.811Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "06aa2603c4d31710e6832d07",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.26,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.128Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0c7b8e9d200d37051a3fa4df",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:20.811Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8422a6cc4f7e342bf457b8df",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7451923076923077,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.301Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4753de135744dad4da0dc8e3",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.13333333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "97a2a60af976c7a9db19862c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.17315820853611572,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:10.632Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6f7746e4c8b54b6fd0329599",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-0125",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4c3afae7664745729c87638c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.26743589743589746,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:23.397Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd9ab382f626c9fd967bd9cf",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5128205128205129,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:38.989Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ab4e0d1585788db0e4cd24b4",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2862925713478626,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:51.779Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4bcd47e1f1e3f2961ffe908b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.35551632720142434,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2025-02-06T18:31:23.397Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a939622df0a75bacf01d5b13",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.820Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "de76bf4780cedd1c317af255",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:23.397Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a1f223accb8695c7cfd8a53",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5128205128205129,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:38.989Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "27efd91c6a07cf3e29d024e9",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.21833333333333332,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f0112f047a0ae1c9aa1643c2",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.20054438071025457,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:51.779Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0f6138df2ffe794d8eca2243",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-3.5-turbo-1106",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "121599ec5301bd9c15f9d0b1",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.41794871794871796,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:34.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "49841fa91f286ba92a30b130",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6621346153846153,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.629Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4cc2868b10415268bf67d95b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.41386615971457424,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.595Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f7051fd430a8002b71cecff6",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4979831643493025,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:31:34.630Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "67977782dee7fd99b4dbe5e3",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.086Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "11593ce18579faf8db4a6c81",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:34.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "12fd805a72bcc399b4432056",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6143333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.629Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "977470dbd06adb7813c8a114",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7099358974358974,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.123Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e0e2bae74e62861de59948f2",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.36666666666666664,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.595Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "02ecd7f155130ff58c8e699a",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.43493181247705603,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:46.661Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d27d1dbd6321bfd871e5a44a",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0125-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "45b8c8773dea35377b0d9053",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3730769230769231,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.876Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2a474399fac095de4a4475cc",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7179487179487178,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-07-10T00:22:00.980Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b89129d2cbf3bd0dc4b8f742",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4956807745485778,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:23.151Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "92d9944565706568c35ab0b3",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5289021385247396,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:23.151Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9d702fd9e17e4bdf06c2d017",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.876Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fcf7c66617d1366913e85fba",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:22.790Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "68c67cc045cdc679a0a70b33",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7179487179487178,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-10T00:22:00.980Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8e42ab65957ebaef65e1120",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.39166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-10T00:22:12.055Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8ebd153b6abc5b04aedcc0e3",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4553756569790666,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:23.151Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d11c35d5f66f897e5bc772bf",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-0613",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.64,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f0f356d14c4e22da99cc7728",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4715384615384616,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:38.626Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0069793ce903af6ddeccd897",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7708333333333334,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.328Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a884226394b35989617de7da",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4836669353197161,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:34.940Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5513528b5d5ea24925baf155",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5753462433971704,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2025-02-06T18:31:38.626Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "1e4caa54572cac5d1e8d11f3",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.456Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "78464eb89ab1ef98c79b9bd5",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4230769230769231,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:38.626Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fe96a8c5eb4f324534cb7302",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7708333333333334,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.328Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fa81b34212892fbbb06b18de",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.39666666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2f35f549cf46930c3083ac87",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4543341392924818,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:34.940Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "48ab57916ba942dc53feb3a8",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-1106-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.6,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cc775141c1d2f4bf32dddd01",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.49,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:28.522Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cca4420ca71ff4be42c57c64",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7102692307692308,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.296Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "33c9621fa114e086a9b52ed9",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.44761985724475245,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "778dc42ef58a20ffd923cc2b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5492963626713278,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:32:28.522Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "6fd8296a00a6df916ef46468",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.212Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "390b11548c54ae117417efcd",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:28.522Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "774d6da6443fd65c26e8298d",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6256666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.296Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "eb396cc7f1e101ad61bbda45",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7948717948717949,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.315Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "83d3c512543f3a8ad2eed773",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4266666666666666,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "87fd3b5821ef8634dc6fb01e",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.39619290506759075,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:39.105Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "41d54569dbac45749ba58895",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4-turbo-2024-04-09",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "047873a158102916521583ad",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.7517948717948718,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-27T21:00:43.574Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "72c7eae861d6fe1d5adf8d4c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7233333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-27T21:04:48.551Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "69c91e07e8b5c0b15f3a1fd5",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6298957787091851,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-03T16:05:01.884Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ce96f0621bb5398e7429a369",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.7016746612791301,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-03T16:05:01.884Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "65f6fd5ea7c8e805f8c0cdb5",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.76,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-27T21:00:02.026Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0632c97b6435212a3527b44e",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.7435897435897436,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-27T21:00:43.574Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bf55b5333f3c03080eee2ef6",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7233333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-27T21:04:48.551Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c4e66d1f9be9582721e76d9a",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.7016666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-27T21:04:48.130Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7124ae37373a5f942f882067",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5080206694608886,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-03T16:05:01.884Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b4343447f5b657a8d6854163",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4.5-preview-2025-02-27",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.68,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-03T16:04:28.694Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3051d197c7873c3e081d08b6",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:40.620Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "581aa3d6a8c6dae46af0151b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7157564102564102,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.200Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "554fe4828ea72734fb1a080a",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5199096596642678,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3277adf074aa233b46ae33c1",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5785553566402261,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2025-02-06T18:32:40.620Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "7b7149df7df962e5b4d2445d",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.282Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "88f4a0f8b725e44c81ee15fe",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:40.620Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d5575958a594686829423f11",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6526666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.200Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b223f753a5e32640adbb7472",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7788461538461539,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.149Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a115765495b6c01d0adbcc73",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.47166666666666673,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "78bc2ebf5393ccab0e7d3eac",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4280623123261367,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:33.340Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1fadcf180855b14547520c9c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-05-13",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.66,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "409388017689b8e4a84ae7e1",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5143589743589744,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-06T22:01:10.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "45bc54b15ad8ad92ef7bef84",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7566923076923078,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.338Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "47dde871e540c535fb9f9349",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.49856564775273665,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-04-01T22:10:15.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a0f5c93ac95cd393665238df",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5898723099346729,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-04-01T22:10:15.213Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0244e461cb222e4d0a3a8a63",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-06T21:59:43.979Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8fea0f81eaacc8d81b220e24",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.44871794871794873,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-06T22:01:10.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2c4e6952d1362c0954d0bb2e",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6688333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.338Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5b630ee4c2ce6007920c896e",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8445512820512822,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-06T22:01:11.194Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d9552b499378cbdb68ddd8f9",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.47833333333333344,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:10:15.213Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4fab607188e41e7479468b1f",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.40736360992487647,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:10:14.609Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "022e1054f8c80f045b5b2e00",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-08-06",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.61,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:08:05.917Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "798ffef2156282a8dc9882e9",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4607692307692308,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-11-21T17:52:53.901Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f52e4f588f4e348b8cee9311",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7356089743589744,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.879Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2ab351a7b4adba77ae0a1c28",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4868442986449773,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-04-01T22:10:13.776Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "26ebc361b2a71cd0459c79b0",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5610741679243941,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-04-01T22:10:13.776Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d138a1d5fc56121a23ce6f4e",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-11-21T17:46:48.925Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2eb8a1a5b99c9980de92053c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.46153846153846156,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-11-21T17:52:53.901Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6e8baa576173a47ca04f9948",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6266666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.879Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aa2598e74c5b43298e284885",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8445512820512822,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-11-21T17:52:54.650Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3f0e6a3edbb71ceeff19233d",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.45083333333333336,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:10:13.776Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1b40a628392c9404b6c4f067",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3896995626015986,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T22:10:12.924Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "13cc56e980c467f4ed341c0b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-2024-11-20",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T22:08:06.235Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4d77256a837fc6559bb6796b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.43153846153846154,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:22.196Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c946f33a4246da19ce5819ed",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6970064102564102,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.186Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d7e9d2cf99323665df4f8c9a",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.32500416290970663,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:22:03.643Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9677f2a947a74d3085da8405",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4845163449015261,
      "unit": "mean category score",
      "sampleCount": 494,
      "asOf": "2025-02-06T20:22:03.643Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "066e81ff93f7119cfe318171",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.196Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "205c38fd24097142ec52282b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4230769230769231,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:24.133Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c306fac266c039114a6ac674",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5734999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.186Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "25fdda336a8ce2d17334da18",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8205128205128206,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-18T18:40:27.650Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bebc11cee990a3890970eb5c",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.26499999999999996,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1acb6f536138ab276ff83f7b",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.21001248872911987,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:03.643Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "63d199ca193d399d2f61fc6a",
      "sourceId": "livebench-model-judgment",
      "model": "gpt-4o-mini-2024-07-18",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.254Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c0e30a92870e2b1dcf154dfb",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4707692307692308,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:20.890Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6de3dc51327ab9323fa4faf0",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6785,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-16T20:24:25.934Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5866a0fac511572f07f9eb85",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.45513472599658317,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:53.916Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "83b308bb18f750092fc5f1f3",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5348013189219379,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:53.916Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "8160241aa0061f693d5eee83",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-16T17:19:11.097Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4ea69e3ed8ef7d490b42d534",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.46153846153846156,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:20.890Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "53c2be4ba812a27fd5b1ea4f",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6785,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-16T20:24:25.934Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "11e266db36514547e0f2020b",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.33,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-16T17:33:58.690Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd47a5f50a063a2c9eee1d5b",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4054041779897493,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:53.916Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7e1bccd6844fc11753fa3a72",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-1212",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.63,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.148Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "67d24a7006535372bbee856d",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3751282051282051,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:24.767Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ecb47848ec18b1973c0ee1d0",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8066666666666665,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-10-17T21:58:46.646Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7f8601db81281de031165f95",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.39500157963642324,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:14.358Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b0b8377450e984febdffe89",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.525598817143765,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:31:24.767Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f6a0487e6a95aec5ddb98583",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.633Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0ebab09e19f6c678e8ae5816",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.41025641025641024,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:24.767Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1a6c82139c526ae4963a012d",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8066666666666665,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-10-17T21:58:46.646Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7590c6f2472c77cc6abb3592",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3383333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-10-17T21:58:46.209Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2766c1799f7e059eed31d63c",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.40667140557593645,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:14.358Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "edd8ba78434fb5468580dc3c",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2-mini",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4aea0df921ad60681a423e8e",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.36230769230769233,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:54.652Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2f678f4ba4f2c5a12f6d0bcd",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7366666666666666,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-10-17T21:56:25.257Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6e0c562c8d57177779fb553e",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3483635220359947,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:16.888Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e677efb1ead86c375038eaf0",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.48244596033678455,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:31:54.652Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "e48268ad29255f0dd4d82a95",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.047Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "12165dd7999dcab5015d556d",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.38461538461538464,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:54.652Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b23c2e1aec69796972b30b4",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7366666666666666,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-10-17T21:56:25.257Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b9a87cdd49750cff2867036a",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-10-17T21:56:24.821Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3de21eb07d9c8797e8212633",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.32509056610798404,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:16.888Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a7eae050574500f3d39ba9f0",
      "sourceId": "livebench-model-judgment",
      "model": "grok-2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7274afb28ae845c60618bc7b",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.512051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-14T18:14:00.732Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "08048a158686a6bfe9b7cad7",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7589166666666667,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2025-03-18T22:27:55.640Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fb06010d1a4c1d0bf72cd9e0",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5432941665840502,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2025-03-18T22:27:22.273Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c3d0cc8dc88f15d245770533",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6047540384339997,
      "unit": "mean category score",
      "sampleCount": 393,
      "asOf": "2025-03-18T22:27:55.640Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "88a74fc270c790b0e9aede2f",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-14T18:14:00.732Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0a19597db4c81c778b7d8bf4",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5641025641025641,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-14T17:20:42.222Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d3931290f54e546afb44ac8e",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7294999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-18T22:20:05.250Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cf5c5fc75565759aab4f8b83",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7883333333333334,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2025-03-18T22:27:55.640Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9870bef4ae03c698b353224a",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5941666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-03-18T22:26:21.908Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f9e883698368a0d1862a2ce4",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.49571583308548367,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-03-18T22:27:20.409Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "780d8414b9d7a449494ee0fc",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-18T22:27:22.273Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "529ac3ac4462a6d0ade2cae6",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5417948717948718,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-14T17:57:38.701Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c2fb3155cf773449126cbbb2",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6236666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-14T17:38:13.351Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "89446071b42d1277a24d3c76",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3775721501175195,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-03-14T17:38:37.012Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95feda1a6aefa802e52b4720",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.514344562859686,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-03-14T17:57:38.701Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "487907f5dd7a3769daf59be1",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-14T17:57:25.624Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5f6606fad77d0cde116b0469",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.7435897435897436,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-14T17:57:38.701Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d5390f902bfed7376a63cebb",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6236666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-14T17:38:13.351Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "072e8f5b4fb0f056853a2b7a",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-14T17:38:12.940Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "edffe1df9b2a6183fec18db5",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.41271645035255833,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-03-14T17:38:36.098Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ba1e52783f92ce605a5d994e",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3-mini-reasoning-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-14T17:38:37.012Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1c0045ad3760324db98ecae2",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5428205128205128,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-26T15:51:17.835Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "89e2d1591ca9a5f5e8db073b",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5133060354791115,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-02-26T15:52:10.658Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "26f1acd08c381fb585293385",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5280632741498121,
      "unit": "mean category score",
      "sampleCount": 268,
      "asOf": "2025-02-26T15:52:10.658Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "65b1f36e13c989c033661054",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-26T15:50:51.624Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4c17c7573535134bf0f2f7a3",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5256410256410257,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-26T15:51:17.835Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a133ebae6af1fa5c64f63d20",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5216666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-26T15:51:45.953Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "62c0be621d3acca5ac74a369",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4982514397706678,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-02-26T15:52:09.787Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8ccdaefe5ca42449c2af9709",
      "sourceId": "livebench-model-judgment",
      "model": "grok-3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-26T15:52:10.658Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5c2ec0ec993691a6392f4b23",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.45153846153846156,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:24.046Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "58f39628c542908ef95d9c8a",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7046666666666667,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.040Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7a522c27552bad2bc9ca0b1c",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.44771874491176883,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:59.853Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "149a2f33c1c118b2115279d0",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5346412910389656,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:59.853Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c293fc123edabf3ee3a2b016",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.038Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a1263dbadc4d07fec88ade86",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4230769230769231,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:24.046Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b36dd86f54a1b1c4c8ecd70",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7046666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.040Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "804bfe8a2a854dd57511fcf7",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3550000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8f2b9ff3af04c56497baee23",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.37815623473530646,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:59.853Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9a8b05dd303e12ac58a3737f",
      "sourceId": "livebench-model-judgment",
      "model": "grok-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.61,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.214Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "176c615cea6be31a12641b3c",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3138461538461539,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-19T19:08:37.035Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bf3d35750034405eb606146a",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.515,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-08-19T19:08:37.678Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cd2a589274db8ff0228df9a5",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.43772296039405284,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:47.696Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7577e8128876cd0eac3df608",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.42218970474673556,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2024-12-10T19:30:47.696Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "07ec1512df5d4a14d57dc8d5",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-19T19:01:52.400Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "25fbfc15b82cc57cc0ca14f2",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-19T19:08:37.035Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a7a033cd826980f7f41fcaba",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.515,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-08-19T19:08:37.678Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8c2b3455e2f82e92caf0263d",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-19T19:08:45.862Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6bbf5c11f96e5c94530cb747",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3731688811821585,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:47.696Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fc0e7d4e38a417deb9e1d4ee",
      "sourceId": "livebench-model-judgment",
      "model": "hermes-3-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.62,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "941e76c1690658b98fff4c95",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.46564102564102566,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-25T15:48:11.483Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7d7f1cf92a0e867d5fda32d7",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8320000000000001,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-25T15:48:13.516Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "50260bfbbe615ea260337ca6",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.42125240393473656,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-03T18:16:54.522Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "443233574de314e922672bf4",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5729644765252541,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-03T18:16:54.522Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0ea52c1ff17d4001564fa1b1",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-25T15:47:25.397Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0f7f7ea814413017de112fe1",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5512820512820513,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-25T15:48:11.483Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "629bb2612a3504637df8a764",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8320000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-25T15:48:13.516Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1dcc5baac291ff78d64b4cd3",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-25T15:41:16.318Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "da6c39546d5ef283c79da5db",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2837572118042098,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-03T18:16:54.522Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c55de129528f92e56fceb051",
      "sourceId": "livebench-model-judgment",
      "model": "hunyuan-turbos-20250313",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.8,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-03T18:16:11.184Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f3eea0bd961efef69d19222e",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3894871794871795,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-16T18:06:07.445Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f6606d2ebfc2b83e3ae4dd35",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8516666666666667,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-08-16T18:06:08.661Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "24dabe8d80ebd43214f22a2d",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.31168991584086353,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:09.615Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "acd0c605ea39eeb819970b1e",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.51761458733157,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2024-12-10T19:31:09.615Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "842019dc417c25455fd8e3d8",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-16T18:05:17.652Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2796c078fc2d28386f8dd1f5",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-16T18:06:07.445Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e8366211b314252d049adf67",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8516666666666667,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-08-16T18:06:08.661Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "51a4ccc7edaf326936e7d25f",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.31000000000000005,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-16T18:06:22.394Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "06b699dc967d28534eec76eb",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.32506974752259066,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:09.615Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9590c8329c658a2f5a40b02c",
      "sourceId": "livebench-model-judgment",
      "model": "lcb-math-qwen2-72b-instructv3-merged-50",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.3,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9f2ac67f404c8d7abddb0b47",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4687179487179487,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:18.916Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d4c98e1a18c3b9ebb8d0844e",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7029999999999998,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-12T19:49:52.769Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "59e161ce56e66f6ca27cf879",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3984290825210106,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:58.671Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f754bd4ce90f4d636a078861",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5233823437463198,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:58.671Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "937aff477df82e77943e5cff",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-12T19:30:21.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aa561223876df1c472f03d0c",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3974358974358974,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:18.916Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "577d1f9ddda264123829cd2d",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7029999999999998,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-12T19:49:52.769Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7091843f7fac8f95f70ae213",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.335,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-12T19:43:25.380Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ffafc80c33a47e0724de26bb",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4002872475630319,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:58.671Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b300551dfb2834f4711bdd3f",
      "sourceId": "livebench-model-judgment",
      "model": "learnlm-1.5-pro-experimental",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.201Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a339763b7f965062b9669a9",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.01282051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:18.465Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ad1be258653b86e54e0d1ad2",
      "sourceId": "livebench-model-judgment",
      "model": "llama-2-7b-chat-hf",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:32.951Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "53b28fe2a31c7f2a7b46f094",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.4503205128205128,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.055Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8c15a4d3b6d6f8da52877145",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.0685874510537095,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:06.295Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "57bd240a940cfc6a4f39c2ef",
      "sourceId": "livebench-model-judgment",
      "model": "llama-2-7b-chat-hf",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:32.951Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "608297296edd4e9cf29d8be0",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.1772428255649117,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:06.295Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a4b75457e7e4a46c7ed6246a",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.465Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "322ab68b4b505fad57426ed7",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.02564102564102564,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:52.778Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b3bd56f233fef51411373b6",
      "sourceId": "livebench-model-judgment",
      "model": "llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:32.951Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "120e992400072f8139779e25",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.4503205128205128,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.055Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c78dc7d56bf9cfb24bd869b6",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "57ddd9d784390b49786d8c31",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.1057623531611285,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:06.295Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e90b4fb1f346f363a544ce21",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-2-7b-chat-hf",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a649ff461d6427f9ffc1d84f",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-3.1-Nemotron-70B-Instruct-HF",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5285,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.364Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "458be0357929b7609236b8fd",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-3.1-Nemotron-70B-Instruct-HF",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.25666666666666665,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c81a6893ca93b649fa0ab692",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-3.1-Nemotron-70B-Instruct-HF",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3925833333333333,
      "unit": "mean category score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:50.364Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a5b8c3d4acad8395169e09b7",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-3.1-Nemotron-70B-Instruct-HF",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5285,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.364Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d2df28449cc72207472a7beb",
      "sourceId": "livebench-model-judgment",
      "model": "Llama-3.1-Nemotron-70B-Instruct-HF",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.25666666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21f579ef1edc808411bc569e",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.32666666666666666,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:33.972Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a3c3312a46e446c608e094df",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6966666666666668,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-10-17T05:58:45.819Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "786e520d7bed18663993731c",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.34471628078827304,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:11.477Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "84e4e0bcd794b32733142a48",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4560165380405355,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:31:33.972Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9f261d9386ae7c40b12fdd89",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.296Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e06862051640a584cab0eed1",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3333333333333333,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:33.972Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b73a31f4e749ec7933c4144",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6966666666666668,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-10-17T05:58:45.819Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7e2001a901dc810a23441160",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.30666666666666664,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-10-17T05:58:45.481Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d5f6bc12f7693ee7e9c4813e",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.38748217569815246,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:11.477Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "115d7a79078acb74d6c5d006",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.1-nemotron-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aafaa119797f05ba95484556",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3658974358974359,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:38.249Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "495d2f23ce0d1282463d1076",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.782,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.160Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6fa69f704327f409a79ffd6a",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.41476013316699817,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:03.353Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7dc95ba252b3b03c275ea4b1",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5208858563548113,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:03.353Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2ac981dfb2c56d9a529887a0",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.36,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.035Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "78e2af3c4663cde90e32fae7",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3717948717948718,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:38.249Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fe0e45e7d51163d49681f631",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.782,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.160Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1869292a86ef8c681762805b",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.36666666666666664,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "401b65a63a14b46e813fc9df",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3776137328343279,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:03.353Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "361fae6477e7e3c38566d714",
      "sourceId": "livebench-model-judgment",
      "model": "llama-3.3-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.254Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "04bc088cea16ccda44d2e756",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5064102564102564,
      "unit": "mean task score",
      "sampleCount": 90,
      "asOf": "2025-04-06T00:20:15.928Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "441e1261416dfb98b1e7e890",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7958333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-04-06T00:20:17.613Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "075a8f9ff8fc46e96ce29e1f",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.47871179773592304,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-07T16:07:43.128Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a8d40c3e004ce6855139e5c4",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5936517958265042,
      "unit": "mean category score",
      "sampleCount": 380,
      "asOf": "2025-04-07T16:07:43.128Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9681f4f62a2e21444fa2959f",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 12,
      "asOf": "2025-04-06T00:19:08.116Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0c0538da3e1bdf64b3aec9ab",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5128205128205128,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-04-06T00:20:15.928Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5728fe5b17a0432fc79f0d69",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7958333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-06T00:20:17.613Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b2b7a2efff930a03d7dbcdf6",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5383333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-07T16:07:43.128Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7bdc81fad1b66b8ce0ce0b59",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3378020598744357,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-07T16:07:42.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2dba62a06157e167539809cc",
      "sourceId": "livebench-model-judgment",
      "model": "llama-4-maverick-17b-128e-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-07T16:06:58.504Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3c3dbed7875c642e9194a584",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.1453846153846154,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:17.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2ab6bfef971f2a64b84fdac1",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.58,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-07-18T19:35:53.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "98667bdc969a19a6747b02d6",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.15367883068692922,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:58.852Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3b22e0bc8aa801126f77ce28",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2930211486905148,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2024-12-10T19:30:58.852Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "413c5a1c0fbee14160a9ef3b",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3306e3ed29f7bf9873b3032c",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.23076923076923078,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:19.685Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "66d7c82385dc198067d97ba7",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-07-18T19:35:53.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "590830bc2f977011d0871c9d",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.03333333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-18T19:36:13.341Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "613f7ffe96937ac73c3b770f",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14770315872745432,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:58.852Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "59fd2c83eff11c5a167dc181",
      "sourceId": "livebench-model-judgment",
      "model": "mathstral-7B-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "26ba6f5de08fdee990859047",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3-70b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:14.041Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a20bcf7123a31c15e3c93f0f",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.22025641025641027,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:21.789Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3e678347e516015defac6b5e",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7900641025641024,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.068Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ac8cf427d3dfe3460cc4cc65",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3410673627139302,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:30.080Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "55e258fbd3c49cce72cac5bb",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3-70b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:14.041Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "617545dfb085af576f4d1c97",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4504626251781476,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:30.080Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "889d9e7e10ed9d9b1ee3865f",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.789Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1d7e3e67f1b28a89097a497e",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3-70b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:14.041Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d12a5d814c03eda632e6f3ca",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.32051282051282054,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:16.975Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "38b578f88778183e3907f70c",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7900641025641024,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.068Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7e71b1ac170b1d7d19c4c435",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3116666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cdec65fd2963878334d49c93",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.31153542147512375,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:30.080Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d85e545ddf65d9280578ea1c",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-70B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dd13c59d795ba20106a21631",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.1982051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:22.626Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f5573b0eba04e1e481103865",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3-8b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:42.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5e93eb58a58a140710cf7fd8",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6378205128205129,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.202Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c3fac37189557df55e9b4af2",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.18718817111460942,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:35.946Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9996d3dd43a43c25da93d4fc",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.34107127071341686,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:35.946Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f2179e8b3064691d95bfaace",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3-8b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:42.630Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "18ab28d4fabd818b41930d62",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.626Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "39503cec9038418c6b79acf1",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3-8b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:42.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f32a4f46e252a473b7f2fca",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2564102564102564,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:20.065Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "574db0bf92f064e3b44e2ff8",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6378205128205129,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.202Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "97ef2b269cbf7ff47ff94d7e",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2033333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "462c3cd8442fe2a42b5ba54a",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.1582311800104949,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:35.946Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b6f9f62b18a256ef54552ac8",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3-8B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "174b030f6962d81bb3f89304",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4379487179487179,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:19.466Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e26b1e9c3807fe21b1b2c563",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.41512820512820514,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:25.073Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3aeaf9bf0442e515e6525b98",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7681666666666667,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.687Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a17411dba555b91b54b878df",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7772435897435899,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-07-23T21:23:20.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "13b10af3ac14fc6c368e6dee",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4441767074556148,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:53.258Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "935b5338e53ca07a1ec33a63",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4984797409603406,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:13.233Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21836a2d0cdbf87297d33454",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5424905264168288,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:53.258Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "eb82a8d826802373d1d6939d",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5712240162175495,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:13.233Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c6bd7595772fcbfaa449e51f",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.585Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f094e0a6300aa96f1051d02e",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.466Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9544406da5547f1fe49dcc70",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.41025641025641024,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:25.073Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c89fda792895cac4599a0105",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:21.356Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "200cf98da48018856a7d5e63",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7681666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.687Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "eb4ff752a3bb0c388c9fd87b",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7772435897435899,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-23T21:23:20.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4e41530d04593b445988b650",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.4416666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-23T22:21:27.096Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "71e12efc84abf971f954b9f0",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.31,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1853f24bf0b744272742b1da",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4737725562143552,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:13.233Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ff063df0145238293daf41f2",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4425301223668444,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:53.258Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "396deb56144be9148265dd96",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-405B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4bac1042eb9afcbaeb3c468c",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-405b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.58,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.140Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d96dfd9c29a89be7af38d61e",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.32666666666666666,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.746Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e302064d473fa160b9faa6f0",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.34307692307692306,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:05.164Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "29e0e9990ad2f5f6692be576",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8669871794871794,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-07-24T14:13:16.078Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dea731426cf7c6d982a669ce",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7276666666666668,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.145Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3dc93d503cb52dda0d5f85c0",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.36826741139438113,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:02.690Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9c088a8f9c4e472678951dde",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.42362737244860815,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:51.171Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95d6144d0657f75d6c0766a2",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5390937395341514,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:51.171Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b2d15baeef024ee30198afc7",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.47967033371265694,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:02.690Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "35b1137c275a08058e640514",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.746Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a50c2f1d287a71239cfaf3b0",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.950Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "48068daabe4ba52f388c4532",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3333333333333333,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b3834621e5cf425a3a8a56c7",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:05.164Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a6985c9ef7c6642db00b21aa",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7276666666666668,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.145Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8c5f34be9e2e87874b80fb37",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8669871794871794,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-24T14:13:16.078Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "45983fb5b131ab6c99b69c2c",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.41666666666666663,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-24T14:14:05.022Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "62b60f07074f1ab4ab208e76",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.20833333333333337,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9222c916b9d810cd0ecc2873",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.37646890084980994,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:02.690Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ea95f3c9927fd6b0695e6718",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.39421545067915775,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:51.171Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a00c6bc73fcdb6dab8584c52",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-70B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a23ed7de4ead6d985666d894",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-70b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.245Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2a34cbdc35663444950dd698",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.19743589743589746,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:21.208Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "49958802820fda5cc686ac94",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.17743589743589744,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:41.290Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c8ecdc95e70b59a1db4b4ebd",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5704999999999999,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.770Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c9fa51051d98e67292ff7dbb",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5384615384615384,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-07-24T14:13:16.295Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd7b3e6d81bbeee9a6f107d7",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.19605179909891668,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-02T17:35:20.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e38b4c36220fe7cc54ae59b4",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2004726993706473,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:25.495Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "20afae4286f695277fbf4898",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3121233784226944,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:25.495Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2de79df82ca6e250ba30e511",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.31466256551160465,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-02T17:35:20.777Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "717ddaeb41f67dd280072205",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.208Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "74564174978b61ff408bf992",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.719Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2a5e7341c815161fee03630f",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:41.290Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d4255f6926f1423e96ca1c72",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:23.124Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1355931c8e1d8b3bc07bfe4c",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5704999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.770Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "029df97682024da13e0c4813",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5384615384615384,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-24T14:13:16.295Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "631543b0f67639deeb2fc191",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.06166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ccf7fc824d55c138760b9db3",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.13166666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-24T14:14:05.025Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "967bbdc06f1a6d347caecbe4",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.16975143144527532,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:25.495Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ef799828fa8ed46939bd5c1c",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14648873063008339,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T17:35:20.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "222cdc64674ab168eee1fcdf",
      "sourceId": "livebench-model-judgment",
      "model": "Meta-Llama-3.1-8B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.3,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "61cb6c71724f0283cf59f5d8",
      "sourceId": "livebench-model-judgment",
      "model": "meta-llama-3.1-8b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T17:33:59.183Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "33dd196044a67615e6ab66ed",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-7b-instruct-v0.2",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13333333333333333,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:53.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9946acfe0ef73e40a8849c10",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13897435897435897,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:18.634Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "98adeb5ed81e0c637d459870",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6282051282051282,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.029Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e34a479d8eb9061db7ab489c",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.09054752699799257,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:07.317Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b38833402a3232d553c774a",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-7b-instruct-v0.2",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.13333333333333333,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:53.630Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a8ea9d3db5468c535fb76ea0",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2859090047258266,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:07.317Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ce79d452d04daaa29c02de4f",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.634Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "35833e1aa3937155f832cc0b",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-7b-instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.13333333333333333,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:53.630Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b5d2b35ed8ac052723f00d45",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.21794871794871795,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:53.045Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "46c883a6d1df441c161472f6",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6282051282051282,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.029Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5f563ced80058f0e26631add",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.06166666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fe1ebfff7cb88061221fd89a",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.129975914327311,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:07.317Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "148c87560902793af5814960",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.2",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.08,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "050c0d21b66abcd887c3c645",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.10974358974358975,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.984Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0e32a28708b4d7ed9d6981a7",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.530448717948718,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-07-08T13:43:11.789Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5e3ebc4f2881e97da165317e",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.11852731287879431,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:52.607Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3a0fcc8ba45a1ec28939f12b",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.25290654019036735,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:52.607Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c0fde39d37cdb49ea41d1c19",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.984Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "69e6c86bb8c99a6e0c37dede",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.1794871794871795,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.849Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b939d4be32196a493a57a060",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.530448717948718,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-07-08T13:43:11.789Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5dbfa60190c3473aefb3d7be",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.06166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-08T13:43:53.930Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "08248449d98a753e7589cac9",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.15391527196971624,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:52.607Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "363d6202d59603db9c3f32d5",
      "sourceId": "livebench-model-judgment",
      "model": "Mistral-7B-Instruct-v0.3",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a91c059c46f7021778830943",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.27384615384615385,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:33.379Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5b294292fb88ac66eb76f02c",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.71,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.273Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ab247cbb1d7105234b85e418",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.28743997010043004,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:28.359Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f27d6c89cc3c0ee35c5f813d",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4237620413155279,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:32:33.379Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c1f9210c2aff089e7c2ea17f",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.544Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7059e4e8b871a90f9dc8970a",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:33.379Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "98537a50d447acd1072c5207",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.71,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.273Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a40f7c0b00a173db2c23d1e",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2833333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c4da6453528029280b12d63a",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3389865769679567,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:28.359Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "03058d190acaa3367faf95f9",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2402",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cffc8f9976cb0d9afb84381d",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4707692307692308,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.212Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6fd9573b4a4933b91f8c4f48",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.69625,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2024-12-10T19:31:49.974Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d3c88a91d373b8df0de54977",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3965399973741665,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bea7efecc1c3188fc882b750",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5211864093811324,
      "unit": "mean category score",
      "sampleCount": 393,
      "asOf": "2024-12-10T19:31:49.974Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "fb219c6ac7eb6a3d71d8a5b4",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.212Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "20c64ea50c8fcadc558315ad",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.46153846153846156,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:22.108Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6c204947f9e3110b0eb7a404",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6108333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.974Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e6a672e718a2dbf826c058bb",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7816666666666666,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-07-24T18:54:00.337Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "078d6ca309b9385ea17f2554",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2891666666666666,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2e59972b1e508e9a6ae1664b",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.40045332545583284,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:17.938Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "13b632ceaf8203d27251d6c0",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2407",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d71cf4c181f42a3d18f7ef0d",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4707692307692308,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:31.075Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a932ae27521694e8d4715953",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6988333333333331,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.377Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ed4af819bd85d36a5bbb60b4",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.39833160570617027,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:22:05.605Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b3b9a1ba14df7c56149812cc",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.522644723269578,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:22:05.605Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "16ebf02c20c9aca8e39e9b1b",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.623Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f5a23b1a8415c64f08fe8c01",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.46153846153846156,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:31.075Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "68d679811cd433cc74783dbd",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6988333333333331,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.377Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64865e71e8fd4b91fa9ab923",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.28833333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "89cc172906377be8391d6188",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.38666148378517745,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:05.605Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3baa87614bbf89387671883b",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large-2411",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.280Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5ef3f4306eede106d9e5807f",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.0186218748643732,
      "unit": "mean task score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:21:54.601Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fbbf720c26305bdf9d6b7802",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.0186218748643732,
      "unit": "mean category score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:21:54.601Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d96d82cc3f86da91900d6c34",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.0372437497287464,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:21:54.601Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "414e6016abe73fd6ad4cb7dc",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-large",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:11:27.153Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7683ff25c54945feb243541e",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.21179487179487178,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:40.301Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c651b2baf92fe16e92cb65c7",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6798333333333334,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2024-12-10T19:31:50.310Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "138e262fc4b03868172ff8ff",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.20471889045398906,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "68ab72b8d927c636f8dc872a",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.36544903186073147,
      "unit": "mean category score",
      "sampleCount": 393,
      "asOf": "2025-02-06T18:32:40.301Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a26a877f36c5dd941ee4c727",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.294Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b729dc3bdc01182abefebb16",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.24358974358974358,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:40.301Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9da405f876056e66ff5fa65b",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5663333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.310Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ff4a755419d40d5cd68a52b5",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7933333333333334,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.341Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b49097958240a9a0f9a5ef57",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.1691666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d52485858678a3333453def5",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2649900046953005,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:39.617Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "798494855386fec4393c93ba",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2402",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "40826e0909bfe2add79ef8a9",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.25743589743589745,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:52.609Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ef60de9c513789fd2dfc6d96",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.4611666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.728Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "221045c5813d9021ded1f235",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.26917991017614534,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:54.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8179382885ee5c87d216facb",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3292608247595698,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:54.599Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "e51efe2f81d07cd68d4e7f87",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.22,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.230Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "165d717f626e60d954319a9d",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:52.609Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4e386300454491a962f78d30",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.4611666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.728Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "026aa6b5c11dde06a46af7bc",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.24,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0a62c698c3ba8b4b9b4db006",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.207539730528436,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:54.599Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2daf655f617da6026f6605ea",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2409",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.36,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.153Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d9205c695d678b88c7e76b07",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.35307692307692307,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:39.674Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c0c6ed8df80c67fd088758f8",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6506666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-31T17:22:14.496Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "15e53ddd860d8bc50668a329",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3128667676446944,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:52.601Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7a1077430405fe7425423e72",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.438870119129428,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:52.601Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4c9c82088d1f4585e4de7863",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.36,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T17:13:48.637Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "307e43f9da3e831b99169abf",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.34615384615384615,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:39.674Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21dc98766cfc40e743e79b40",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6506666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T17:22:14.496Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dfea63ee69b8bfa53d2b4a54",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.135,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T17:21:00.153Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b2c2a82039c8315fe4d3b2fb",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2836003029340831,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:52.601Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1bfee5d186b7adb01dcc6c67",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2501",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.131Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "592c5949adc7a61a2cb00d97",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.36230769230769233,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-18T16:49:42.362Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8e05e3d48811e754fdaa248e",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6241666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-18T15:09:00.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bb260b499b4acc87180ebcea",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.31796884301032496,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-02T19:57:37.580Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0d8c0364b80a6ffd5e75052d",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.43481440066156135,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-02T19:57:37.580Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "5ab857062365c7412cc748d9",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-18T16:49:42.362Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c7a66b6bfcf4a23be664f671",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.38461538461538464,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-18T15:08:57.881Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "980c05ccfbe3c82a75939375",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6241666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-18T15:09:00.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d50a9278fc83175f3bae8110",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.23,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-18T15:04:14.031Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "054c8e65f2df05033a5509a9",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.283906529030975,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T19:57:37.580Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ea5f95935c3af103cda69b63",
      "sourceId": "livebench-model-judgment",
      "model": "mistral-small-2503",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T19:57:10.082Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1c28b933dc397c13e50f6358",
      "sourceId": "livebench-model-judgment",
      "model": "mixtral-8x22b-instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:37.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4c05a4f9eef43ff541440126",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3310526315789474,
      "unit": "mean task score",
      "sampleCount": 88,
      "asOf": "2024-12-10T19:05:06.376Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7010e9ebb0bb2d9c330a68ff",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7419871794871795,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.176Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ada8cc1a758bb8d0bf686025",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2647769266808427,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:23.692Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "17f359ae94a438fa4ebde264",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4459389125823232,
      "unit": "mean category score",
      "sampleCount": 254,
      "asOf": "2024-12-10T19:31:23.692Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "2a370fc6bc15e480edb91469",
      "sourceId": "livebench-model-judgment",
      "model": "mixtral-8x22b-instruct-v0.1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:37.673Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "7aa37cfa53d33f24b72e24e9",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34210526315789475,
      "unit": "mean score",
      "sampleCount": 38,
      "asOf": "2024-12-10T18:50:30.516Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3653ebca3556fc6da39b4c99",
      "sourceId": "livebench-model-judgment",
      "model": "mixtral-8x22b-instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:37.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e4d4e2190f3e2b5bf4279bd4",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:05:06.376Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3eded50cc513e97a37bdf93a",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7419871794871795,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.176Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bf3f180bcb6c7774463a7a45",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.25166666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2727fcdcfeb9c57054fcc948",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2826641133758614,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:23.692Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5fa1ac011490c1e7d7dee56c",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x22B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.26,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7c12af2f129c328f33922d36",
      "sourceId": "livebench-model-judgment",
      "model": "mixtral-8x7b-instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13333333333333333,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:05.485Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a8d48db852e59d8013d3ea4c",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.11315789473684211,
      "unit": "mean task score",
      "sampleCount": 88,
      "asOf": "2024-12-10T19:04:44.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2e0ca12d6d632ecf28bcb71e",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.578525641025641,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.042Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "44768df4293acc463bd51e29",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1376130330438123,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:57.305Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "06996212d8b2f2c985ad93e4",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2764321896020985,
      "unit": "mean category score",
      "sampleCount": 254,
      "asOf": "2024-12-10T19:30:57.305Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f305115011e31aabe701913e",
      "sourceId": "livebench-model-judgment",
      "model": "mixtral-8x7b-instruct-v0.1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.13333333333333333,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:05.485Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "5e61c21bc58bedceffaff8da",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.02631578947368421,
      "unit": "mean score",
      "sampleCount": 38,
      "asOf": "2024-12-10T18:50:05.863Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b247aa81ac93d16481240d0d",
      "sourceId": "livebench-model-judgment",
      "model": "mixtral-8x7b-instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.13333333333333333,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:05.485Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e78c6165db250e1494059433",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:04:44.336Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c38d77e6d57d0132eb823725",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.578525641025641,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.042Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd67a8cdc4d879f54c00bb20",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.15,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8cd37c914ef43bf503fa2fb8",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.16283909913143693,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:57.305Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d46ab02ebfa0ead8814a7e74",
      "sourceId": "livebench-model-judgment",
      "model": "Mixtral-8x7B-Instruct-v0.1",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "30850ffcd0c58f9ba851fe2f",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.696923076923077,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:37.987Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e73b7a545db7b0d7669c42dc",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8290000000000001,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-18T20:47:54.330Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f5b4b2832c30b199894816a",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6866432501740096,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:56.570Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "786323ae983e17d6404c57c5",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.7375221090323621,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:56.570Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "cef8c818f030a477f9ae736e",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.74,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-27T16:43:26.912Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "77002ac4bf327934629a1409",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6538461538461539,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:37.987Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "02b9ecb80406ad8c74555fa5",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8290000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-18T20:47:54.330Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "459d6e698453d93f61f8707a",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.97,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-18T20:48:36.023Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f979cf26efd476ebcde93ca7",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4999297505220287,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:56.570Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9a7a236af60a879451085599",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-high",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.59,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.184Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c379d89a3cee51dde8a42fdc",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5256410256410257,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:30.729Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dc564b3ddcecaca0fd1a6318",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8314999999999999,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-23T17:01:03.008Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "94cb2ac3f2c736757bf7f971",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5989287228655877,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-23T17:34:52.876Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "05f6ab72b6a20704db6b2ccb",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6520232495022044,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-06T18:32:30.729Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "5172946aee3aeac933534c9b",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-23T16:33:26.739Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "66510e5c1af1de16295f11a4",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5512820512820513,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:30.729Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e7fd6bf7e6b2c388b46a82af",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8314999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-23T17:01:03.008Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9b7d45203c0f1eca0e7aa12e",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.9316666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-23T17:34:52.876Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21bde0cb84da70351da1f4c8",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.42511950193009673,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-23T17:34:52.788Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a203ed4e381e77b69d8b7675",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-low",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-23T17:34:39.629Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "001236ab4dfa9e1443e2118f",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5556410256410257,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-04T16:30:54.204Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1506adc22ca185603680fa4e",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8086666666666668,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-04T16:18:04.005Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1da60e85cb95f22c79d849b5",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6350536862989655,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-03-04T16:25:32.323Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8f89eb67444bc7e1e9c5b9fe",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.666453792868886,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-03-04T16:30:54.204Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "72c5f6846bedce2f661b01fb",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-04T16:30:46.952Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4baaa927311f2a63495f6f0d",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5512820512820513,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-04T16:30:54.204Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8b97a084344625975a6071b",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8086666666666668,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-04T16:18:04.005Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "946c7076756e0ead99cf1deb",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.965,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-04T16:25:10.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "65175630ae0ad443584861c8",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4601610588968966,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-03-04T16:25:31.465Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "34e767e546820491a90da611",
      "sourceId": "livebench-model-judgment",
      "model": "o1-2024-12-17-medium",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-04T16:25:32.323Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9d65be4c0fde74be4d4d5cf8",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4805128205128205,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:18.222Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "58d3a8ee5696de830137004a",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7255,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2024-12-10T19:31:50.013Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c14f42b7c8e68e31ae7c639b",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4510760300964458,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:21:59.255Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9a6fc9535e113b4aad36499f",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5523629502030888,
      "unit": "mean category score",
      "sampleCount": 493,
      "asOf": "2025-02-06T20:21:59.255Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "1d0bf90c3ac30c9af693c0ea",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.32,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.711Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "36b5655a6b83a380839ffb93",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6410256410256411,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:18.222Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f133d915c3906caae1657711",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6659999999999999,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.013Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "472c72bb36a501b37b29d53f",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.785,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-09-15T06:02:09.947Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b0ca7d2544d10f40981827c",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.6658333333333333,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64f310e10e9c39748317c37a",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.20739475695600432,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:59.255Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1e18d57f4af54e95899f8f60",
      "sourceId": "livebench-model-judgment",
      "model": "o1-mini-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.210Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d2c4ece5b0a00feff9cf9833",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5084615384615384,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:14.728Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e1e012cb026a876aeaf88e52",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8520833333333333,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2024-12-10T19:31:50.226Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a4857d4cafae6637479a80c8",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.7068933753629222,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "be1304d930081b757b8c9905",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6891460823859313,
      "unit": "mean category score",
      "sampleCount": 393,
      "asOf": "2025-02-06T18:32:14.728Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b1a02a1a7c3052c0d30a0b5f",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.44,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.542Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8ef2314e2d0ba58e2da09d7b",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5769230769230769,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:14.728Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "df546f6085790f3e8a606bed",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7908333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.226Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "73264c3c3d6d37a54d8b3bd2",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.9133333333333333,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-09-15T06:00:44.966Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e1603e4d93b9448db70e8f2c",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.9258333333333333,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "652d688db6cfc45e1046bc0d",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.5348467927554331,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:35.532Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0fd7cd12dd7423f80fe41fae",
      "sourceId": "livebench-model-judgment",
      "model": "o1-preview-2024-09-12",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.66,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6fa4e2b5fef71f2aad90c853",
      "sourceId": "livebench-model-judgment",
      "model": "o1",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6161538461538462,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:22.957Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8f81f7453f5db9e68ba07b9b",
      "sourceId": "livebench-model-judgment",
      "model": "o1",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6161538461538462,
      "unit": "mean category score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:22.957Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "bec772a5148abf87749620d8",
      "sourceId": "livebench-model-judgment",
      "model": "o1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.957Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "85dc90468fb5780871e02e8d",
      "sourceId": "livebench-model-judgment",
      "model": "o1",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6923076923076923,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:28.331Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "49bb9f2e3edef25011870979",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.8338461538461539,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:53.293Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1b5260baea362396b140bf1c",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.825,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-31T20:40:59.287Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3b685302ed72827331a52ee0",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5366709742796791,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:57.660Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9e6affff5c13fec5544357ef",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.7318390427086111,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:57.660Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "23e81c8606f93ffeab4a4611",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.86,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T15:57:53.453Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "97f6c2da06e8e54837ea460f",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:53.293Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "896d308394eb2e027096c28f",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.825,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T20:40:59.287Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "394819444bce05d7001f9480",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.795,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T20:46:53.870Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d1fbe064c5eae6a687c8baa0",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.25501292283903737,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:57.660Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "76c2b7e3dead7bd68a1387ec",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-high",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.197Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b277f5834989a0022e51bf7",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6146153846153847,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:36.774Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bd987e259edea105712cfda1",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7858333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-31T20:32:20.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "47e7856960d608f754131da4",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4300339128441237,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:54.259Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4b6eae0ab3626b55bc2ec2a1",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6101608769309471,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:54.259Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "7987a74bd2a3e24485a58ba5",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.46,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T15:57:54.653Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2521b779c1e0b7c7bf7cf251",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.7692307692307693,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:36.774Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "067de9807b5ae17d60fcbfae",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7858333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T20:32:20.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e347435a90c126ea6c31b56d",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.6483333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-31T21:04:32.516Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4d4d8f6f253e74cdaa4cd663",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.19176840519903754,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:54.259Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "77b401327c816760a48fe08f",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-low",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.45,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.153Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dde55acdd6266e61170fb451",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6602564102564102,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:36.076Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fd21ed121d8910dd1ae4a26f",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7985,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-01T00:41:38.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "23f1ea1488a34007e9f523b1",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.49994189107567094,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:58.009Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9b8c226651fee7d0e5060cd2",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6528994337773604,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:58.009Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "8403ed4d1bd53ac9c99587ff",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T15:57:55.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3d4ab98f4868193a311adb9f",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8205128205128205,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:36.076Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c0a4bb1220a62b6eaaf2dd9e",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7985,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-01T00:41:38.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "02c369efd1eb91ac80927730",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.7983333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-01T03:43:02.400Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7407496191373c97b7e1a7af",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.21149233989367958,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:58.009Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0b2e455d3d90cb99b60b8c92",
      "sourceId": "livebench-model-judgment",
      "model": "o3-mini-2025-01-31-medium",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.49,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.197Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ffede462b147f31375c1e5e7",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.1041025641025641,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:39.985Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ba8056c0dfbb6ed92b0978cb",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6678333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.052Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "598b433a516353d3c83de541",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.11158967319777889,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "41c52902d81436fbcb39d8eb",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.29450852354455875,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-06T18:32:39.985Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b7893bcef99ff610adf37bed",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.08,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.292Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "87e65c97aeeb4c6361a5f3ea",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.1282051282051282,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:39.985Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "69e19363da4e6116075a033f",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6678333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.052Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "40e43c98f139c8547cd315a8",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.04666666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3b53ab7789af82c0e9d9bba5",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14810235292666998,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:25.717Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "81005dce1eca520979b993cd",
      "sourceId": "livebench-model-judgment",
      "model": "olmo-2-1124-13b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "87abd7a5ef8cf1b3a4bce51e",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2874358974358975,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.545Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "41c49a1cbe0a84789891398a",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6233333333333333,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-07-24T18:55:19.700Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cbd5582b6a8afcbfddf0e029",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.14149493509126856,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:19.403Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fdde26120d3192bd6dd4acea",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3507547219534997,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2024-12-10T19:31:19.403Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "82bd463dfe800d62a9fc2917",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.545Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0cb1d137471220124be49672",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:22.449Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b5aa5d629720300a920a572c",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6233333333333333,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-07-24T18:55:19.700Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "12b2ec3ca6ec9c92c4f6572a",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.09833333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-07-24T18:55:34.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ac007ee2a3d38a9c5b8e3258",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.16615147194047242,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:19.403Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "00019da1b4ce10ba2ffeff89",
      "sourceId": "livebench-model-judgment",
      "model": "open-mistral-nemo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "aa8abb672225e3553240cd95",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2857142857142857,
      "unit": "mean task score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:07:21.627Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2dbb599e2d258898d5b91578",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5168333333333334,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.105Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b7de29b52fec99307a5d53c5",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2458763087092211,
      "unit": "mean task score",
      "sampleCount": 150,
      "asOf": "2025-04-03T16:14:29.968Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "df2197b05e912fc9526e828d",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3494746425856134,
      "unit": "mean category score",
      "sampleCount": 240,
      "asOf": "2025-04-03T16:14:29.968Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dfc3598cf3758d9c6d40b140",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.25,
      "unit": "mean score",
      "sampleCount": 12,
      "asOf": "2024-12-10T19:07:21.627Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c0abb754e7d66867b611b280",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.32142857142857145,
      "unit": "mean score",
      "sampleCount": 28,
      "asOf": "2024-12-10T18:01:23.545Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c19ee25e4b857eef5288b420",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5168333333333334,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.105Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "42b419d41ee406d6821b0b6c",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.11166666666666668,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4d6820dd60b9cd27140a51ab",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.20596225946099656,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:14:29.968Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "70ff39850cfba8ec5ef14ac2",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x22b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-03T16:14:00.006Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1a67e210ce31008da11a06f",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x7b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13095238095238096,
      "unit": "mean task score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:07:18.882Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6aa61383ee328a007d78719e",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x7b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.13095238095238096,
      "unit": "mean category score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:07:18.882Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "002ba2a7a71b69d6cd951371",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x7b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.08333333333333333,
      "unit": "mean score",
      "sampleCount": 12,
      "asOf": "2024-12-10T19:07:18.882Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0c0f04bbc83582159bddba1f",
      "sourceId": "livebench-model-judgment",
      "model": "open-mixtral-8x7b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.17857142857142858,
      "unit": "mean score",
      "sampleCount": 28,
      "asOf": "2024-12-10T18:01:20.770Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6b67ae4a5edfb94a98bff137",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13256410256410256,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.667Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f4f8238a5523878d16b0f2c",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6634615384615384,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-14T17:34:39.478Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b91e0b2a0cf52ff37b6e7b76",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1136841122603151,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:50.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "02b3a5cc6b83eac654715879",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.30323658442865203,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:50.597Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "cc66b83d183747007942bebe",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.667Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f513fdf3597100f2e8b567ba",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.20512820512820512,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.509Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d98dea1d92aade60d941b100",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6634615384615384,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-14T17:34:39.478Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8bf0cb5b5eacb65f51d438d",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.01,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-14T17:35:15.886Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "85fc51ded1c0ca251232deee",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.15105233678094532,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:50.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95dc6fdb976347d6fb0b45c6",
      "sourceId": "livebench-model-judgment",
      "model": "OpenHermes-2.5-Mistral-7B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "79035fac6601520781d4c8de",
      "sourceId": "livebench-model-judgment",
      "model": "perplexity-sonar-reasoning",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.02631578947368421,
      "unit": "mean task score",
      "sampleCount": 38,
      "asOf": "2025-03-24T21:14:28.404Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8baef573fd3e120a726d1d4d",
      "sourceId": "livebench-model-judgment",
      "model": "perplexity-sonar-reasoning",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.02631578947368421,
      "unit": "mean category score",
      "sampleCount": 38,
      "asOf": "2025-03-24T21:14:28.404Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "7a800469256ca05e7c7e6f89",
      "sourceId": "livebench-model-judgment",
      "model": "perplexity-sonar-reasoning",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.02631578947368421,
      "unit": "mean score",
      "sampleCount": 38,
      "asOf": "2025-03-24T21:14:28.404Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "41847ccf53512e4b6f4460a3",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.22102564102564104,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.794Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "131b3c67f463334eac41f18e",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7275641025641024,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:17.115Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "649e51d103e0ef47e7467b45",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.12756635648886164,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:22.572Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "791cd5f3438519d4f12cdcdc",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3587187000262017,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:22.572Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ddd1baf205bb783517e37455",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.794Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "19bf7dff756a5c6f3628a15c",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.28205128205128205,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:22.705Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cb4dc9dcd09308c2caddca16",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7275641025641024,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:17.115Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3dbf9298fb221969caf8777c",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.095,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-14T13:52:44.558Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f63e226f4de18dc692b13744",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14769906946658495,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:22.572Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2674f865b35cd971ae6d49a3",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "af38a580e96bb535029a1769",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.20461538461538462,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:18.718Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "00ba10af9e5620e3f4d59318",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5352564102564102,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:16.902Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3fe6bfcf5a566c9ed67f1e08",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-medium-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.39533333333333354,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.891Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "58b8f143f85371560e5384d1",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.13909024942065537,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:07.578Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "30265fba34893de5da7f7779",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2929873480974834,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:07.578Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9e926d21cfa2b516486613f5",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-medium-4k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.39533333333333354,
      "unit": "mean category score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.891Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9623c5da7d48c4142c51783f",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.718Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1947eb1c2a8a915a8cf1e8d9",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2692307692307692,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:20.601Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "901e8ebb21ee9239611bd47e",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.39533333333333354,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.891Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0283819f779be99e7e0fd970",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5352564102564102,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:16.902Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e8e8d0e5acde235db57f3d7b",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-14T13:52:44.555Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3eadff1042f948b1b284c471",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.15727074826196613,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:07.578Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0c91a22ca66fc1b0384c9d84",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-medium-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21b3dc93ec80236476898c49",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13333333333333333,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:39.353Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "51a764241b29da7fddad1769",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.1503846153846154,
      "unit": "mean task score",
      "sampleCount": 256,
      "asOf": "2024-12-10T19:07:18.215Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "95876d80392d7ab95bf4d96b",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.407,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.755Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a60b5b6a038c4fe2eca49f2a",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5480769230769231,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:08.045Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "59aff0a6819bbc5f26dd1564",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.07764587443023865,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:04.753Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5e4b549153f01f814d63dac3",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.06166666666666666,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "25dec94e30df9fc072393184",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.20066666666666666,
      "unit": "mean category score",
      "sampleCount": 115,
      "asOf": "2025-02-06T18:32:39.353Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4c601b2f85ff6d29d6ff8f4d",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.25870247096392573,
      "unit": "mean category score",
      "sampleCount": 422,
      "asOf": "2024-12-10T19:31:04.753Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "28d4344d942077e78f4c2037",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.07,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:07:18.215Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "413a543fb944cee4110cd031",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.23076923076923078,
      "unit": "mean score",
      "sampleCount": 156,
      "asOf": "2024-12-10T19:04:52.240Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c5b5ccb8fcd44bbd3383d814",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.13333333333333333,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:39.353Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9e8956e9b64ce6bf975426f0",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.407,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.755Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "07736fff3fdd2755cd7aba59",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5480769230769231,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:08.045Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b100e1c1357e9622b04ff43b",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.02,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-24T03:26:48.105Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f41aa914ef542120ba5a9128",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.06166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5bd8803a9f90472d4fdeaa6a",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.11293762329071595,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:04.753Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bae2fabfac8cc675ceb299a7",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "23359ca1f92e5521c85e31dd",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.1553846153846154,
      "unit": "mean task score",
      "sampleCount": 256,
      "asOf": "2024-12-10T19:07:17.392Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8ffe4d3ae662e5d71310e3a9",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:38.958Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6b283260df906b09c662acf0",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.34266666666666673,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.268Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e5ce02c5c76d8a49a384d3bd",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6538461538461539,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:08.028Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a15164476cd976d9c6d366f",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.045,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "683fc1d68b9c728d650fd518",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.08058839141615325,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:56.244Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "826e8e3a84ec6b2771079a95",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2966063868823075,
      "unit": "mean category score",
      "sampleCount": 422,
      "asOf": "2024-12-10T19:30:56.244Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "eb75314dc4ae21ee816469d7",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.19588888888888892,
      "unit": "mean category score",
      "sampleCount": 115,
      "asOf": "2025-02-06T18:31:38.958Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0ffe211f9d09411321c354c8",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.08,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:07:17.392Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "69bb08d9c20962f9ed0839f0",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.23076923076923078,
      "unit": "mean score",
      "sampleCount": 156,
      "asOf": "2024-12-10T19:04:43.115Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d3d4b26b645f9f002091cf53",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:38.958Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9a892c06c880526e4713456c",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.34266666666666673,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.268Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "35004f7c33c460391dd5aeec",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6538461538461539,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:08.028Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6de2b4c9ce2223e328b16d1f",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.045,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7584854cb5e1625b094039d2",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.03,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-24T03:26:48.104Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "16d45b66136d566d532061fe",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.13176517424845974,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:56.244Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b083d6d3c1f34723e2b399f",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-mini-4k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.08,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "eed38c236724da5811813b03",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.24566037735849056,
      "unit": "mean task score",
      "sampleCount": 206,
      "asOf": "2024-12-10T19:07:23.540Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8f308ba13bfbebd664be3c34",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7419871794871794,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:08.011Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d518c6b86b913c3c81a9718f",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.15532008533615868,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:41.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "20146be071e4d9fc65ae1842",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.38098921406060954,
      "unit": "mean category score",
      "sampleCount": 372,
      "asOf": "2024-12-10T19:31:41.596Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d6f8891f4e1482715da5fcfd",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:07:23.540Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f64cdf0c0a54b9e6256d5843",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3113207547169811,
      "unit": "mean score",
      "sampleCount": 106,
      "asOf": "2024-12-10T18:01:25.479Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b61a430960047a6a7c861838",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7419871794871794,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:08.011Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1ef19847e82197af719c7e4a",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.12833333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-24T03:26:48.104Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2ca3228cdc46fbab6bd2f49b",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.13762692267514273,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:41.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "798c7569269b5ad35497f207",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-128k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "22f5edb97ae138304ba83fa4",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.20264150943396225,
      "unit": "mean task score",
      "sampleCount": 206,
      "asOf": "2024-12-10T19:07:18.964Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0be70b4837901c5abce732a9",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-small-8k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.4416666666666667,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.840Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5ade7c978d49a5b1fcaedddf",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6923076923076923,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:07.995Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b3090e25398913912cb148eb",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.15129313524716217,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:09.078Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0d213935fcc70f0b09fc2e21",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-small-8k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.4416666666666667,
      "unit": "mean category score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.840Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "76e880ae80a09c2455830790",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3487474456629389,
      "unit": "mean category score",
      "sampleCount": 372,
      "asOf": "2024-12-10T19:31:09.078Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ad76ace5c31eaaf5d624a787",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:07:18.964Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b668faf20360a6792e43d103",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.24528301886792453,
      "unit": "mean score",
      "sampleCount": 106,
      "asOf": "2024-12-10T18:01:20.852Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "613e091c6bd7ee3c1b460156",
      "sourceId": "livebench-model-judgment",
      "model": "phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.4416666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.840Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ba59b718f3631bc4abd026db",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6923076923076923,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-24T03:26:07.995Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f8aec32601eac870f6a4a570",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.195,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-24T03:26:48.104Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "80acfa452237930333c73527",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.15887940574148657,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:09.078Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "63aa8eb91ba7d15a96c31eae",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3-small-8k-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "554340d84e592aa870207ca3",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.15897435897435896,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-23T03:20:08.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5faf09f4711b58c78ea1a0eb",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7115384615384616,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-23T03:20:09.765Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0762345bbc1084ea7b525e16",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.09666278523472717,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:05.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e6ca5f2586bd24a4a7bd2b16",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3223918685825159,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:05.803Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4895a2b35025ba87447fa022",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-23T03:18:42.473Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "45a6ce06ff8495324cff6981",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.21794871794871795,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-23T03:20:08.777Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1995a4b0b905dc6bc1fde86c",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7115384615384616,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-23T03:20:09.765Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c35ca1da1d85307df75d3f77",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.051666666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-23T03:20:23.179Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "05c954e0caf9941b1461ad04",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.11832168903751487,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:05.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c66146c255817825d08e345e",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-mini-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c3731b61e830cd6fde137081",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.21743589743589745,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-23T03:08:50.289Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "025843996711f30ec860e23a",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6282051282051282,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-08-23T03:08:51.375Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4eb245c881df9b24e9aae3a1",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.17071693030638668,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:42.757Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2436ef5de917947524fa6b56",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3387859853158041,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:42.757Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "81ac06ebc70c98679a67d1c5",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-23T03:08:50.289Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "17a6b760f791eee740f46ddd",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2948717948717949,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-23T03:08:37.417Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3be068c8ad3734f963e6d135",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6282051282051282,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-08-23T03:08:51.375Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dfbbbae885c29532a6932a2a",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.11,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-23T03:09:03.627Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3b9d0e2bd8dd41404d5fb8ea",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14215079091916002,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:42.757Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "50b00345a0bdd5c35193d088",
      "sourceId": "livebench-model-judgment",
      "model": "Phi-3.5-MoE-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.26,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7105f066c0ad879800f5a572",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.30666666666666664,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:04.788Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4337a3ab69cae5e70212acda",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.548,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-09T02:38:33.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e8a9b70fb99700b8a1ba3f85",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.29333692280977797,
      "unit": "mean task score",
      "sampleCount": 150,
      "asOf": "2025-02-06T20:21:56.892Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f671de96df07d292feb31a8c",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3826678631588149,
      "unit": "mean category score",
      "sampleCount": 328,
      "asOf": "2025-02-06T20:21:56.892Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a5c799f2ae59cc6aa5ebe37f",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-09T02:37:49.395Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2c0300d4a88ee07c7206062e",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3333333333333333,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:04.788Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5d12f4d3902d46cf68cf7f1f",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.548,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-09T02:38:33.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "38586f3c1ea0792ed60aaf58",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-09T02:38:32.304Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d92b43cd193d49d74aba8028",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.20001076842933396,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:21:56.892Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e4e3d315986aee38029dd12d",
      "sourceId": "livebench-model-judgment",
      "model": "phi-4",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:11:27.188Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9c78b9e296469ce15e374205",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-0.5b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:45.914Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f0bbc026ab8035f9cb4952d0",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:17.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8cfc4fa7345af465cd780075",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.2644230769230769,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.354Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1900ab7f0397ed40ab6b2b7f",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.0287767460555796,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:57.896Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2e01d15a1e16fccdd8d4fbf4",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.09773327432621885,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:57.896Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "8bfe01f956498b80377533b0",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-0.5b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:45.914Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c2b014a491bc3ef5ce06833a",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "30d9f46aaabce432bf1554fe",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:44.590Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7c249d0bcd84830cf1c103c7",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-0.5b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:45.914Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4716d190273b90628b240e6c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.2644230769230769,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.354Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4b3f9de684e7faf0e3d94c94",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4850e5b5eeafe2eba416617c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.08633023816673879,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:57.896Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e926d9f3777ae868e95b2bbd",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-0.5B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "34fe89648cec380dea101e87",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:21.460Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a3b30b6e24b73684d3ed6b0b",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-1.8b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:03.127Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3fadba4caf35bc23f8b21039",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.29967948717948717,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.289Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3ecca85b98a7494169379943",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.03155684468061979,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:27.203Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "26b284a64f5961278ce43fe2",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-1.8b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:03.127Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "9e85eb77a1ed7fc0d2840438",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.11041211062003566,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:27.203Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "cf31e62a949932ab938efc7d",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.460Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0a3cf552fccc8af2510ad8cb",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:08.302Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e1e09aa1f881388a0b91f595",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-1.8b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:03.127Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "538af1dd4cf68795b29cddd5",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.29967948717948717,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.289Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cbf8dc466c28f7eaaac49308",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "63304cd7920577b6c78a2d14",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.09467053404185938,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:27.203Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "35e721923b63ff3b33ad14c0",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-1.8B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "921faeefd930973a26c56a1d",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2182051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.377Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a8db509b881118c458b0cba9",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-110b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:15.657Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0b09f576c5df84bea6de9d64",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5512820512820512,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.189Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1776fe1b3de4146c21a5a76a",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.1322433372220129,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:18.773Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1488dab3b2023c733face78a",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-110b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:15.657Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dd20f39f16e7354cc6417b1c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3005768389030641,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:18.773Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c3304627d199a4a03b9db898",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.377Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a7901482bc391e4fd13d76d5",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2564102564102564,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:03.957Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "acd24e836648b5ec466c8227",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-110b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:15.657Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7c7250e9b342c145c0935a6b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5512820512820512,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.189Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9d6a8b512e902262e2ad7627",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2033333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "caf7e76c13b3abbff0eca9de",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.15339667833270543,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:18.773Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "da0c9e527070f07b5e18da39",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-110B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5860c072d8db3f8cd22b0da9",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.04487179487179487,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:19.549Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6a09799ae795496e5c20fc92",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-4b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.06666666666666667,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:33.974Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1b2eb929410c04bcaf5b1ad",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.36217948717948717,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.109Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bc50581412ed285e922c769e",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.057983726222583326,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:13.783Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "14273307c46bda61834e89bc",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.15501166942462177,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:13.783Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "d48bfbc009c5ddc44cfdefee",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-4b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.06666666666666667,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:33.974Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "791625d180499836fa3b1d9d",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.549Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1c55f91c42f0269447b1e382",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.08974358974358974,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:00.990Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f9c018f676df697b2267e04",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-4b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.06666666666666667,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:33.974Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f99ccfe478e8ca24b44e1d52",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.36217948717948717,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.109Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b50cbba782ca539328d73e78",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d126fdc601e74fa5211711b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.09395117866774998,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:13.783Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5a857e55f435bd30a77adfa4",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-4B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.08,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "13de65dad17162db175a8751",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2282051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:17.067Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4c4623fb769e023bd62ff140",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-72b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:31.728Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b5e7daef0598de1f9f241815",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.733974358974359,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.380Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fd4797ad8b8fb57137600f63",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.11368115074861568,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:52.970Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "49bcc5a648fe33236abfb5ad",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-72b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:31.728Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f286c133a56c9c2c0e38524e",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.35862021264270094,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:52.970Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "36c74aebd3c3be520112586f",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.067Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21fed413926dec506af06044",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-72b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:31.728Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e24a82ec839d94e6b344c533",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2564102564102564,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:42.277Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "21dfa09e765b3282056cfcfa",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.733974358974359,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.380Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "70e8f290ae77161b7a2bf5ae",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.04166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "022fddfdc354abe9f46d176a",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.17937678557918038,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:52.970Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3c9d477910b4c2e6d833361f",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-72B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "738657f100ad1e5f719347ae",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.0941025641025641,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:19.047Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "97036ba9f48e63684554a673",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-7b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.13333333333333333,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:01.032Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "03038de8c6626beb89d02b72",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.49038461538461536,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:38.952Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8de0e2170b59c107ba5c68eb",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.06181733560418979,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:09.837Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7ffabd1d8ff41b6e432e9fb3",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-7b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.13333333333333333,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:01.032Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "eafeca9277967864f9c0f037",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.21543483836378974,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:09.837Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "5ec574080bee7e027e7cc2a4",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.047Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3ae566cf4705b4269dc33701",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.1282051282051282,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:59.651Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d9f6aa27f77279e8a12f1444",
      "sourceId": "livebench-model-judgment",
      "model": "qwen1.5-7b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.13333333333333333,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:01.032Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0cd6bb75763141062a7d9150",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.49038461538461536,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:38.952Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d150ac9cb970fb5652561dd8",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.035,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e13abde88ef35ecdcee20bf1",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.11045200681256936,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:09.837Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e0e38e34dac38e1738402cd1",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen1.5-7B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9d1bd256a61b4aeb8fcd47f7",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.01282051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.904Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "86f946a9ea9f64ddc41025a2",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.34294871794871795,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-13T19:13:58.221Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "14f1a1d2b86c628cb819093b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.028050005363988953,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:52.143Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bbccd6b6f84e793c3e232aa4",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.12793974537773992,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:52.143Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "78d1700e213b6441c17372d9",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.904Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "503f64fb3bea09358af559d2",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.02564102564102564,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.765Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "abd84185f8317623166cd5f2",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.34294871794871795,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-13T19:13:58.221Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "319feb25e6ba3fc3a97aa99a",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-13T19:14:14.605Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f8840718d3a7d248fda7c7b3",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.08415001609196686,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:52.143Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "484b5247542f1ac5a140b27b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-0.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1be1adf1a03a4980281d7f6b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.05205128205128205,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.169Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "387aabdc75741115698ef6bd",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.4150641025641026,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:16.471Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "416e96e15077f0c3c2c138c1",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.030482376548208318,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:47.104Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2d1a1d35096d6d736fcd2d27",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.16586592038786432,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:47.104Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "41787f95420de723ba7c8fc6",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.169Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7f9b3908eff51d06cc88eb7c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.0641025641025641,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:18.000Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9712841be595a33809632d1f",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.4150641025641026,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:16.471Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fea5e6c85c8a027874f4fd47",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-14T13:52:44.547Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d607e7b7270bfbeb18101a25",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.09144712964462495,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:47.104Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1fc77b2aab20e23105dc9211",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-1.5B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1d6090d9ebf5d841a2b9662d",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:52.937Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "865f6fb3ff510f02a8cfc67d",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3238461538461539,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:17.886Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1bfcf0b97b12c52277b23ffd",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8541666666666667,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T16:05:43.779Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8505ffc6757d6088abf2b52b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.29213597247987483,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:59.445Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "518a04bbde1daaaa6e7b985d",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-72b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:52.937Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "85d8471927f70b0725c20653",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.49004959766423184,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:59.445Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "460355280c4e30aadbd0a0dc",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.886Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1071498c1e294c0a1f91d71f",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:52.937Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "417421d8cff8d56a3dac5a63",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3076923076923077,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:45.125Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7b10cd69ec13ea6da88acc6f",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8541666666666667,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T16:05:43.779Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d5e545034197f82d7f2a4b4",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.34,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-11T15:55:53.295Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c5acf95c09e78bb29abc2c42",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.33640791743962434,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:59.445Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f5e254e9a59db9823a933023",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b0ffd85653e0bf7aff748f2e",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2894871794871795,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:17.311Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d6048958e1f8a1ac7a975a1c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.46153846153846156,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:16.688Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ff94e2115e44a5d0c79ca086",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.10208259332045577,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:30:54.210Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ab43942f71c4bffad39589b0",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2843694114486989,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:30:54.210Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "6310deecf0395b2fb66e2985",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.22,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:17.311Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "86051ecf38e1473160604d5c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.358974358974359,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T18:01:19.188Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "32d41d0b7b461a147282a6c8",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.46153846153846156,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-14T13:50:16.688Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "92d60368565c4777db15a3af",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-14T13:52:44.551Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "78d17c4d530e56efeed4831c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.14624777996136734,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:54.210Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e61d5a38fbaca4a117d21760",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2-7B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.803Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fa48f3dcc23d104b683153e7",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.4115384615384615,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-08-09T17:23:50.913Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7dfbdf42aa9452d06e6e0d3a",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5433333333333333,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-08-09T17:23:56.990Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "484a2df490a2f99c337fc0a3",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.20305155708396375,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:33.753Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4d566bde2a9fd71241c8f672",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.38597445065191954,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2024-12-10T19:31:33.753Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c5cf8de42c15c06d27c622c1",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-09T17:22:45.184Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a93f639b98c79b1432b1aa77",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4230769230769231,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-08-09T17:23:50.913Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5ccb9ae4a96768824599980f",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5433333333333333,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-08-09T17:23:56.990Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ee77e9646f9dc2bd5721eccb",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.265,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-08-09T17:24:16.269Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f0f7636d32131a0f8bcf2d77",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.18415467125189125,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:33.753Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b8df2d2b17b28b72f0cbc64f",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2-math-72b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.16,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "212b7668047fa736c8bd732a",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5764102564102564,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:22.792Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "60250728c32d4153871740ca",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-72b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3333333333333333,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:14.406Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f6974add464d42856d7f20ba",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7851153846153844,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:50.255Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "68adab54acf1e01e3728aee0",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-72b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3978180815931798,
      "unit": "mean task score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:22:04.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d266d5d34837a0731d87403",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.36104531888974173,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "053b2ccbe8aabcf534eefb6e",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5741903199717943,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2024-12-10T19:31:50.255Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ad8a65a0744387516136a7b5",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-72b-instruct-turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.3655757074632565,
      "unit": "mean category score",
      "sampleCount": 115,
      "asOf": "2025-02-06T20:22:04.291Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "85d3adb0061f38de19b58a7d",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.64,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:22.792Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4194846249487637d22275e2",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5128205128205128,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:20.625Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c04527226bbcf0cfb692e08e",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-72b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3333333333333333,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:14.406Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b547a9ebb7f066a7039c53b",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6551666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:50.255Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c8bb365bb6f6c4491a2210ae",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.9150641025641024,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-09-20T16:40:19.881Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "de4ea3f9107d8595e8ad44f1",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.33166666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.598Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2059a17854f197f88f24f584",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3714692900025585,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:37.135Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2c836729c090fd923be933a3",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-72b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3156361631863595,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:22:04.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0565949b6e715a46e0b2b263",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-72B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.38,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5547c340bd61c168e6558be5",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-72b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.48,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:11:27.262Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "491168892e09ddb2e4763a18",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.38371794871794873,
      "unit": "mean task score",
      "sampleCount": 256,
      "asOf": "2024-12-10T19:07:20.130Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8396b9fba82d64fec4f4033a",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-7b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3333333333333333,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:39.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0d8dd4992bb7613d96d77120",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6143782051282052,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4ff8a6db1435fb25913b79a5",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-7b-instruct-turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.20820694745682938,
      "unit": "mean task score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:21:53.586Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5200d4b788b913cc900d066a",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.15351927361562417,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "061d89236ba028f2a56257ae",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-7b-instruct-turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.27077014039508135,
      "unit": "mean category score",
      "sampleCount": 115,
      "asOf": "2025-02-06T20:21:53.586Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "690fe34ae35c492cd9848744",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.383871809153926,
      "unit": "mean category score",
      "sampleCount": 522,
      "asOf": "2024-12-10T19:31:49.961Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "b525873e23ad0890b9eb0925",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.37,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:07:20.130Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "03f248d1d00f415c95c1412a",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-7b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3333333333333333,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:39.291Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "668f46fd2d242756614789e7",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.3974358974358974,
      "unit": "mean score",
      "sampleCount": 156,
      "asOf": "2024-12-10T19:05:03.395Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "11d96e7192f723d9acc006a5",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5060000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.961Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "968ce12cc3cf84957d8efa69",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.7227564102564104,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-11-14T23:08:20.126Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fc2f4c6766f7d90f0b22a394",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.12166666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6aa5ac7b018a704187d67f16",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-7b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.13641389491365877,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:21:53.586Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e4f6918c0ab32e0f30de4692",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.15889115418020583,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:17.346Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1527cdb97bbf216df8aab02a",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-7b-instruct-turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-06T20:11:27.144Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "586891026f8c9a6f8aa90297",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-7B-Instruct-Turbo",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b27af73475d6bbbd36c82177",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5684615384615385,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-11-15T19:41:48.668Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f33eff1abcb848f91334a38c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6879166666666666,
      "unit": "mean task score",
      "sampleCount": 76,
      "asOf": "2024-12-10T19:31:49.812Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "859c9826734833a5e461b632",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-coder-32b-instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.37335808006042404,
      "unit": "mean task score",
      "sampleCount": 98,
      "asOf": "2025-04-02T21:37:23.528Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b458e926fe5479fccdf7d428",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.25134288925800713,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ebf6794d67667db5ea854b2c",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5025736981287374,
      "unit": "mean category score",
      "sampleCount": 394,
      "asOf": "2024-12-10T19:31:49.812Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "f733d683686d893ca6eedacc",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-coder-32b-instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.37335808006042404,
      "unit": "mean category score",
      "sampleCount": 98,
      "asOf": "2025-04-02T21:37:23.528Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dec3aa526eb1c75be3d1d713",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-11-15T19:40:51.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fe0a9f54ac6fb11dcf802b70",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5769230769230769,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-11-15T19:41:48.668Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6d6afc4e42af5e9dace707a0",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5633333333333332,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.812Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f9160b0aea0f95cce3e31c30",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.8125,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-11-15T19:41:56.620Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "57cd5c12b1e2c0a985670df9",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2316666666666667,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2024-12-10T19:31:44.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e80fe1c6890a1ba89fd4190c",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-coder-32b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.20504949345418147,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-02T21:37:23.528Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ed3f771f48cee4d2701b58e3",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.26236200110735464,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:02.734Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b547f622ef6f81f71a932b0",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-coder-32b-instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.5416666666666666,
      "unit": "mean score",
      "sampleCount": 48,
      "asOf": "2025-04-02T21:36:56.655Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dd74ffed3592daf7c40f84a5",
      "sourceId": "livebench-model-judgment",
      "model": "Qwen2.5-Coder-32B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.26,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b3fa4d26da7c1d5550f9bc63",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6441025641025642,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:41.963Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "de02021ab08271dc3572e7b4",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7663333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-02-03T21:32:43.997Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8fdbc03d16a4210a0623abac",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5721623614383137,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-02T20:57:00.009Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0f3b2133d1bcaac2afa93a08",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6608660862914038,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-02T20:57:00.009Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4a9fd2ba7039d08a6ba83e18",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.66,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-03T21:10:09.391Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6020fa0c6c30cb442db32a72",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6282051282051282,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:41.963Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "46cfc3adaea7a903f27764f8",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7663333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-03T21:32:43.997Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8eb0f99b5e8977ec503daba4",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5316666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-02-03T21:20:45.924Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "afb7a7ee287971595055a20b",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.48482041764827444,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-02T20:57:00.009Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2df0c6dee2d32d7459abf6ad",
      "sourceId": "livebench-model-judgment",
      "model": "qwen2.5-max",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.7,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-02T20:56:34.135Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "707d2134cf5d6053d3507fed",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.372051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:16.251Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c2767543304ea295a964a8ea",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.372051282051282,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:22.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "532e5fff5b82350d1369e741",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.36783333333333346,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.646Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "92ce4ea06884af20d286129a",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.36783333333333346,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2024-12-06T03:15:56.691Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ad4d0b52fbbbbc6f3809c050",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.20068904143409516,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-02-06T20:21:55.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bae09e3c9f87d71c969ba75c",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.2361030196405222,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:44.595Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3d00a44e7045c9916cbbd86e",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.31352455227290355,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-02-06T20:21:55.596Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a314e586acc060179b11cb63",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.32532921167504586,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2024-12-10T19:31:49.646Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "08e6ea3937d6aebfa84402e0",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:16.251Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7d5ed263a386b09547813de4",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.18,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-06T04:58:11.052Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d3cf30cd64cdc3afe32a280c",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5641025641025641,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:22.368Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e707639b918347bcf83f3ff2",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5641025641025641,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:04:41.153Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ac08923a81f2aec436b6958e",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.36783333333333346,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-06T03:15:56.691Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f3748970a7d49bf4ccefd03f",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.36783333333333346,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:49.646Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0c526d13fa1f89a88d3a9ae2",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.275,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:31:44.595Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1e2c5fe3edf6c6a45f84b138",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.17666666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-04T00:30:04.975Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "553b4e45a642bced479cf730",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.21540045763561888,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:21:55.596Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7a6f145fbf2c652e9f120296",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.23330905892156667,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:30:48.267Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b16d92a7c5f34f7c58019e56",
      "sourceId": "livebench-model-judgment",
      "model": "QwQ-32B-Preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.802Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "df8d2ab89e6446fe17d17342",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.21,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.171Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "715feaf75071c7c25b97b617",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.7223076923076923,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-13T18:04:34.755Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "45c7a2a65ff11664782ac03c",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.853,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-13T18:04:35.837Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "58854c6622eae7fd1801cb2d",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.5055995323873826,
      "unit": "mean task score",
      "sampleCount": 240,
      "asOf": "2025-04-01T23:39:36.887Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "91095982c57a7ddbfb646d43",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6936357415650249,
      "unit": "mean category score",
      "sampleCount": 418,
      "asOf": "2025-04-01T23:39:36.887Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "6e46b76eb86a876d64dba762",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.56,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-13T18:04:08.103Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e804c2eab71232866734b681",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.8846153846153846,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-13T18:04:34.755Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9b5e20cec1ee2a1796bb7d2f",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.853,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-13T18:04:35.837Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f5816dbece7468f05b79b6d4",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.6816666666666665,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-04-01T23:39:36.887Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f5bd98f1311e315b14aa89fc",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3151319304954811,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-04-01T23:39:36.068Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c79b108b182bc2fc56ef6480",
      "sourceId": "livebench-model-judgment",
      "model": "qwq-32b",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.52,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-04-01T23:37:56.764Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b2b1309bcd9505f65ce1320",
      "sourceId": "livebench-model-judgment",
      "model": "reflection-llama-3.1-70b",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.2,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:34.310Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "64e18b63c77318a6e8b1c9dd",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.17102564102564102,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:21.871Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a7e1b4d05cc0d534608ae9e8",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5737179487179488,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-10-04T14:31:29.995Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f2110d2d4b27b0d8940dd671",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.3379090311445951,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:30.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "40c07004944559ec3ae44c96",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.36088420696272827,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:30.673Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dc279a7079c52d1c4d2b1b9f",
      "sourceId": "livebench-model-judgment",
      "model": "reflection-llama-3.1-70b",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:34.310Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "be3c1c8a6e5503c02052c671",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:21.871Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5729ccb0a932da296086107f",
      "sourceId": "livebench-model-judgment",
      "model": "reflection-llama-3.1-70b",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:34.310Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d245886553209240b7295a89",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.28205128205128205,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:17.256Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2365109fcc226140c703231e",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5737179487179488,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-10-04T14:31:29.995Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a0b347f42951f51b43cfe7c4",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.2733333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-10-04T14:30:01.604Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4041e18b2811751f2e905c9c",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.32039376010045195,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:30.673Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "94922c37edf6c8b8f9657315",
      "sourceId": "livebench-model-judgment",
      "model": "Reflection-Llama-3.1-70B",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.42,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.806Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4165a94e3e2c6522cad18400",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.5456410256410257,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:31:23.006Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ef376cb4ab8f9cc33e8eebd7",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5253333333333333,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-01-20T00:13:02.680Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f9558d48451f8ae9d38f9f8b",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.20796764153740566,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-01-20T00:11:16.285Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a7e64e1e378904be1c07f40f",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.42631400017058824,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-02-06T18:31:23.006Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "ba282dbe2f2136858d4a8833",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-20T00:12:38.620Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "129a0421ba09ed6427aa9025",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.5512820512820513,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:31:23.006Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "e6feb959cb072054db70b4ee",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.5253333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-20T00:13:02.680Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5092cb122b31802f369f62c7",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.11166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-20T00:10:27.552Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "14c88a46720f2e3f84693c8e",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.25223625794555027,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-01-20T00:11:14.636Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "53437d5fd1da7c9adb4ec776",
      "sourceId": "livebench-model-judgment",
      "model": "sky-t1-32b-preview",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.26,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-20T00:11:16.285Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7fd6f74259d2476911de2b83",
      "sourceId": "livebench-model-judgment",
      "model": "Smaug-Qwen2-72B-Instruct",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.375,
      "unit": "mean task score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:07:17.555Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "b5b41f519c409963a92c2245",
      "sourceId": "livebench-model-judgment",
      "model": "Smaug-Qwen2-72B-Instruct",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.375,
      "unit": "mean category score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:07:17.555Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "341a8000ed3619ca56c9a853",
      "sourceId": "livebench-model-judgment",
      "model": "Smaug-Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 12,
      "asOf": "2024-12-10T19:07:17.555Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1281f904d4505879f50cd026",
      "sourceId": "livebench-model-judgment",
      "model": "Smaug-Qwen2-72B-Instruct",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.25,
      "unit": "mean score",
      "sampleCount": 28,
      "asOf": "2024-12-10T18:01:19.436Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5eccc22498e5de20ff3eb364",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6012820512820513,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-21T02:38:34.404Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8d52402c679927c952260504",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6101666666666667,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-21T02:38:37.453Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c1974bc7c0cdb34f082c88be",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.6904628255913141,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-03-21T02:36:45.792Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f5a7a9ef97985b54da0d4231",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6339705145133441,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-03-21T02:38:37.453Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "facdc24bf2e29984eb298b7b",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.6,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-21T02:38:17.444Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6950511ecab53ccd499d57ce",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6025641025641025,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-21T02:38:34.404Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "73429929ecdc6553f4e57a26",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.6101666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-21T02:38:37.453Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "13d147c9e536fd1b2d68d5a1",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.5166666666666666,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-21T02:36:22.597Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "981311bbcb0826dbd749bbcd",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.7347218101072757,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-03-21T02:36:44.132Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "25bfecea5d3e90d68bc631d3",
      "sourceId": "livebench-model-judgment",
      "model": "sonar-pro",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.82,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-21T02:36:45.792Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d84aad28dc7f37e84ce1d66c",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.3515384615384616,
      "unit": "mean task score",
      "sampleCount": 256,
      "asOf": "2025-03-22T16:24:57.812Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4c29ef6b2e49716628b429d9",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.829,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2025-03-22T16:24:58.715Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f7795368840bbb7445ec6f25",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4475580603481302,
      "unit": "mean task score",
      "sampleCount": 190,
      "asOf": "2025-03-22T16:21:57.791Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0511e779ce7547ae478bace5",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5426988406288639,
      "unit": "mean category score",
      "sampleCount": 521,
      "asOf": "2025-03-22T16:24:58.715Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "469a20a3a0163ce5e9c4d2b9",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.28,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-03-22T16:24:26.280Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "178a9cf316d36a269f3ebced",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.4230769230769231,
      "unit": "mean score",
      "sampleCount": 156,
      "asOf": "2025-03-22T16:24:57.812Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4b1c07f30f56e881963ff9fd",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7213333333333333,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-22T16:24:58.715Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "be6fd653137be91b5588f578",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.9366666666666668,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2025-03-22T15:43:04.947Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d07d7bfe06d713c7f9f03fa5",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.39583333333333326,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-03-22T16:21:40.413Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ac413cd74e9c985c87c50f4e",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.4468408477110574,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-03-22T16:21:56.938Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "57480ae37171cd47a1723929",
      "sourceId": "livebench-model-judgment",
      "model": "sonar",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.5,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-22T16:21:57.791Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "13f2224b53e50bfb0e6e2d36",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.18461538461538463,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:20.459Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "805534ff4d7d954e3c05c6d3",
      "sourceId": "livebench-model-judgment",
      "model": "starling-lm-7b-beta",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.26666666666666666,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:30.356Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d1845aaba2cb4c2d4e7bc5bd",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.41185897435897434,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.259Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f99f36f6c0a252ce55058ab3",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.09264336519341738,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:19.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "03378e252ae7a892d27f444d",
      "sourceId": "livebench-model-judgment",
      "model": "starling-lm-7b-beta",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.26666666666666666,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:30.356Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dc01c98c98f053b6974eb915",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.22970590805592547,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:19.118Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "1bd2871f06e97c724a4d7196",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:20.459Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1e0a8b948fe5226a04a7edc7",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.2692307692307692,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:04.231Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dc0c3b5a5bbbb0c0ca9dacf8",
      "sourceId": "livebench-model-judgment",
      "model": "starling-lm-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.26666666666666666,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:32:30.356Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2b0fd28027e2367a990c9f3e",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.41185897435897434,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.259Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9928353ceabaccc5d471df53",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.045,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "3f5484794ad9824c92a9bd2c",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.1329300955802522,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:19.118Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d6f98830fc0f1d6d9bd253bc",
      "sourceId": "livebench-model-judgment",
      "model": "Starling-LM-7B-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.1,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4f021c0ac20110a70c4d495d",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.47192307692307695,
      "unit": "mean task score",
      "sampleCount": 256,
      "asOf": "2025-02-06T18:32:21.524Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "8b733f69a173a1cbdc185391",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.8936666666666666,
      "unit": "mean task score",
      "sampleCount": 75,
      "asOf": "2025-01-06T21:50:01.646Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6ca83e2fcd0951094197a5c5",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.4407529659828233,
      "unit": "mean task score",
      "sampleCount": 290,
      "asOf": "2025-02-06T20:22:01.421Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6ac34acbe05070c0c29db449",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.6021142365241889,
      "unit": "mean category score",
      "sampleCount": 621,
      "asOf": "2025-02-06T20:22:01.421Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "4b8573011dd63f2b5bd5a734",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-01-06T20:21:16.175Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4bff51fbff9d0327339c69c2",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.40384615384615385,
      "unit": "mean score",
      "sampleCount": 156,
      "asOf": "2025-02-06T18:32:21.524Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "799d5b2dcaddadac25f0cd9e",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.8440000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-01-06T21:50:01.646Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "91df7560b66d21177c9115bf",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.9433333333333332,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-11-18T08:16:35.064Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "33d495f3fabe4ce2a1e5d8b9",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.40083333333333326,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-01-06T22:45:30.862Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "54ab74801cf8a4708a580a5d",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.3814255646151367,
      "unit": "mean score",
      "sampleCount": 90,
      "asOf": "2025-02-06T20:22:01.421Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7998e35ccd01ae7d7f1976cc",
      "sourceId": "livebench-model-judgment",
      "model": "step-2-16k-202411",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.54,
      "unit": "mean score",
      "sampleCount": 100,
      "asOf": "2025-02-06T20:11:27.227Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "59766e55b005af8999bdd32f",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.026410256410256412,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:05.808Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0c4d99da49ab74e6bf36852b",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.6333333333333333,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.232Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "71dd9a82d059eddf017b37b2",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.0791626328986176,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:40.602Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9c49ad3b7bb17ef4a514a8de",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2463020742140691,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:32:05.808Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "0dc2de60a644e89f1db68102",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.457Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "28b4abde4fa53d2780f48f4c",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.01282051282051282,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:05.808Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9231751c8971d65e8cf8911e",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.6333333333333333,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.232Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "80017b38201f755b1e5a04c2",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.01,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "004f59881292c67f703d75f0",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.10748789869585282,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:40.602Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "405f6ee0dd2ac41e69c4698e",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5-16k",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.12,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "685899fceac29763fc981b63",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.019230769230769232,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:41.624Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4a35a63c580fbdb76c492b67",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5816666666666667,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:38.965Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "1162d4517dd049a345fd6fae",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.08659993059937081,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:38.618Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a3f18885b043794d810a7aa4",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2291657888322689,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:32:41.624Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "5c2b7bfe69a16a7f5d503657",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.125Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "04f5981d842e1093a34df6b0",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.038461538461538464,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:41.624Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "7fa5fff1d283d65561ee67a4",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5816666666666667,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:38.965Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "750a948c5df4943e5364365d",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.01,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "6cf63f9d7842f3bc4b594586",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.10979979179811243,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:38.618Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f917758d1fe286ea52e37977",
      "sourceId": "livebench-model-judgment",
      "model": "vicuna-7b-v1.5",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.14,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "554314706a82aa441e96c462",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.6412820512820513,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-03-05T16:09:24.906Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "83e0602188c00edaa2fdf1ea",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.7190000000000001,
      "unit": "mean task score",
      "sampleCount": 50,
      "asOf": "2025-03-05T16:09:25.917Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dbf5436f4cc73faeb372d8e6",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.31883129993967285,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2025-03-05T17:48:29.712Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ac20d64dcfb2525f4096bc27",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.5597044504072414,
      "unit": "mean category score",
      "sampleCount": 318,
      "asOf": "2025-03-05T17:48:29.712Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "c3a52b386e47a5aa544af603",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.68,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-05T16:09:09.017Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "4edb1fbc5f2ccfba5ad08ede",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.6025641025641025,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-03-05T16:09:24.906Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d54a2689095ab4c548797a1a",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "paraphrase",
      "score": 0.7190000000000001,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-05T16:09:25.917Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "a3ac8a194ec23c9d5ec6b6da",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.3266666666666667,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-05T17:48:29.712Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "2d1a9392aa40281b76adcc96",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.2298272331523518,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2025-03-05T16:07:28.924Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "200aa7bf8ce8022db3c651d3",
      "sourceId": "livebench-model-judgment",
      "model": "wbot-4:347b_no_s",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.4,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2025-03-05T16:07:29.785Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "06b3eb8874275fccc59f1e66",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.02,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2024-12-10T19:07:23.704Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "373b1edef5d87fb2c6e5452d",
      "sourceId": "livebench-model-judgment",
      "model": "yi-6b-chat",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0,
      "unit": "mean task score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:32.317Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "60feaf313e45aad135aa4fb7",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.4631410256410256,
      "unit": "mean task score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.134Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "71ff28e6e47bf80b348d27d7",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.04689133606956498,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:43.564Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "456a18f71aadd68e19239d3b",
      "sourceId": "livebench-model-judgment",
      "model": "yi-6b-chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0,
      "unit": "mean category score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:32.317Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a28e08719377a8dda442b303",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.17667745390353018,
      "unit": "mean category score",
      "sampleCount": 294,
      "asOf": "2024-12-10T19:31:43.564Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "dfc28db0ffa5b03e72ff6d55",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:23.704Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "12e8522fb21b572d098c5924",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2024-12-10T19:05:31.158Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "5242630a2225ec88b087bc48",
      "sourceId": "livebench-model-judgment",
      "model": "yi-6b-chat",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 15,
      "asOf": "2025-02-06T18:31:32.317Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "dab2bcc76a89d42f96d4fdf4",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.4631410256410256,
      "unit": "mean score",
      "sampleCount": 26,
      "asOf": "2024-06-11T15:33:39.134Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "cd3bcaa76bf4d54c7ed368bf",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.424Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0abc95b9bc7410843c68f06e",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.10067400820869495,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:43.564Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "962f9ac9cfc0a62df09451c3",
      "sourceId": "livebench-model-judgment",
      "model": "Yi-6B-Chat",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.807Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "78748d525391e42ffcf5bc3f",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.12256410256410256,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:42.983Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "f494c5aa1602b54cdc5d3069",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5633333333333332,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.002Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "abf44c7ef9918b5f42ba541a",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.0719671166725223,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:14.975Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "c9fc32cbbaba4e2dd83a549c",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.25262151752331935,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:32:42.983Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "15db5232ffdda27aa11a147f",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:19.715Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "905d49bc13a3aa77da4e188e",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.20512820512820512,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:42.983Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "bfb7d7b200067a3c1293b80f",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5633333333333332,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:39.002Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "73e3961e2a610d98207ca54b",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0.04,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.423Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "9173203ab8b63355c519deb1",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.11590135001756692,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:14.975Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d48e9c76df98ca9f0a8634fc",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-alpha",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.06,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.805Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "67cf45b0cf87339bafe6f690",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench category mean",
      "category": "coding",
      "score": 0.08051282051282051,
      "unit": "mean task score",
      "sampleCount": 128,
      "asOf": "2025-02-06T18:32:28.808Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "d854c730ecb61e26a02827f4",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench category mean",
      "category": "instruction_following",
      "score": 0.5883333333333333,
      "unit": "mean task score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:38.978Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "77677fea1728730fd316c7de",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench category mean",
      "category": "language",
      "score": 0.04284714886587875,
      "unit": "mean task score",
      "sampleCount": 140,
      "asOf": "2024-12-10T19:31:01.693Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "377dab1c2a8f3d1ce24480f6",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench overall mean",
      "category": "overall",
      "score": 0.2372311009040108,
      "unit": "mean category score",
      "sampleCount": 293,
      "asOf": "2025-02-06T18:32:28.808Z",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "aggregation": "Mean of category means computed from task means, not an official YerelAI benchmark."
      }
    },
    {
      "id": "a571afb97bf56962bb790b87",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "coding_completion",
      "score": 0.02,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:18.130Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "345d4114c2d351bd6eec397a",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "coding",
      "task": "LCB_generation",
      "score": 0.14102564102564102,
      "unit": "mean score",
      "sampleCount": 78,
      "asOf": "2025-02-06T18:32:28.808Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "780ca9315581df186bdcc684",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "instruction_following",
      "task": "story_generation",
      "score": 0.5883333333333333,
      "unit": "mean score",
      "sampleCount": 25,
      "asOf": "2024-06-11T15:33:38.978Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "0bbe7dbbafdb496978f84ebb",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "connections",
      "score": 0,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-06-07T20:33:45.422Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "ff2f7ff8add2078f62eda347",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "plot_unscrambling",
      "score": 0.10854144659763625,
      "unit": "mean score",
      "sampleCount": 40,
      "asOf": "2024-12-10T19:31:01.693Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "fb6f66273b030b02897bdb31",
      "sourceId": "livebench-model-judgment",
      "model": "zephyr-7b-beta",
      "benchmark": "LiveBench task mean",
      "category": "language",
      "task": "typos",
      "score": 0.02,
      "unit": "mean score",
      "sampleCount": 50,
      "asOf": "2024-12-10T19:07:28.804Z",
      "provenance": "external-dataset",
      "verification": "third-party"
    },
    {
      "id": "32129003f437f3f6c1cd5bce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 911.1955820654973,
      "unit": "Arena rating",
      "confidenceInterval": [
        868.8305919512236,
        953.560572179771
      ],
      "voteCount": 263,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 467.21635481652817
      }
    },
    {
      "id": "844204b567fd3a8643adfc38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 997.8181780412451,
      "unit": "Arena rating",
      "confidenceInterval": [
        970.7693919006267,
        1024.8669641818635
      ],
      "voteCount": 626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.45806966341726
      }
    },
    {
      "id": "e08200ce393da11b384dcb0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1090.3575194418315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.2609493128048,
        1112.4540895708583
      ],
      "voteCount": 954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.10234165122954
      }
    },
    {
      "id": "4df97fe0e5260eefbffdba58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1091.1058462647836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.7357200603137,
        1103.4759724692535
      ],
      "voteCount": 4750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.83383122322894
      }
    },
    {
      "id": "7015b730a261d75800bc9fd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 888.3315197073115,
      "unit": "Arena rating",
      "confidenceInterval": [
        871.2675473636823,
        905.3954920509407
      ],
      "voteCount": 4016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.79910803040438
      }
    },
    {
      "id": "ae992fcb33ba43e55200bdf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1020.0373253392831,
      "unit": "Arena rating",
      "confidenceInterval": [
        998.4211829677965,
        1041.6534677107697
      ],
      "voteCount": 899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.63546007762426
      }
    },
    {
      "id": "7a44eb6ee4e0fdac02bde024",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1006.7671665097873,
      "unit": "Arena rating",
      "confidenceInterval": [
        986.9708217739308,
        1026.563511245644
      ],
      "voteCount": 1057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.01730207017096
      }
    },
    {
      "id": "d0e41d01cc5bd5464241282b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 983.6170362561047,
      "unit": "Arena rating",
      "confidenceInterval": [
        949.7713424482696,
        1017.4627300639398
      ],
      "voteCount": 391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 298.202074473035
      }
    },
    {
      "id": "f95e37467e4cf13067840f01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1071.912986263751,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.3136822129218,
        1093.51229031458
      ],
      "voteCount": 935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.44603320148636
      }
    },
    {
      "id": "d09f49f5118cbdc0450d4956",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1095.0272352882544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1051.6253707705812,
        1138.4290998059278
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 490.366272693791
      }
    },
    {
      "id": "83d2da6db37ae86ce5b05b11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1077.200947222968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1055.3520019986115,
        1099.0498924473243
      ],
      "voteCount": 986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.26956260607997
      }
    },
    {
      "id": "4a0775bda14d19efed56563c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 978.9191578967634,
      "unit": "Arena rating",
      "confidenceInterval": [
        953.5168176627512,
        1004.3214981307756
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.97756255731937
      }
    },
    {
      "id": "0e514ea9f5e745664352d013",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1040.595777743375,
      "unit": "Arena rating",
      "confidenceInterval": [
        991.1954992636242,
        1089.9960562231258
      ],
      "voteCount": 212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 635.2762395188112
      }
    },
    {
      "id": "6413fa97177b06fd67da033b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1007.0863141228349,
      "unit": "Arena rating",
      "confidenceInterval": [
        987.3212224025879,
        1026.8514058430817
      ],
      "voteCount": 1335,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.69544148313517
      }
    },
    {
      "id": "ed1b43e3b322252428ab2a15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1077.0400796051144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1057.7615821054515,
        1096.3185771047777
      ],
      "voteCount": 1217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.74982427050035
      }
    },
    {
      "id": "7a857dee0c2d046ba43a15f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1019.8543242993665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1003.5372866713174,
        1036.1713619274158
      ],
      "voteCount": 1512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.30849174300545
      }
    },
    {
      "id": "34e01a02c086199b2e2a6f5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 990.4782462679689,
      "unit": "Arena rating",
      "confidenceInterval": [
        967.7323350107314,
        1013.2241575252062
      ],
      "voteCount": 652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.6822920852328
      }
    },
    {
      "id": "a1568f9e7ae5113755b9a315",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1008.8000636897166,
      "unit": "Arena rating",
      "confidenceInterval": [
        982.8162048523395,
        1034.7839225270936
      ],
      "voteCount": 653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.75638620505583
      }
    },
    {
      "id": "1e9cb0c386f6706df9957ad0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "alpaca-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1067.1798911748342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1055.7066368126307,
        1078.6531455370375
      ],
      "voteCount": 5745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.26707711942522
      }
    },
    {
      "id": "43ea290b7d9756bb605f5858",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1388.8859972292266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.695562367503,
        1413.0764320909507
      ],
      "voteCount": 552,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.33200877930122
      }
    },
    {
      "id": "5cf6232ff9b527b86df4e39e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1288.621959326002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.7621353847594,
        1320.4817832672447
      ],
      "voteCount": 322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.23513278311464
      }
    },
    {
      "id": "2260e5026b3e424dadf1cbad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1371.9957918871269,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.9041467737156,
        1387.0874370005383
      ],
      "voteCount": 1402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.289390531068705
      }
    },
    {
      "id": "e57b4fa596752785c406b2d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1304.9647308638423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.1745287316767,
        1320.7549329960082
      ],
      "voteCount": 1971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.905155830773
      }
    },
    {
      "id": "e1c4cdc702c038215c6b152d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1368.801695498089,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.7164266780364,
        1388.8869643181415
      ],
      "voteCount": 779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.01688093089496
      }
    },
    {
      "id": "97aacb849d2fcdb7ccd2152a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1357.5718488921766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.5054317752129,
        1372.6382660091406
      ],
      "voteCount": 1418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.09133361511013
      }
    },
    {
      "id": "82824d04ecc2ca52f2d0b02e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1368.7956321077484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.0194265165517,
        1392.571837698945
      ],
      "voteCount": 579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.15970642962776
      }
    },
    {
      "id": "55f67dd951474b692b5fe9d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1292.0667604598889,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.6565007035488,
        1316.4770202162292
      ],
      "voteCount": 484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.11315080668624
      }
    },
    {
      "id": "64e5cc3bdd9778e53f945820",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1342.4218953774644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.3093241934807,
        1381.5344665614475
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 398.23236328373343
      }
    },
    {
      "id": "bee68c2559490777ba38f9ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1386.790755126297,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.1354008356443,
        1414.4461094169499
      ],
      "voteCount": 434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 199.09587910233822
      }
    },
    {
      "id": "9e6bff6ce7f46b57474d5e21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1382.5669058882156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.6238354942927,
        1400.5099762821385
      ],
      "voteCount": 1001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.81028931688427
      }
    },
    {
      "id": "d323eb93e11f0672d529571f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1307.166499503314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.0196506055495,
        1330.3133484010784
      ],
      "voteCount": 618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.47217421925285
      }
    },
    {
      "id": "aea09f8e0b7a5522adad2b1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1316.7098257443263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.353054644232,
        1338.0665968444205
      ],
      "voteCount": 720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.7339740217251
      }
    },
    {
      "id": "5c015b721a40a8b7732e6273",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1335.3399228422504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.23826022008,
        1359.4415854644203
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.21602710502296
      }
    },
    {
      "id": "647fb8df1936a80dafd377f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1348.6682965503978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.9214409489045,
        1374.4151521518916
      ],
      "voteCount": 481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.56480006842156
      }
    },
    {
      "id": "b07a8d8e6afb96dbef365738",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-09",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1347.7474182473336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.9080991597084,
        1358.5867373349588
      ],
      "voteCount": 2839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.584953208512424
      }
    },
    {
      "id": "b8ff877fb7548c568623b1f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1355.3409092083846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.2621812406471,
        1379.419637176122
      ],
      "voteCount": 606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.92837580894314
      }
    },
    {
      "id": "72323addf8e55e7873b52637",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1411.268262758597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.9400197860882,
        1423.596505731106
      ],
      "voteCount": 2293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.56454614857765
      }
    },
    {
      "id": "c4e853f528bcac66c5d5ebc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1280.8772415847861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.5656088566934,
        1296.1888743128784
      ],
      "voteCount": 1547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.030485485623586
      }
    },
    {
      "id": "afd6e8b7cb806330c467dfc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1377.5692967372815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.345510722843,
        1385.7930827517202
      ],
      "voteCount": 5558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.605461770654852
      }
    },
    {
      "id": "da1ef809796963a8bfd2084d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1311.8884489617212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.2183278722348,
        1320.5585700512074
      ],
      "voteCount": 8161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.568347134532488
      }
    },
    {
      "id": "0a94e44cd3e662d3b14c1463",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1369.617350607726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.642216908336,
        1392.592484307116
      ],
      "voteCount": 652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.41049771541304
      }
    },
    {
      "id": "2bcb4b5e1d3616479504d9a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1381.7105289623896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.02162872307,
        1422.399429201709
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 430.97861514656154
      }
    },
    {
      "id": "fe76d9fbe3df3421b5af7e4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1326.03742526733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.9601374175181,
        1362.1147131171417
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 338.8219838740822
      }
    },
    {
      "id": "9baff965dacf3e079cc82821",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1395.416186094451,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.57406227497,
        1406.2583099139322
      ],
      "voteCount": 2997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.600783297142875
      }
    },
    {
      "id": "a4213a36f2ecc1614a79d1a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1372.9325197167102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.8453253094283,
        1381.0197141239921
      ],
      "voteCount": 5953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.0254886057465
      }
    },
    {
      "id": "e226e599e8957fe76bbc95f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1363.0578236455553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.177800686634,
        1375.9378466044768
      ],
      "voteCount": 2134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.18541449114501
      }
    },
    {
      "id": "b781f81fe71ea09ebf5e4d40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1296.624260133823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.6285026449314,
        1309.6200176227144
      ],
      "voteCount": 2032,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.96499366341315
      }
    },
    {
      "id": "a8163cdab8e2fccf82b51118",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1331.5604693948003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.6549700291891,
        1352.4659687604117
      ],
      "voteCount": 814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.76925384992298
      }
    },
    {
      "id": "a14f0a66b38b8a7685074d3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1374.6616796098701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.8256284747463,
        1388.497730744994
      ],
      "voteCount": 1846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.83427389159717
      }
    },
    {
      "id": "cb1da23e2610a904198551b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1386.4234655946223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.898750880857,
        1409.9481803083877
      ],
      "voteCount": 594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.0630313106016
      }
    },
    {
      "id": "b05eaac89fa89952f368844d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1350.0611343601017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.9483361950745,
        1374.1739325251287
      ],
      "voteCount": 643,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.35579020531577
      }
    },
    {
      "id": "9b659a3a241b476242db7466",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1397.764200298325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.1252303446972,
        1407.4031702519526
      ],
      "voteCount": 3862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.186056939209358
      }
    },
    {
      "id": "4e20ca01c2fcf61e289fff08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1316.122285020294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.2346399718676,
        1328.0099300687202
      ],
      "voteCount": 2505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.787093495861136
      }
    },
    {
      "id": "6c3443b085fc8358c853d3b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1347.7522093017956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.0128055465048,
        1358.4916130570862
      ],
      "voteCount": 3034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.02369630980773
      }
    },
    {
      "id": "95154ecbd36c7bf00beebbb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1253.1351477987428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.7982619046788,
        1301.4720336928067
      ],
      "voteCount": 167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 608.2206388232415
      }
    },
    {
      "id": "e1f21c607579a403f9f576f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1353.4966984917032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.9303034301788,
        1365.0630935532279
      ],
      "voteCount": 2582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.82570059024785
      }
    },
    {
      "id": "41f2d815a6fbffd1358a8951",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1395.763545327831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.6750754033683,
        1415.8520152522935
      ],
      "voteCount": 805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.05035788282112
      }
    },
    {
      "id": "d3c87145826751d3475e077c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1335.081000843692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.308801686771,
        1348.853200000613
      ],
      "voteCount": 1902,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.37537494769316
      }
    },
    {
      "id": "cedc242e69ee1e5d75842947",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1350.308186740757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.1055650827666,
        1356.5108083987475
      ],
      "voteCount": 11474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.015079486188775
      }
    },
    {
      "id": "414cc56502f216661d6eca9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1329.9155196204374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.7128944166707,
        1349.1181448242044
      ],
      "voteCount": 916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.98978719488395
      }
    },
    {
      "id": "20562eaa87ad888ae15718a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-10-20",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1307.357395474201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.263631903652,
        1343.4511590447505
      ],
      "voteCount": 272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 339.13151994983775
      }
    },
    {
      "id": "59ef2eed49f6ae64bd2ea03f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1395.1525499667073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.5621697065026,
        1412.7429302269122
      ],
      "voteCount": 1171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.54790956803585
      }
    },
    {
      "id": "f07a0ba8a086d5299ef57bcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1419.8203455701564,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.5707467695518,
        1428.0699443707608
      ],
      "voteCount": 5322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.716155124275996
      }
    },
    {
      "id": "61c01589b58f786d4fcf7cf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1304.256395595094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.4099738103496,
        1314.1028173798386
      ],
      "voteCount": 3831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.23833431216462
      }
    },
    {
      "id": "d265ae392bfe707e54de3afb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1380.5680202786716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.5947955489546,
        1386.5412450083886
      ],
      "voteCount": 11721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.287985459975904
      }
    },
    {
      "id": "d8c2994b814f4bd134faa78a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1333.6612788803932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.3469949462012,
        1339.9755628145854
      ],
      "voteCount": 17781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.378916828891615
      }
    },
    {
      "id": "7f326520668aa8ed9f8a10a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1413.434884100782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.262368781318,
        1428.6073994202463
      ],
      "voteCount": 1535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.92651017869865
      }
    },
    {
      "id": "63f84d98dfc1232acddbcf00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1397.2028634391113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.334413276918,
        1424.0713136013048
      ],
      "voteCount": 567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.92694333446713
      }
    },
    {
      "id": "39996d5ed2ee9cd2eac0d5f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1328.103668061901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.9219649988552,
        1356.2853711249472
      ],
      "voteCount": 455,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.7465576502487
      }
    },
    {
      "id": "43863ed8a9c1604c54d775c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1403.506468251973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.940107327876,
        1411.0728291760702
      ],
      "voteCount": 6546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.903144952458232
      }
    },
    {
      "id": "ec41d2637d9670ee6cc85d80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1393.885343263036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.2476322241628,
        1399.5230543019093
      ],
      "voteCount": 13649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.273884282349663
      }
    },
    {
      "id": "156682b862cdd2c6a596c0ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1376.2144048989549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.4124980606634,
        1385.0163117372463
      ],
      "voteCount": 4694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.167745537868868
      }
    },
    {
      "id": "e50ff1cc7bba550c997d26c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1316.022642924052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.9480221825552,
        1325.0972636655492
      ],
      "voteCount": 4456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.436840910123035
      }
    },
    {
      "id": "dfc51cf1c5fc58d21165076f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1366.8649715656065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.723838132794,
        1381.0061049984192
      ],
      "voteCount": 1838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.05617555688864
      }
    },
    {
      "id": "1da12993b6734fc618995365",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1387.5825415668874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.865918213632,
        1397.2991649201426
      ],
      "voteCount": 3914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.57732174048576
      }
    },
    {
      "id": "324de41ad17edb2b18a6e2c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1396.171275805684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.0581480056965,
        1414.2844036056715
      ],
      "voteCount": 1053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.40645989259868
      }
    },
    {
      "id": "458683d443ee557a48520174",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1385.9339903159162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.0051554998313,
        1400.862825132001
      ],
      "voteCount": 1697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.01705012828339
      }
    },
    {
      "id": "9d12d0c22f749a68220c17b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1409.6897315016513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.0102771965908,
        1416.3691858067118
      ],
      "voteCount": 8759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.614105967516032
      }
    },
    {
      "id": "d01f48caa2f848f5621e1c04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1333.2823473944577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.1821022956497,
        1341.3825924932653
      ],
      "voteCount": 5665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.080482630008678
      }
    },
    {
      "id": "89be1e67f69f9fa5bb355bab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1365.0276077583242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.6333401638071,
        1372.4218753528412
      ],
      "voteCount": 6723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.232924472543427
      }
    },
    {
      "id": "b772b7cbc2f7a1168217d963",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1302.249894406823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.2928407357922,
        1349.206948077854
      ],
      "voteCount": 170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 573.9915465410769
      }
    },
    {
      "id": "d6109f99cc62adbcd033b744",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1301.9140376507287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.7076665644886,
        1334.1204087369688
      ],
      "voteCount": 370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 270.0146967492907
      }
    },
    {
      "id": "d3197ce58fc8c9ba31403326",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1373.3233660539245,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.5217352162272,
        1381.1249968916218
      ],
      "voteCount": 6119,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.844356680286335
      }
    },
    {
      "id": "0c26e97292ffbedae74431bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1398.2922473667488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.7482813215365,
        1412.836213411961
      ],
      "voteCount": 1584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.06422382683918
      }
    },
    {
      "id": "3b5ff224211c62d2d1a0b599",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1344.6739630709812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.2196939026016,
        1354.1282322393604
      ],
      "voteCount": 4100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.268036878765518
      }
    },
    {
      "id": "a21d39c3d01a5b9e5cafdc56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1367.1987448068007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.814249739597,
        1371.5832398740044
      ],
      "voteCount": 25407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.004295995774881
      }
    },
    {
      "id": "6fde004a2a894d8d417af830",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1352.4706019348696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.1577379010073,
        1363.783465968732
      ],
      "voteCount": 2731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.31570078513252
      }
    },
    {
      "id": "ea0bc63c430baba5bea89edd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-11-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1370.933101126837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.784795994336,
        1396.0814062593379
      ],
      "voteCount": 614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.63465588395704
      }
    },
    {
      "id": "c2aa4e33748fa64ac819f60a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1411.5036438738389,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.833408739445,
        1447.1738790082327
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.2193970917104
      }
    },
    {
      "id": "dfe2a899e3e8277ccc90bbdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1435.0159687119487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.6354498096716,
        1456.3964876142256
      ],
      "voteCount": 704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.99817487774621
      }
    },
    {
      "id": "dc3ceacb59b0d6775aa2d53a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1342.2838675500516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.1601041598713,
        1366.407630940232
      ],
      "voteCount": 581,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.49347871969434
      }
    },
    {
      "id": "0b8aea3405a3b2d4c4a1d1ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1420.3990287333795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.4600794756823,
        1434.3379779910767
      ],
      "voteCount": 1669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.57826088411614
      }
    },
    {
      "id": "8f11f4a3b3fa358c5eb8d3f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1374.5631408094932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.5693547493868,
        1388.5569268695997
      ],
      "voteCount": 2538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.97700051894486
      }
    },
    {
      "id": "f61f16d9b7c5e9380bfbbd3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1404.1164262722723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.294352530686,
        1439.9385000138586
      ],
      "voteCount": 242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 334.0452226729257
      }
    },
    {
      "id": "7de6fc24bc627fe375d8f0e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1441.227559445295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.3519534692823,
        1460.1031654213073
      ],
      "voteCount": 901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.74822862666977
      }
    },
    {
      "id": "d35efbbed33c6bc26fdfc817",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1417.719341980045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.608868292737,
        1430.8298156673532
      ],
      "voteCount": 1859,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.7445953031296
      }
    },
    {
      "id": "8c78b1b936f9edf059e62b93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1399.4144461253231,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.9777324585095,
        1422.8511597921367
      ],
      "voteCount": 594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.9872278055444
      }
    },
    {
      "id": "d5421c930a44c653c2ba6d00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1322.767873902018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.7451351628738,
        1343.7906126411622
      ],
      "voteCount": 728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.04888239683243
      }
    },
    {
      "id": "e30755146bb4a28f72edab25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1396.4596025582819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.3311243512808,
        1431.5880807652832
      ],
      "voteCount": 256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 321.23472845578476
      }
    },
    {
      "id": "470e9fa32e2335cc15699123",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1419.6023831934672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.4941212848037,
        1442.7106451021307
      ],
      "voteCount": 600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.00754722730557
      }
    },
    {
      "id": "6a145ca9f60c88bf4ac45721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1434.1976752624362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.8011037251595,
        1472.5942467997131
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 383.7856331753745
      }
    },
    {
      "id": "65763390a1f554b1c93514b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1432.6832480148134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.0984409795515,
        1449.2680550500756
      ],
      "voteCount": 1189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.60191928002466
      }
    },
    {
      "id": "d5eee850796f75a6db76b3de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1375.2803816824219,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.4900822090021,
        1395.0706811558414
      ],
      "voteCount": 829,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.95500499387431
      }
    },
    {
      "id": "95d06b9f65485ac82d54da68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1385.4464880883172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.8346814891743,
        1404.0582946874604
      ],
      "voteCount": 921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.17390555323253
      }
    },
    {
      "id": "dba3c662d58d554cbfa36abb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1385.5598523941235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.2632575504151,
        1405.856447237832
      ],
      "voteCount": 760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.23836476664805
      }
    },
    {
      "id": "bf1735e4242b195184e70bb3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1400.2233090828563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.408058863752,
        1437.0385593019603
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 352.82498445482224
      }
    },
    {
      "id": "871b0ba11d0fd7db4926c4fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1389.561611058474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.6599202612338,
        1412.463301855714
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.5334019844106
      }
    },
    {
      "id": "a220b3bedc00982e634af00e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1394.9152810701469,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3359721637544,
        1404.4945899765394
      ],
      "voteCount": 3681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.887581100637593
      }
    },
    {
      "id": "816a46ec69694abdc1c726d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-12-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1391.6629047250678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.1468597795897,
        1420.178949670546
      ],
      "voteCount": 382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.68125373412036
      }
    },
    {
      "id": "9be878508f9390d55a4659a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1479.164595663159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.8713911137302,
        1500.4578002125877
      ],
      "voteCount": 736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.02822342942375
      }
    },
    {
      "id": "9847479e02dfb144e6de4285",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1355.837798213299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.5056562169311,
        1381.1699402096667
      ],
      "voteCount": 551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.05044830031167
      }
    },
    {
      "id": "c6869184fcffb8ff93680b62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1434.3391000331442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.8832536821349,
        1448.7949463841533
      ],
      "voteCount": 1573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.3989935797947
      }
    },
    {
      "id": "515a359e7b49f7c6b193fcf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1401.123658794416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.6116846239654,
        1415.635632964867
      ],
      "voteCount": 2348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.82224440083312
      }
    },
    {
      "id": "0a13dce24c7926f60e6db02f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1472.3924419435523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.7196626338973,
        1508.065221253207
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.2666471445868
      }
    },
    {
      "id": "503ddcaaf25f1be49b9c0b07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1467.8840697092535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.6639968668499,
        1487.1041425516569
      ],
      "voteCount": 884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.16430041557706
      }
    },
    {
      "id": "56c5b30062c6ed54eb98389f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1447.1769447433308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.906469388189,
        1460.4474200984725
      ],
      "voteCount": 1856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.843395535763015
      }
    },
    {
      "id": "ee0eddff5d13857a2e5198be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1415.3260598562995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.1152859688195,
        1438.5368337437794
      ],
      "voteCount": 603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.24360265259182
      }
    },
    {
      "id": "ccc224968854ba5b5737d8ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1368.4062206987971,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.8505835855763,
        1391.961857812018
      ],
      "voteCount": 606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.4420116703189
      }
    },
    {
      "id": "068506f036c3a2507d9bbc94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1401.0244416016296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.5432267091342,
        1436.5056564941249
      ],
      "voteCount": 264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 327.71836664383403
      }
    },
    {
      "id": "5cc445629da5e446e3b4e1c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1435.2872196225667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.1458216945994,
        1459.4286175505342
      ],
      "voteCount": 555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.7150439767472
      }
    },
    {
      "id": "de75150c8a8a0dda13ae4a56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1438.0250911701526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.6718015432052,
        1475.3783807970997
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 363.21312060882246
      }
    },
    {
      "id": "7af00c4915ef8b4f78089161",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1467.1615192314682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.3431017426503,
        1483.979936720286
      ],
      "voteCount": 1170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.63326799298225
      }
    },
    {
      "id": "447886d216f58db13a98f2de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1374.5187698278712,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.7075515194335,
        1395.3299881363089
      ],
      "voteCount": 761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.74539900005873
      }
    },
    {
      "id": "faaa09837604613de3e4dc82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1402.0162088131942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.2770703334431,
        1420.7553472929453
      ],
      "voteCount": 926,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.41196804495219
      }
    },
    {
      "id": "ad9586ab9fc150c28bc2508b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1422.271186088479,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.1041079398374,
        1441.4382642371204
      ],
      "voteCount": 886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.63473198698752
      }
    },
    {
      "id": "800ce51046a2a2ebe7e03fea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1409.4169791142915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.9672832007125,
        1442.8666750278705
      ],
      "voteCount": 263,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 291.2649097482021
      }
    },
    {
      "id": "8e2b18e7077ee559c1801490",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1404.3404217515715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.8269694123621,
        1427.8538740907807
      ],
      "voteCount": 603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.92512498894047
      }
    },
    {
      "id": "fd00b91731951742e5244c84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1415.884207804389,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.993238809797,
        1425.775176798981
      ],
      "voteCount": 3414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.46721759060855
      }
    },
    {
      "id": "a6c160d0e7ff0e709bfa6d80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-01-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1413.0927554571729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.8845094119179,
        1443.3010015024277
      ],
      "voteCount": 342,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.54989229996974
      }
    },
    {
      "id": "8638e14b5348419aeb5af178",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1429.876371607656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.8997792487737,
        1468.8529639665383
      ],
      "voteCount": 213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 395.4681861293451
      }
    },
    {
      "id": "b4a4da079fdd8079b47b92f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1487.5406724801462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.4001524775263,
        1507.6811924827662
      ],
      "voteCount": 841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.59544301001789
      }
    },
    {
      "id": "d78536cc33e78b820b701d56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1342.5592267251404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.9698138582476,
        1369.1486395920335
      ],
      "voteCount": 457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.04385146535128
      }
    },
    {
      "id": "c5fc3835835aab5dce6b6734",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1439.5323952960916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.946030847418,
        1454.1187597447656
      ],
      "voteCount": 1562,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.3857369714279
      }
    },
    {
      "id": "8a321b4933ff3d8d6f8d6d8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1419.2216610447813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.8076453209183,
        1433.6356767686445
      ],
      "voteCount": 2360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.08462227124213
      }
    },
    {
      "id": "59e2e013c37ac62835e40456",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1493.9758517830012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.065806449637,
        1527.8858971163656
      ],
      "voteCount": 270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 299.33710816221907
      }
    },
    {
      "id": "1f45352cca650323667b7571",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1454.2663303924098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.3345088860942,
        1473.1981518987254
      ],
      "voteCount": 930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.30149879941513
      }
    },
    {
      "id": "3ceda8b9a2c05d7a8acea931",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1449.0194197941248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.1087988822935,
        1461.930040705956
      ],
      "voteCount": 1937,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.39084189346939
      }
    },
    {
      "id": "a61ffd249b0998d8b86fa84d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1432.8344208263243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.693092777556,
        1455.9757488750927
      ],
      "voteCount": 602,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.40565000354349
      }
    },
    {
      "id": "a20d4a4de687ce312a460bc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1372.8278564046711,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.151979895245,
        1397.503732914097
      ],
      "voteCount": 541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.50719998045344
      }
    },
    {
      "id": "7aa17d1c7f6765d7fcfd5e60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1445.794132318848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.845567201994,
        1481.7426974357015
      ],
      "voteCount": 247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 336.40848289170435
      }
    },
    {
      "id": "5f020050ddb31ce891a42d1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1425.8226691783536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.6685268422677,
        1449.9768115144395
      ],
      "voteCount": 512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.87526906418267
      }
    },
    {
      "id": "233b1d90e59c61ea789f3db5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1406.049406390466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.9798588352173,
        1443.1189539457148
      ],
      "voteCount": 216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 357.7160188593523
      }
    },
    {
      "id": "8d7c956d2f1de4a8f0fa90f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1472.4491490779833,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.1639526530146,
        1488.734345502952
      ],
      "voteCount": 1255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.03825733368
      }
    },
    {
      "id": "0d882421485769b9db4df0da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1374.2001235968005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.2637983173813,
        1395.13644887622
      ],
      "voteCount": 697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.10501496055332
      }
    },
    {
      "id": "68b311c3f60df38cb99a7f7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1417.511726900603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.8575660356723,
        1436.1658877655334
      ],
      "voteCount": 935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.58478401489909
      }
    },
    {
      "id": "c930827fd41720be8617d9cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1427.7208693101218,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.193410700772,
        1446.2483279194714
      ],
      "voteCount": 947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.35842828041675
      }
    },
    {
      "id": "85d4d674013aaf621109a282",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1428.2080316112908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.8846481284356,
        1467.5314150941458
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 402.5367863400075
      }
    },
    {
      "id": "bbbc2b347b8c792f1b4eac7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1430.6787366460746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.0734648318048,
        1454.2840084603442
      ],
      "voteCount": 599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.05136809585056
      }
    },
    {
      "id": "b2799c723f11861f0fb267b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1427.421712463989,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.557527665567,
        1437.285897262411
      ],
      "voteCount": 3418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.329476711620064
      }
    },
    {
      "id": "371f7df45d7c54bf35fd1ce4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-experimental-chat-26-02-10",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1407.110533228792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.3467646815302,
        1434.874301776054
      ],
      "voteCount": 379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.65992632628252
      }
    },
    {
      "id": "6c040ef8b4b151e9ed4c072b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1272.549874342104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.438982251824,
        1288.660766432384
      ],
      "voteCount": 1284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.5683004972958
      }
    },
    {
      "id": "1bd1259a65af678e81f59da1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1305.443119098807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.129131544792,
        1315.7571066528221
      ],
      "voteCount": 3060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.692172226684534
      }
    },
    {
      "id": "7d521c2651e90e47af003b3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1220.9951526097827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.4384937428263,
        1231.5518114767392
      ],
      "voteCount": 3037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.010605510839884
      }
    },
    {
      "id": "5e13a61566f93e2ae3b116d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1274.2857045459566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.9612957040104,
        1280.6101133879029
      ],
      "voteCount": 11044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.412228548335612
      }
    },
    {
      "id": "ccb702cc6fe3b1e603ad65fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1166.2328444085208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.9446934374469,
        1174.5209953795945
      ],
      "voteCount": 12331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.88212492328592
      }
    },
    {
      "id": "07a1a52ba62d071e033ebead",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1259.9489054994851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.2442731331469,
        1276.6535378658232
      ],
      "voteCount": 1138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.64030555040345
      }
    },
    {
      "id": "e1397c66d1462b0d03b45aac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1273.242330662618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.7566254735273,
        1318.7280358517091
      ],
      "voteCount": 170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 538.5842913122901
      }
    },
    {
      "id": "b561192cdce614e8c6f7bbe5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1259.6844980951219,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.1757574820333,
        1286.1932387082104
      ],
      "voteCount": 490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.9287678697633
      }
    },
    {
      "id": "86e9f7e464c4c35f4391ff40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1277.9244284165443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.6897757570814,
        1288.1590810760067
      ],
      "voteCount": 3136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.267795894508293
      }
    },
    {
      "id": "e4e3d2cd2200f9eea50c7fd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1271.1806786582079,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.8056411497396,
        1279.5557161666761
      ],
      "voteCount": 4913,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.259014749916254
      }
    },
    {
      "id": "7acc74c629ea5498f993fb64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1269.9996800815184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.1068795556382,
        1282.8924806073985
      ],
      "voteCount": 2103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.271140772010135
      }
    },
    {
      "id": "720107eeec3eca9d1103f2d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1206.9201056974748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.9176457035794,
        1216.9225656913704
      ],
      "voteCount": 3418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.044586340613886
      }
    },
    {
      "id": "91beb29df1d734ac8e55b5ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1283.8614273212106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.729008638637,
        1301.993846003784
      ],
      "voteCount": 1079,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.58847631242661
      }
    },
    {
      "id": "1d97962b7ece9884e1df5a5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1280.4417728639764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.0470986135083,
        1290.8364471144448
      ],
      "voteCount": 3333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.127140707920812
      }
    },
    {
      "id": "662a2c76614e6bf8c4b64e0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1257.480171138277,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.9219940919215,
        1269.0383481846325
      ],
      "voteCount": 2173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.776230299602126
      }
    },
    {
      "id": "e3931424dd6961c52b6d58f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1272.9526910283562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.1005682756718,
        1292.8048137810406
      ],
      "voteCount": 872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.59299817678027
      }
    },
    {
      "id": "5d53d2cb9ce0f9cf86b8de63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1295.5934642519098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.9725699695546,
        1304.214358534265
      ],
      "voteCount": 4869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.34676946871865
      }
    },
    {
      "id": "3fc67e07593dbff1f9491530",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1239.1006803108912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.7492012837051,
        1247.452159338077
      ],
      "voteCount": 5254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.15643618663703
      }
    },
    {
      "id": "f505a4522b222e394a0cfcab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1243.1743389408311,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.0802606337875,
        1250.2684172478748
      ],
      "voteCount": 7809,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.100738384949096
      }
    },
    {
      "id": "70aee1db1df6ae9a88b47573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1184.1990730637303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.2658460058901,
        1212.1323001215706
      ],
      "voteCount": 403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 203.1168913386562
      }
    },
    {
      "id": "f67ba9590d81756a3f6f9646",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1187.1186296573164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.7029327362143,
        1222.534326578419
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 326.5091849092744
      }
    },
    {
      "id": "da24cc4bbe6aabb47a85246c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1274.0597121055534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.2079552662638,
        1284.9114689448434
      ],
      "voteCount": 2784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.65518387563898
      }
    },
    {
      "id": "4feddf24d902a053d83b1e67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1244.423995412828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.5949722196583,
        1255.253018605997
      ],
      "voteCount": 2511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.526877624322
      }
    },
    {
      "id": "c37fc8384f56b0a61d9f4fc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1228.3828501759804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.708788527374,
        1239.0569118245867
      ],
      "voteCount": 3166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.659459438812497
      }
    },
    {
      "id": "9d44f8aa57d757cfe21d9fd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1260.2720799334418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.1065405871593,
        1265.4376192797242
      ],
      "voteCount": 19372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.946006187610439
      }
    },
    {
      "id": "d40d8103b4e0272a92e6637e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1248.4692039779334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.9327563116158,
        1260.0056516442507
      ],
      "voteCount": 2470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.645594543594314
      }
    },
    {
      "id": "96ce6526d2eca0f22652a8c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-lite-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1268.16950527357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.4914534529705,
        1322.8475570941696
      ],
      "voteCount": 107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 778.2692696822804
      }
    },
    {
      "id": "8958c5bcd95d60f687ffaa7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1259.549413197055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.3079621840056,
        1275.7908642101045
      ],
      "voteCount": 1281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.66785336556566
      }
    },
    {
      "id": "ef6d08b3949afa7dcae10725",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1288.0382950042208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.713210821213,
        1298.363379187229
      ],
      "voteCount": 2981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.75179127572685
      }
    },
    {
      "id": "a7e0478111ea8e94d5318c5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1197.8713115262078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.0551402655599,
        1208.6874827868555
      ],
      "voteCount": 3061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.454461755371558
      }
    },
    {
      "id": "2fff067d35b9c0e1dedd9c49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1255.042016182563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.7662409857658,
        1261.3177913793602
      ],
      "voteCount": 10991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.252707671514171
      }
    },
    {
      "id": "0b03346dc948d946c8c3356b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1130.5621573521507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.0851773893569,
        1139.0391373149448
      ],
      "voteCount": 12418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.706224026794818
      }
    },
    {
      "id": "d3f4853b85d9cf16d3bae87c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1241.9965653506183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.6931810500016,
        1259.2999496512352
      ],
      "voteCount": 1094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.94099123018285
      }
    },
    {
      "id": "6d5d9bc38252698f92bfef5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1279.0081300936617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.100591944146,
        1323.915668243178
      ],
      "voteCount": 163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 524.9794613927027
      }
    },
    {
      "id": "ef21c26ef3b6c8f31132c985",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1225.4171711135646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.0364198456232,
        1252.7979223815055
      ],
      "voteCount": 468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 195.16167554840433
      }
    },
    {
      "id": "285e342ede5a65d16f036225",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1255.9304412225092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.817881697435,
        1266.0430007475834
      ],
      "voteCount": 3050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.621100191746656
      }
    },
    {
      "id": "77be2031ae7f2f24825933e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1244.2004958506786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.9272635720831,
        1252.4737281292741
      ],
      "voteCount": 4859,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.81780712235418
      }
    },
    {
      "id": "7ec7356123c3995bd05dc78e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1233.9395822363056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.7829161746388,
        1247.0962482979726
      ],
      "voteCount": 2061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.06044967233036
      }
    },
    {
      "id": "95184eae198b1b6a6d60c150",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1193.3394691236804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.260977207635,
        1203.4179610397255
      ],
      "voteCount": 3339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.442037789028166
      }
    },
    {
      "id": "e4ba3e2761683a655888033c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1266.4503106214934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.8381382742625,
        1285.062482968724
      ],
      "voteCount": 1082,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.17744967533544
      }
    },
    {
      "id": "dcb918b9f8bad46fbc8cd4c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1256.7366044429623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.2000866948883,
        1267.2731221910362
      ],
      "voteCount": 3314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.90001206245243
      }
    },
    {
      "id": "4f35248874ac8a57cd021cf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1235.5188075444294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.6510172538165,
        1247.3865978350427
      ],
      "voteCount": 2016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.66431242819405
      }
    },
    {
      "id": "238d85f1d310bd9554e9e0ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1267.563357628201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.4336202584022,
        1286.6930949979997
      ],
      "voteCount": 952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.26246900424987
      }
    },
    {
      "id": "1c874e3b16ccfdfadbbd0caa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1271.3984163562586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.6917562976705,
        1280.105076414847
      ],
      "voteCount": 4685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.733630611226804
      }
    },
    {
      "id": "979dad34ceae097327aedf74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1222.1228190597865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.7022888910842,
        1230.5433492284888
      ],
      "voteCount": 5246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.45791706527028
      }
    },
    {
      "id": "02a1006401c5e96e2d70c1d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1214.2467466633423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.1586114939344,
        1221.3348818327504
      ],
      "voteCount": 7716,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.078797020846576
      }
    },
    {
      "id": "ad8e02b9be4e2014044dd52a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1184.330558985523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.0360261391963,
        1211.62509183185
      ],
      "voteCount": 443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.93453322626166
      }
    },
    {
      "id": "b8487af917f8addbdbedea17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1186.3142811435355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.577822618946,
        1223.050739668125
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 351.31637430517173
      }
    },
    {
      "id": "42c5dac2c96b4ce59210201c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1247.581385828104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.2730696291628,
        1258.889702027045
      ],
      "voteCount": 2625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.28891997132636
      }
    },
    {
      "id": "22cae859b731f56c389a52c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1223.829118541025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.9967715091898,
        1234.6614655728604
      ],
      "voteCount": 2455,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.545620217506027
      }
    },
    {
      "id": "1b98d469f81be9e6eb947c9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1209.6069251641525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.675427480227,
        1220.538422848078
      ],
      "voteCount": 3069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.107359779552358
      }
    },
    {
      "id": "863928f2f2dc19153e25457b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1240.5389589886968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.3862285527957,
        1245.6916894245978
      ],
      "voteCount": 19364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.911601082909287
      }
    },
    {
      "id": "4cf5803e15b70446af848c54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1220.7943541608415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.081089584467,
        1232.5076187372156
      ],
      "voteCount": 2465,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.7157458768108
      }
    },
    {
      "id": "53e8193fd2665799d2de656f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-micro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1248.735644568481,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.6122077369446,
        1294.859081400017
      ],
      "voteCount": 144,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 553.7925888187199
      }
    },
    {
      "id": "d4b0be9f26bb274f67ae71f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1290.2216853457253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.9261118221007,
        1304.5172588693501
      ],
      "voteCount": 1627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.19943071326134
      }
    },
    {
      "id": "897953b96b01824a30dc3402",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1342.578034188075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.461399094996,
        1351.6946692811534
      ],
      "voteCount": 3853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.635800173782776
      }
    },
    {
      "id": "3c859dc79ccedcb8814cdfea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1237.1547330596572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.6293300883538,
        1246.6801360309607
      ],
      "voteCount": 3944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.61949092801244
      }
    },
    {
      "id": "887d3c569e2fa7826824d7fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1305.549425409647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.0237936960343,
        1311.0750571232593
      ],
      "voteCount": 14188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.948179912797533
      }
    },
    {
      "id": "daf75e50b6161bae4e4af136",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1215.0490796120812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.8741255106995,
        1222.2240337134626
      ],
      "voteCount": 15626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.401150125469938
      }
    },
    {
      "id": "c5729ddefa3aab8947bbf4c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1271.4965920121126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.660820218178,
        1287.332363806047
      ],
      "voteCount": 1387,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.28032188153381
      }
    },
    {
      "id": "389150701730afee71754189",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1315.4580483745146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.7949401391966,
        1354.1211566098327
      ],
      "voteCount": 222,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 389.1323604363939
      }
    },
    {
      "id": "99d6b7ceeb5c0e37f85d04e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1278.866561157358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.4305739934568,
        1302.3025483212593
      ],
      "voteCount": 553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.97836316446566
      }
    },
    {
      "id": "e00dee2bd084d4b11bc1a67a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1314.5825345876706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.7642522351694,
        1323.4008169401714
      ],
      "voteCount": 4069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.242857538787693
      }
    },
    {
      "id": "ab8288e68dfd5771c3ab84f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1302.2088975378615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.9067100254638,
        1309.5110850502592
      ],
      "voteCount": 6300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.880649241629314
      }
    },
    {
      "id": "0c21bfbeb62369d2fce418b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1279.677617379948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.359007774612,
        1290.9962269852842
      ],
      "voteCount": 2591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.349550100046976
      }
    },
    {
      "id": "4359153f325697f647fd6db1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1239.7520810632159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.1153178998702,
        1248.388844226561
      ],
      "voteCount": 4518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.418060018731023
      }
    },
    {
      "id": "bb1d174330b12c3b56fe23b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1325.8147385606715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.7632474843354,
        1341.8662296370078
      ],
      "voteCount": 1296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.07096907709351
      }
    },
    {
      "id": "2b2ff7fb388cc7748a684979",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1303.9222016472395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.708649782686,
        1313.1357535117927
      ],
      "voteCount": 4281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.098255356405364
      }
    },
    {
      "id": "c38fc388d67ff8adeb14376a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1284.4139915413539,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.0433746506596,
        1294.7846084320477
      ],
      "voteCount": 2650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.997096861788787
      }
    },
    {
      "id": "3ab70908be7d55842d59bb04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1322.4500990786592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.9095038927444,
        1339.990694264574
      ],
      "voteCount": 1096,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.09261424818389
      }
    },
    {
      "id": "1cf2cf9627069d883c4f8506",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1329.3937705703497,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.845688951414,
        1336.9418521892853
      ],
      "voteCount": 6163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.831223966060739
      }
    },
    {
      "id": "e473c18f7fe3f096189fd2ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1273.5820882944417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.1862853575399,
        1280.9778912313436
      ],
      "voteCount": 6609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.238835722207499
      }
    },
    {
      "id": "c40eff2fe3a58b6d658ade2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1276.0182724669094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.7318076824838,
        1282.3047372513347
      ],
      "voteCount": 9525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.287664486451337
      }
    },
    {
      "id": "19b487aa04fecdcb53b9c388",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1227.552917114475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.504538433604,
        1253.601295795346
      ],
      "voteCount": 511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.63030207348334
      }
    },
    {
      "id": "ce2acc7119238c9cf6f665ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1241.1277166548464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.2721997594954,
        1273.9832335501972
      ],
      "voteCount": 326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 281.0091272215255
      }
    },
    {
      "id": "a994cf6e2549b09e9a1dc579",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1299.5185784504151,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.6395181302337,
        1309.3976387705968
      ],
      "voteCount": 3398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.40592971712559
      }
    },
    {
      "id": "b6f1bc1a1ee7d7b02e475dff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1269.120050310496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.2114662683935,
        1279.0286343525988
      ],
      "voteCount": 2978,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.55800863737264
      }
    },
    {
      "id": "768df1a3397040c892744e68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1276.94881077242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.5884737691154,
        1286.3091477757253
      ],
      "voteCount": 4060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.807978141910137
      }
    },
    {
      "id": "5210ef82b607f66c128abcd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1289.9275611612022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.3738211095024,
        1294.481301212902
      ],
      "voteCount": 24745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.39809208594077
      }
    },
    {
      "id": "648fce7192a3bfeee6bbe294",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1277.0936493669772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.7105466884625,
        1287.4767520454918
      ],
      "voteCount": 3014,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.06455210499895
      }
    },
    {
      "id": "910164dc66569b71a667fa81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "amazon-nova-pro-v1.0",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1221.38881367983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.8352257817633,
        1271.9424015778966
      ],
      "voteCount": 150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 665.2850827399357
      }
    },
    {
      "id": "5ee8c88fa78a2d6f1c667b41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1300.1568211725944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.4570807674309,
        1314.8565615777582
      ],
      "voteCount": 1678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.25008052023258
      }
    },
    {
      "id": "79ca2d2b444d194b089c31f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1350.2945164736961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.4591852989745,
        1361.129847648418
      ],
      "voteCount": 3122,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.562452220867982
      }
    },
    {
      "id": "f4e8b881be3fc127101402e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1270.4043660992286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.10133498795,
        1281.7073972105072
      ],
      "voteCount": 3097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.25781122897679
      }
    },
    {
      "id": "0a03524332051ff0b98f05a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1327.9865774523923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.0435694121338,
        1334.9295854926509
      ],
      "voteCount": 11268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.548712064127502
      }
    },
    {
      "id": "e02584d6e92345508c22ebd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1244.4499049678916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.614027615094,
        1253.2857823206893
      ],
      "voteCount": 12348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.323718732347665
      }
    },
    {
      "id": "c01c21e2db6bd292b401f718",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1296.5775066324993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.391715882237,
        1315.7632973827617
      ],
      "voteCount": 867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.82155735469902
      }
    },
    {
      "id": "c6bb8250d2d1bfc855c5ab9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1328.666802012643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.7087417713406,
        1371.6248622539456
      ],
      "voteCount": 199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 480.3890984732521
      }
    },
    {
      "id": "1c108fd8f667a14b5974f529",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1284.5215787067054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.7622037317192,
        1308.280953681692
      ],
      "voteCount": 585,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.95143838610838
      }
    },
    {
      "id": "303354e8621c7db3d9f756a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1324.6100375662686,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.498332779382,
        1334.7217423531547
      ],
      "voteCount": 3605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.61660022133553
      }
    },
    {
      "id": "a74314efbd69af3b72b8fa8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1312.0381951807146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.4272693632272,
        1320.649120998202
      ],
      "voteCount": 5448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.302053437312214
      }
    },
    {
      "id": "a5f0d2619bf03a02a65de6ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1298.9458307377984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.5445724735862,
        1312.3470890020108
      ],
      "voteCount": 2092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.75143778624809
      }
    },
    {
      "id": "9031d09863f92af2d40c91c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1271.070350606598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.4816883498775,
        1281.6590128633184
      ],
      "voteCount": 3246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.18676826181207
      }
    },
    {
      "id": "242aefd5ee876db347853263",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1332.2025035663223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.9924399202841,
        1351.41256721236
      ],
      "voteCount": 1008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.06416793975899
      }
    },
    {
      "id": "cc58b0fc803bd0184fe4e390",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1337.7107531833785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.1973893739773,
        1349.2241169927797
      ],
      "voteCount": 3029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.50708504111424
      }
    },
    {
      "id": "3d0f5a27441b930de988ed7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1268.1828630797418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.2185499199777,
        1279.147176239506
      ],
      "voteCount": 2559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.294403682728284
      }
    },
    {
      "id": "4cdc245b1a00dc412322d920",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1327.4396670103913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.5335298354048,
        1346.3458041853778
      ],
      "voteCount": 1039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.0485108818174
      }
    },
    {
      "id": "bf6d4f4894475f2c21a63b75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1332.6190408617072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.4162881265916,
        1341.8217935968228
      ],
      "voteCount": 5037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.04648334310982
      }
    },
    {
      "id": "4adffcc8d9b96d438e1c8973",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1277.650166721118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.7548902804879,
        1286.5454431617482
      ],
      "voteCount": 5378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.597889147991186
      }
    },
    {
      "id": "c167776f1fe09baf116d4be2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1277.152951368605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.4179657221546,
        1284.8879370150557
      ],
      "voteCount": 7490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.57481304458823
      }
    },
    {
      "id": "230cd85243d868df8a33f0f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1185.946722752798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.2050013290288,
        1208.6884441765674
      ],
      "voteCount": 676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.6326792650282
      }
    },
    {
      "id": "f19bd2a1b03672bfa51646d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1206.3199664194167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.727039103364,
        1237.9128937354694
      ],
      "voteCount": 396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 259.82656667318776
      }
    },
    {
      "id": "3bedb5aa4311afc0f3b0d10c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1292.0915258985628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.6677051102556,
        1304.51534668687
      ],
      "voteCount": 2123,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.18039244582714
      }
    },
    {
      "id": "2c351eca093a17c61faf223c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1260.7065457578942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.3020198443246,
        1271.1110716714634
      ],
      "voteCount": 2921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.18048156678557
      }
    },
    {
      "id": "afb69fccb3e00887e151def6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1295.819095570254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.984749075692,
        1306.653442064816
      ],
      "voteCount": 3344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.55689763791851
      }
    },
    {
      "id": "752d9f805014d527b8b92134",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1305.9977974295255,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.328866350931,
        1311.6667285081198
      ],
      "voteCount": 19621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.365774845933482
      }
    },
    {
      "id": "8dfaf92f005be4b0fd3ab308",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1287.486284981846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.3652240488543,
        1300.6073459148374
      ],
      "voteCount": 1934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.816890677007756
      }
    },
    {
      "id": "fd4f45a56b4915e41fc31733",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-70b-0725",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1287.365708351164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.6165675829486,
        1323.114849119379
      ],
      "voteCount": 271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 332.6863895510247
      }
    },
    {
      "id": "399eeb490e2179a2ee2cbd4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1332.8897503632113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.9685707257013,
        1346.810930000721
      ],
      "voteCount": 1781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.44938695055479
      }
    },
    {
      "id": "8fc634f1f9219c8613b73fe4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1369.2494682739402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.1368343407526,
        1378.3621022071277
      ],
      "voteCount": 4019,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.61681305886731
      }
    },
    {
      "id": "9a2f9ea4046c850f757ee502",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1253.751085226656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.9792398027591,
        1263.522930650553
      ],
      "voteCount": 3713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.857474060149073
      }
    },
    {
      "id": "30fbe8b9f769aa88d14d3f14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1330.9313076014837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.2422124928246,
        1336.6204027101428
      ],
      "voteCount": 13676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.425393754324007
      }
    },
    {
      "id": "1f8f7cee6e53cf1741de246c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1257.202455789301,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.0957947035065,
        1264.3091168750957
      ],
      "voteCount": 15433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.147253203984897
      }
    },
    {
      "id": "6e70a46fceb7250ceeb05b9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1310.5131693992198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.5265203235654,
        1325.4998184748742
      ],
      "voteCount": 1469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.46728053074049
      }
    },
    {
      "id": "c5cb7295dc0bdc5a105da7d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1360.4072262505138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.416738262888,
        1397.3977142381398
      ],
      "voteCount": 228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.19181811649844
      }
    },
    {
      "id": "ed451f2326cc16935c1bebde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1277.8773191136106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.375872183225,
        1300.3787660439964
      ],
      "voteCount": 626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.8028222073919
      }
    },
    {
      "id": "39fca6c7034859a9524ed9aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1346.8795071550844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.7749822617502,
        1355.9840320484186
      ],
      "voteCount": 4039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.57835796307316
      }
    },
    {
      "id": "63da175dd72d24227b34ad15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1333.2611363626258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.8613497473757,
        1340.660922977876
      ],
      "voteCount": 6517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.25417907807786
      }
    },
    {
      "id": "6ea73f2670158c29e810f0ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1309.8368125802576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.6241901683907,
        1321.0494349921248
      ],
      "voteCount": 2733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.7279055222012
      }
    },
    {
      "id": "b132392b31aca2336bd855f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1249.3961525442687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.4063855408117,
        1258.3859195477257
      ],
      "voteCount": 4378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.037817805331155
      }
    },
    {
      "id": "5647f22e2e87e8457970f39c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1327.1507598752478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.547181876862,
        1342.7543378736332
      ],
      "voteCount": 1443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.379996432634094
      }
    },
    {
      "id": "45d83ab475587337adacb73e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1336.029525670001,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.8817282220646,
        1345.1773231179377
      ],
      "voteCount": 4368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.78396334686064
      }
    },
    {
      "id": "300fa0349679eaf58e31a4fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1321.7616754784954,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.5623191756333,
        1331.9610317813572
      ],
      "voteCount": 2942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.08004272552186
      }
    },
    {
      "id": "a0c6fc962d38d6b052228b98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1332.7374661701597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.7054231969637,
        1349.7695091433557
      ],
      "voteCount": 1198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.51570936490663
      }
    },
    {
      "id": "429a3f3f5cfe6b2fa139bc8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1353.7446848585812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.0947585544907,
        1361.3946111626717
      ],
      "voteCount": 6182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.234153270824681
      }
    },
    {
      "id": "ad99a81ca2bc7b31f3f53a7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1278.2693150152506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.667855460168,
        1285.8707745703332
      ],
      "voteCount": 6686,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.041730255255914
      }
    },
    {
      "id": "f562e582a4b05fe6af0e806d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1301.8992075082294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.5854616326728,
        1308.212953383786
      ],
      "voteCount": 10236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.377148068426795
      }
    },
    {
      "id": "350c1e100eb596298eadd74d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1231.4630850822136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.4839383642939,
        1254.4422318001339
      ],
      "voteCount": 584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.45850431588985
      }
    },
    {
      "id": "2c1d081ef536be052ac09217",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1229.771967080941,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.6487447512718,
        1262.89518941061
      ],
      "voteCount": 349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 285.60708540992255
      }
    },
    {
      "id": "789b692a52f25792c6fd34c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1320.5871621956426,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.9509244290605,
        1330.2233999622244
      ],
      "voteCount": 3663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.172347701314717
      }
    },
    {
      "id": "e55bcfdea1bf177f603d2e6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1312.1673533281696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.7064402350125,
        1321.6282664213268
      ],
      "voteCount": 3412,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.300751285966054
      }
    },
    {
      "id": "a6020783b8e9ae70e80a4d58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1306.6394942303423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.415600203925,
        1315.8633882567594
      ],
      "voteCount": 4304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.14789354300645
      }
    },
    {
      "id": "35a9e0ae24da9055e61bc66d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1314.2917642703726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.750099171136,
        1318.833429369609
      ],
      "voteCount": 24739,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.369502274111523
      }
    },
    {
      "id": "041685f7f1a270639b69bbc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1304.2448355151055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.229546375017,
        1314.2601246551937
      ],
      "voteCount": 3448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.111438711568905
      }
    },
    {
      "id": "e371e0824dd8aab1d600c75d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "athene-v2-chat",
      "license": "NexusFlow",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1294.6096900755233,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.92783144844,
        1334.2915487026066
      ],
      "voteCount": 180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 409.9093541279442
      }
    },
    {
      "id": "3fe86dca4fa070d420829cd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1270.3558510285548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.9202810290894,
        1282.79142102802
      ],
      "voteCount": 2375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.25642560022516
      }
    },
    {
      "id": "96dae44ea1229bb818951c04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1292.0714917809112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.9610284975336,
        1301.1819550642888
      ],
      "voteCount": 4685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.606515938851864
      }
    },
    {
      "id": "9d0a32d75474e74d76d05918",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1227.7681894270909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.7813444281908,
        1237.7550344259912
      ],
      "voteCount": 3853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.963332600305467
      }
    },
    {
      "id": "96dcf847dbf06902e625fff6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1273.8861950104153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.745871331716,
        1280.0265186891147
      ],
      "voteCount": 14358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.814910594924537
      }
    },
    {
      "id": "eb5ad041b482544fb628e30f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1175.7763535439612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.8788614513498,
        1183.6738456365729
      ],
      "voteCount": 17124,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.23611868930317
      }
    },
    {
      "id": "dbda58e534b8908ce776dbcd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1262.056192155024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.1477052710345,
        1275.9646790390138
      ],
      "voteCount": 1764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.35743357705869
      }
    },
    {
      "id": "e5bb0dfbe2c68deba3b9ca0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1294.9711792464595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.2208258402234,
        1329.721532652696
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 314.35637298856096
      }
    },
    {
      "id": "69fe8242cfc41d9542aef9c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1236.3965941778602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.505181188173,
        1260.2880071675472
      ],
      "voteCount": 609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.58928372962308
      }
    },
    {
      "id": "0c4724757c7765f176b86b9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1276.344287145685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.0847083406488,
        1285.6038659507212
      ],
      "voteCount": 4272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.319593583768956
      }
    },
    {
      "id": "7580d676844abc1ee6b150b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1270.6562354987686,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.090097748296,
        1278.2223732492416
      ],
      "voteCount": 7233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.902265813898484
      }
    },
    {
      "id": "b3d06bb7bc5793318a827cd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1268.2011625637215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.1714615675737,
        1279.230863559869
      ],
      "voteCount": 3115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.66877734288402
      }
    },
    {
      "id": "8ef78740c2cae88264dede68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1221.087996271726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.861067685222,
        1230.31492485823
      ],
      "voteCount": 4344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.162468768847134
      }
    },
    {
      "id": "26c47a5dfd8bdad0d215372f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1299.3442707518157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.787701967025,
        1313.9008395366066
      ],
      "voteCount": 1742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.1596944485942
      }
    },
    {
      "id": "db52837cb48caee02cd7c124",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1286.170983766679,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.8974211547065,
        1295.4445463786515
      ],
      "voteCount": 4768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.387058545283605
      }
    },
    {
      "id": "d80272ef51c16c8d0a489221",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1246.2880712165738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.03873656852,
        1256.5374058646275
      ],
      "voteCount": 3239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.3460853366157
      }
    },
    {
      "id": "35174216aacc3210398a9b53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1288.997121653486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.6758008404586,
        1305.3184424665133
      ],
      "voteCount": 1358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.3448831591596
      }
    },
    {
      "id": "b597b87a4e3c9cef5f37bd93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1290.354707265396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.5939561057135,
        1298.1154584250785
      ],
      "voteCount": 7302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.678746375739996
      }
    },
    {
      "id": "ceef3b87096d35ec22d5e091",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1253.674651360885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.874290885727,
        1261.475011836043
      ],
      "voteCount": 7297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.839197133815093
      }
    },
    {
      "id": "3ce435f8179e20a006db9332",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1247.8129765928868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.13512614537,
        1254.4908270404037
      ],
      "voteCount": 11265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.608529124189408
      }
    },
    {
      "id": "a149dac5bb2afb0f269b529c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1204.658657679956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.1126063664049,
        1227.2047089935072
      ],
      "voteCount": 670,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.325882837769
      }
    },
    {
      "id": "ca60f8d994e56f02f6fa54a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1209.8185389162934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.9230431198957,
        1240.714034712691
      ],
      "voteCount": 385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.48155481014584
      }
    },
    {
      "id": "5228b3a6fc18470329e7fc91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1288.613578113827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.2131658554104,
        1298.0139903722438
      ],
      "voteCount": 4165,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.003695927222118
      }
    },
    {
      "id": "7ea689c6114f196dab7d549b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1231.8433236699693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.2151901762586,
        1241.47145716368
      ],
      "voteCount": 3854,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.131705922065116
      }
    },
    {
      "id": "1a2524c46fba800b162acea0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1232.5465402611046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.4708438465345,
        1241.6222366756747
      ],
      "voteCount": 5170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.441923304167727
      }
    },
    {
      "id": "0ba11529a74e529d8df98a9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1266.683825601513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.8063683776627,
        1271.5612828253636
      ],
      "voteCount": 27124,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.19285278872075
      }
    },
    {
      "id": "752c20a995285b99fda21b77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1263.6263251774412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.818272854272,
        1273.43437750061
      ],
      "voteCount": 3891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.042020457384258
      }
    },
    {
      "id": "9720c487905701e84b834d4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-32b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1240.2889721811546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.7436170827082,
        1276.834327279601
      ],
      "voteCount": 256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 347.67077863149507
      }
    },
    {
      "id": "d6bf3a0bd9ae80752aa9eb62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1233.8348475472785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.3747794681922,
        1257.2949156263644
      ],
      "voteCount": 618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.2723400054321
      }
    },
    {
      "id": "e5c7be14553a130d7396dfb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1255.1816795868149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.6628497664155,
        1269.7005094072142
      ],
      "voteCount": 1567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.87405415311111
      }
    },
    {
      "id": "564dc89833ad990cf7d5a99d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1189.1797669295008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.1169967405194,
        1204.2425371184825
      ],
      "voteCount": 1528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.062730164857854
      }
    },
    {
      "id": "619f19f4915a2ecf4345f6b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1232.186762337885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.4682096702734,
        1240.9053150054965
      ],
      "voteCount": 5497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.78757658638174
      }
    },
    {
      "id": "d6d3785823a222e182afa485",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1105.2739041668715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1093.52521546333,
        1117.022592870413
      ],
      "voteCount": 6336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.932100979226654
      }
    },
    {
      "id": "3875bff442c4f6151d027bbe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1228.0171825107077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.2753230241474,
        1251.759041997268
      ],
      "voteCount": 600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.73485209395452
      }
    },
    {
      "id": "0a07adc0794517f0874ce25b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1218.0727551074092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.7478625605709,
        1255.397647654248
      ],
      "voteCount": 240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 362.66107972525765
      }
    },
    {
      "id": "f9e66c84c5917671964acb2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1230.6501914798168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.3046465300572,
        1244.9957364295765
      ],
      "voteCount": 1620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.57200727935622
      }
    },
    {
      "id": "79ac7eddfaa51f92ecf95a8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1229.333092795254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.0022436901586,
        1240.6639419003495
      ],
      "voteCount": 2576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.421714883630216
      }
    },
    {
      "id": "0d53431e4167a3e3f3b0665c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1228.150318015759,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.214341550413,
        1246.086294481105
      ],
      "voteCount": 1096,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.74403235365492
      }
    },
    {
      "id": "e0f6ab911093028963969b17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1180.8136438783536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.0935750060662,
        1194.5337127506411
      ],
      "voteCount": 1784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.00229278685831
      }
    },
    {
      "id": "9b27df2652fefad40c430ae1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1265.9230840783289,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.576481332675,
        1291.269686823983
      ],
      "voteCount": 551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.2412228617642
      }
    },
    {
      "id": "af6fa91ab64fed2cccb61142",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1249.844722797815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.4561674883025,
        1264.2332781073274
      ],
      "voteCount": 1689,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.89372463909118
      }
    },
    {
      "id": "9657adf4b83a6f6b3f074975",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1214.295737176591,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.2669352188686,
        1230.324539134314
      ],
      "voteCount": 1146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.88149065033288
      }
    },
    {
      "id": "c3476fa689d2ec02edf705e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1258.9063181287993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.6593747209322,
        1286.1532615366664
      ],
      "voteCount": 470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.25885287958374
      }
    },
    {
      "id": "6c7dbee618a3f6cddd2db98e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1250.943551288403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.0144562927258,
        1262.87264628408
      ],
      "voteCount": 2471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.044079881657204
      }
    },
    {
      "id": "17e834dc65ac1eb64a13f490",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1212.4135606718155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.1714744185933,
        1223.6556469250372
      ],
      "voteCount": 2746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.90013227371903
      }
    },
    {
      "id": "7a30c1aa9be2a6ade61c799f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1203.4009405558404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.8478434327617,
        1212.9540376789193
      ],
      "voteCount": 4006,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.757033174830955
      }
    },
    {
      "id": "efc10bbf2e29137d08986271",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1153.978506381236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.148682742013,
        1189.808330020459
      ],
      "voteCount": 231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 334.1897757961243
      }
    },
    {
      "id": "da2a1335d8b391957b845f68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1247.3546231728706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.4973332602735,
        1262.2119130854676
      ],
      "voteCount": 1483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.46230113357657
      }
    },
    {
      "id": "a127bbb453157aaae314eaae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1199.6379720555888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.548391037128,
        1214.727553074049
      ],
      "voteCount": 1307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.273173536593546
      }
    },
    {
      "id": "99f02dbe4ae1d46c1e364f38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1199.3687976580582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.9152594361453,
        1213.8223358799708
      ],
      "voteCount": 1746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.38162346213676
      }
    },
    {
      "id": "ed05be737b9814ca1a2912da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1222.6540036792549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.6876088202052,
        1229.6203985383045
      ],
      "voteCount": 9818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.63339257231031
      }
    },
    {
      "id": "968643c5c84d2ac3a503f312",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "c4ai-aya-expanse-8b",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1228.477899787964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.7206002344874,
        1243.2351993414402
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.69145506333615
      }
    },
    {
      "id": "2d71383b8e3c832fcfb71669",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1165.6264733758608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.5355679307609,
        1204.717378820961
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 397.7912974846432
      }
    },
    {
      "id": "1e17d0c154786958e2a5c92a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1033.851795417518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1006.6786235469608,
        1061.024967288075
      ],
      "voteCount": 551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.21376668913916
      }
    },
    {
      "id": "9c307a9ac55179bbcbbbe8ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 951.0501259540699,
      "unit": "Arena rating",
      "confidenceInterval": [
        926.336102041192,
        975.7641498669477
      ],
      "voteCount": 771,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.99766377189334
      }
    },
    {
      "id": "20d56c43c2166df0dcf2bdd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1013.9522812200057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1000.2794562125644,
        1027.6251062274473
      ],
      "voteCount": 4055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.66540353811125
      }
    },
    {
      "id": "f609697dcd8dbf12dfa950c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 766.278239937251,
      "unit": "Arena rating",
      "confidenceInterval": [
        746.703696196997,
        785.8527836775049
      ],
      "voteCount": 3347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.74407654066246
      }
    },
    {
      "id": "ae573e88e0076c2a245f7fef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 996.5801397175845,
      "unit": "Arena rating",
      "confidenceInterval": [
        972.8961748196872,
        1020.2641046154819
      ],
      "voteCount": 732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.02009795421338
      }
    },
    {
      "id": "6041eec9da5f61e09164775c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 998.7017918671363,
      "unit": "Arena rating",
      "confidenceInterval": [
        977.0486072955055,
        1020.3549764387672
      ],
      "voteCount": 848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.05269507701956
      }
    },
    {
      "id": "ee783db80abb7618fc7a8ed8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 953.1908100164758,
      "unit": "Arena rating",
      "confidenceInterval": [
        915.0708886104456,
        991.310731422506
      ],
      "voteCount": 300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 378.27514905895777
      }
    },
    {
      "id": "cbfb0fd01bce0b0dcf5bf6c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 912.1577547307957,
      "unit": "Arena rating",
      "confidenceInterval": [
        887.4136446214625,
        936.9018648401288
      ],
      "voteCount": 774,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.38501847383318
      }
    },
    {
      "id": "730198dc1caeb29057bb89b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 994.6567384957011,
      "unit": "Arena rating",
      "confidenceInterval": [
        947.1677095196477,
        1042.1457674717547
      ],
      "voteCount": 195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 587.0706880780623
      }
    },
    {
      "id": "67547b93d772fe70ceac722d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 955.9368869200778,
      "unit": "Arena rating",
      "confidenceInterval": [
        930.4946082761161,
        981.3791655640393
      ],
      "voteCount": 819,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.50617768174388
      }
    },
    {
      "id": "6c92ba218a7b455141cebd74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 972.2374005858788,
      "unit": "Arena rating",
      "confidenceInterval": [
        944.4738330724452,
        1000.0009680993124
      ],
      "voteCount": 466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.657020432072
      }
    },
    {
      "id": "3b2429bb992b3c6eeaf96fb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 944.3660661876481,
      "unit": "Arena rating",
      "confidenceInterval": [
        891.6548604561875,
        997.0772719191087
      ],
      "voteCount": 193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 723.2854338296175
      }
    },
    {
      "id": "abb9ae5785c356f3a14e4c60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 996.0923916542986,
      "unit": "Arena rating",
      "confidenceInterval": [
        975.9978512980667,
        1016.1869320105304
      ],
      "voteCount": 1162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.11385673405884
      }
    },
    {
      "id": "7cde7ee21ce9e885db827784",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 980.2930177049537,
      "unit": "Arena rating",
      "confidenceInterval": [
        959.7960034582121,
        1000.7900319516953
      ],
      "voteCount": 1056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.36667881688041
      }
    },
    {
      "id": "f798cbaf5a2ca8c6c4db2e87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 975.1069610974135,
      "unit": "Arena rating",
      "confidenceInterval": [
        957.0326182807455,
        993.1813039140816
      ],
      "voteCount": 1277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.0410959749423
      }
    },
    {
      "id": "48a7685eada8e900b2b4f3ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 976.0724525856733,
      "unit": "Arena rating",
      "confidenceInterval": [
        950.572684796514,
        1001.5722203748328
      ],
      "voteCount": 525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.268548135461
      }
    },
    {
      "id": "b9a104c9940379e04efa0827",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 922.7008991809416,
      "unit": "Arena rating",
      "confidenceInterval": [
        893.0408608870985,
        952.3609374747848
      ],
      "voteCount": 492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 229.00619599334522
      }
    },
    {
      "id": "5d6073e94db493ac0ee2fd84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm-6b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 994.6039195380874,
      "unit": "Arena rating",
      "confidenceInterval": [
        982.0276689969633,
        1007.1801700792116
      ],
      "voteCount": 4914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.17239961576587
      }
    },
    {
      "id": "8db6eddbe530f70e11fc88ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1028.959100419731,
      "unit": "Arena rating",
      "confidenceInterval": [
        994.1529369324332,
        1063.7652639070286
      ],
      "voteCount": 293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 315.36691482367456
      }
    },
    {
      "id": "ccd21737a64af1de291f390d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1003.1913948736052,
      "unit": "Arena rating",
      "confidenceInterval": [
        976.8639775421365,
        1029.5188122050738
      ],
      "voteCount": 566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.43481284021004
      }
    },
    {
      "id": "82f89b5beb8499706610fada",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1054.9916530760408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.0152291572376,
        1069.9680769948438
      ],
      "voteCount": 2059,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.38752512129466
      }
    },
    {
      "id": "58ea859a59cdf3556ebbc9b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 802.3263325235264,
      "unit": "Arena rating",
      "confidenceInterval": [
        780.404786039014,
        824.2478790080389
      ],
      "voteCount": 1894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.09679856097134
      }
    },
    {
      "id": "5758f1be3b5108b5d3311c44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1047.4589550739202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1018.2438698391991,
        1076.6740403086415
      ],
      "voteCount": 408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 222.1867381928094
      }
    },
    {
      "id": "d68c9f57b65352b3b2532e7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1026.7312177567223,
      "unit": "Arena rating",
      "confidenceInterval": [
        999.9994329213002,
        1053.4630025921442
      ],
      "voteCount": 490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.02003921993753
      }
    },
    {
      "id": "20c47e56468df0b4525a9e32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1007.4085256504352,
      "unit": "Arena rating",
      "confidenceInterval": [
        965.9202742664137,
        1048.8967770344568
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 448.0784731131757
      }
    },
    {
      "id": "4a39c25fea2fb2869e77817b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 993.3772542262709,
      "unit": "Arena rating",
      "confidenceInterval": [
        965.5086132128088,
        1021.245895239733
      ],
      "voteCount": 483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.17870038156101
      }
    },
    {
      "id": "05d47d022a66342157744537",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1041.052128466148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1010.6621954654195,
        1071.4420614668763
      ],
      "voteCount": 436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 240.41596458448595
      }
    },
    {
      "id": "10071771c062bcab7c395b75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1032.5675779859148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1007.887414288607,
        1057.2477416832228
      ],
      "voteCount": 653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.5622828610337
      }
    },
    {
      "id": "daf80b117b852c771b9f7777",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1014.5130076826323,
      "unit": "Arena rating",
      "confidenceInterval": [
        992.1026562103316,
        1036.923359154933
      ],
      "voteCount": 775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.73779430005692
      }
    },
    {
      "id": "bac96839f590e712c8700cee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 979.9505694462248,
      "unit": "Arena rating",
      "confidenceInterval": [
        957.289767400488,
        1002.6113714919616
      ],
      "voteCount": 762,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.67628636021178
      }
    },
    {
      "id": "0c901bbe518d7b46cab9d57a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 970.8098788507543,
      "unit": "Arena rating",
      "confidenceInterval": [
        935.9484039718025,
        1005.6713537297062
      ],
      "voteCount": 227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 316.37002697745845
      }
    },
    {
      "id": "a5ffc5853923de763e0cc13b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 974.2805039530516,
      "unit": "Arena rating",
      "confidenceInterval": [
        942.1882611560595,
        1006.3727467500437
      ],
      "voteCount": 369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 268.1044092397676
      }
    },
    {
      "id": "e650268246f4a9eace4d700f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm2-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1023.2688092820842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1009.6701156513889,
        1036.8675029127794
      ],
      "voteCount": 2658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.13912554920965
      }
    },
    {
      "id": "1b6bd3dfbd2f053e8da88a18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1167.5687625301216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.1206940661752,
        1211.0168309940682
      ],
      "voteCount": 189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 491.41087835653786
      }
    },
    {
      "id": "489d10c3d8af6966d540267c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1088.5545150790226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.4661403059986,
        1114.6428898520464
      ],
      "voteCount": 535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.1731339748612
      }
    },
    {
      "id": "8d1b98c9e6ded5070a3c790c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1039.2158607185195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1016.0129177855183,
        1062.4188036515206
      ],
      "voteCount": 816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.14898659120064
      }
    },
    {
      "id": "0aa58fc71dcb20c4941edd6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1085.3533991188162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.5985775985123,
        1098.10822063912
      ],
      "voteCount": 3600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.3499195509815
      }
    },
    {
      "id": "768ffb9e522d63e5ce217ef9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 860.2379557660955,
      "unit": "Arena rating",
      "confidenceInterval": [
        841.9110202505103,
        878.5648912816807
      ],
      "voteCount": 3275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.43463904468662
      }
    },
    {
      "id": "5736d9f8099a1afd0c729663",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1081.9986470197014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1060.7210003575183,
        1103.2762936818842
      ],
      "voteCount": 835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.85581171449236
      }
    },
    {
      "id": "7487add26fd9f139e83665d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1058.7285848152528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1038.7744360858376,
        1078.6827335446683
      ],
      "voteCount": 999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.65021990361612
      }
    },
    {
      "id": "48b2a38438874d2ec6fa678d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1045.9375949539967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1014.316910669203,
        1077.5582792387906
      ],
      "voteCount": 378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 260.28332498379774
      }
    },
    {
      "id": "fc5c6d743562e614cdd63c8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1016.0854447719923,
      "unit": "Arena rating",
      "confidenceInterval": [
        992.4487711473707,
        1039.7221183966137
      ],
      "voteCount": 754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.43754498347764
      }
    },
    {
      "id": "0ba6ed58153180542a8d370d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1093.186594826438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1052.4291439493281,
        1133.944045703548
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 432.43202115072495
      }
    },
    {
      "id": "84ab3df6d4f358ced4638a04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1049.3014120026369,
      "unit": "Arena rating",
      "confidenceInterval": [
        1026.0870599108516,
        1072.5157640944221
      ],
      "voteCount": 888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.28684627263428
      }
    },
    {
      "id": "52562e1772b988cbd681c5dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1027.952569874481,
      "unit": "Arena rating",
      "confidenceInterval": [
        1001.385188998189,
        1054.5199507507732
      ],
      "voteCount": 466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.7389803122838
      }
    },
    {
      "id": "352b257b5ffe2fdc06269ecb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1037.7039884067601,
      "unit": "Arena rating",
      "confidenceInterval": [
        995.8933865506403,
        1079.5145902628801
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 455.06837614755483
      }
    },
    {
      "id": "e70c0fbca9cd3b8de25f9ac5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1085.6259647374059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.2681608483363,
        1105.9837686264752
      ],
      "voteCount": 1082,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.8861439183471
      }
    },
    {
      "id": "9e6595fcaf88e7976d5a5fee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1038.9112950140664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1018.7135124815902,
        1059.1090775465427
      ],
      "voteCount": 1108,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.19674406804819
      }
    },
    {
      "id": "c840416d3df0cb72903fd63b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1033.8247581982623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1016.149345673194,
        1051.5001707233307
      ],
      "voteCount": 1321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.32853233993266
      }
    },
    {
      "id": "36dc9db081c9cb5fa7270de7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1040.4786220829562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1000.6193055512294,
        1080.3379386146828
      ],
      "voteCount": 205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 413.5837942131835
      }
    },
    {
      "id": "a19837ff576b435bb7180b45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1041.3504214621394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1018.0071904149027,
        1064.6936525093763
      ],
      "voteCount": 576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.84882909306342
      }
    },
    {
      "id": "90c066975adc4cded7d848ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1033.5655079056894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1007.9222864419514,
        1059.2087293694276
      ],
      "voteCount": 637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.17840844627287
      }
    },
    {
      "id": "40ac19c7fd41f55d8eaadd9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatglm3-6b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1055.1127664266296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1043.4456906256573,
        1066.7798422276016
      ],
      "voteCount": 4658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.43462629674487
      }
    },
    {
      "id": "fa492750623e4b63cbafbe59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1465.992813812335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.474854193559,
        1475.5107734311114
      ],
      "voteCount": 4122,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.58259180513216
      }
    },
    {
      "id": "e76fe61a4de8f34fef5e3e39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1469.144748334747,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.0055172902407,
        1474.2839793792532
      ],
      "voteCount": 15865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.875433777016231
      }
    },
    {
      "id": "a17360ccb78b765a12fe1cf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1422.9845398762989,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.0712452791668,
        1428.897834473431
      ],
      "voteCount": 11563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.102545315363757
      }
    },
    {
      "id": "035c0634891100883d12fdf1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1448.4288602077936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.7463850967542,
        1452.1113353188327
      ],
      "voteCount": 41169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.5300711465059798
      }
    },
    {
      "id": "24b2fbbcce82e321904042a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1444.618451170547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.6485623716317,
        1448.5883399694624
      ],
      "voteCount": 58847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.102612525963704
      }
    },
    {
      "id": "4341d55fddf87045ccf32a55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1429.5798955249306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.3918698978546,
        1438.7679211520067
      ],
      "voteCount": 4317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.97597810212963
      }
    },
    {
      "id": "8631fe0a995b3d3703c41d16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1467.078216565121,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.0804993101444,
        1485.0759338200974
      ],
      "voteCount": 1287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.32156675612782
      }
    },
    {
      "id": "b049c9435f48d3b66b5036d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1428.017200708089,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.934412029336,
        1443.0999893868416
      ],
      "voteCount": 1694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.21982375612378
      }
    },
    {
      "id": "20cf53de31ee42696c906de2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1455.201320718782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.4480072723518,
        1459.9546341652122
      ],
      "voteCount": 19984,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.8816167957596095
      }
    },
    {
      "id": "07366d96ba8a1b4f5d452ccd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1455.8978001536452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.1483058678864,
        1459.6472944394043
      ],
      "voteCount": 38336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.6597313820478155
      }
    },
    {
      "id": "85038b70b5088dc06376429c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1451.7150738108805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.065122425609,
        1457.365025196152
      ],
      "voteCount": 13582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.30985106073921
      }
    },
    {
      "id": "0aff9cdd2e34f6f758bde1b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1426.1613926318273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.844197018014,
        1431.4785882456408
      ],
      "voteCount": 14836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.359852211157515
      }
    },
    {
      "id": "420c4ec458359f726d4b0d2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1458.2500924883932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.8168539187259,
        1466.6833310580605
      ],
      "voteCount": 5273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.513673084245816
      }
    },
    {
      "id": "7124d80a6df5ff5b5cb98152",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1460.4312311808333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.8843166219879,
        1465.9781457396787
      ],
      "voteCount": 13675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.009525172411367
      }
    },
    {
      "id": "3cb5de62b76adf9b14cc77de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1410.1006010046294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.512469518413,
        1418.6887324908457
      ],
      "voteCount": 4764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.199998195272784
      }
    },
    {
      "id": "f9bc4fd049f3bc6eeb269307",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1478.5724860750386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.3151879000156,
        1487.8297842500617
      ],
      "voteCount": 4602,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.308600326425193
      }
    },
    {
      "id": "ea564139eeb6f0d0c340d9fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1465.2450040878682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.9948721342712,
        1469.4951360414655
      ],
      "voteCount": 27072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.702281728409546
      }
    },
    {
      "id": "876a34f18652bba9ab07ae68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1431.1039826608633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.2270116398754,
        1435.9809536818514
      ],
      "voteCount": 18566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.1916181976041464
      }
    },
    {
      "id": "e8211154c3a0f8e2975c02f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1427.6799924520155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.2549752596956,
        1432.1050096443355
      ],
      "voteCount": 22789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.097224275018892
      }
    },
    {
      "id": "9bb469e3c345920fc44dc88c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1413.2344638584648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.3856112824283,
        1432.083316434501
      ],
      "voteCount": 1163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.48550095584625
      }
    },
    {
      "id": "22c5e093b29e7d4bd5962a17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1407.0317930708218,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.825040765006,
        1424.2385453766376
      ],
      "voteCount": 1305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.07288786196094
      }
    },
    {
      "id": "db1a20f36b47330a1c952a60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1440.5019104235882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.509994204437,
        1445.4938266427396
      ],
      "voteCount": 17318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.4869177836255405
      }
    },
    {
      "id": "2735598731be9a16b23739e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1403.926155498186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.1420945960929,
        1411.710216400279
      ],
      "voteCount": 5725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.773071365774705
      }
    },
    {
      "id": "6afc5757320dbd5d2ea9bf7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1471.3227803388215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.8394735278328,
        1476.8060871498103
      ],
      "voteCount": 14599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.826884261121161
      }
    },
    {
      "id": "87fb77b470ab0d268d8bed1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1443.175501288646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.3572175101913,
        1445.993785067101
      ],
      "voteCount": 82471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.0676320706899416
      }
    },
    {
      "id": "5bfb17946141e5ab1a0231ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1448.7507893397335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.3414768749867,
        1456.1601018044805
      ],
      "voteCount": 6394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.290901910627651
      }
    },
    {
      "id": "8c21f7987f3999b939b398a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "chatgpt-4o-latest-20250326",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1446.735225276336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.2478859951307,
        1462.2225645575413
      ],
      "voteCount": 1678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.439216247494116
      }
    },
    {
      "id": "d36f21d53ce666d09fecad5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1315.3051366492489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.5630237530524,
        1325.0472495454453
      ],
      "voteCount": 4171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.706437869633803
      }
    },
    {
      "id": "77b22478000ac351d2e0192f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1384.4586420545038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.4713810192106,
        1390.4459030897974
      ],
      "voteCount": 11248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.331687876395122
      }
    },
    {
      "id": "7ef8e8d700186df05468b7b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1303.892015304714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.5141359990919,
        1310.2698946103365
      ],
      "voteCount": 9924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.58903565956589
      }
    },
    {
      "id": "c234a648b58df09b54691abd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1336.0220472987921,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.032950629933,
        1340.0111439676512
      ],
      "voteCount": 37376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.14240864636593
      }
    },
    {
      "id": "055689ac170c4296be6b85b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1269.419191833344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.7176883608681,
        1274.12069530582
      ],
      "voteCount": 49344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.754099141354345
      }
    },
    {
      "id": "c515b56c1c60242cc94d6b64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1311.016838061047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.4564961706528,
        1321.5771799514412
      ],
      "voteCount": 3505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.030851571608128
      }
    },
    {
      "id": "52eeff9e58a08f9cedce5beb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1345.8271947273652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.0949272602536,
        1368.5594621944765
      ],
      "voteCount": 778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.52076628090006
      }
    },
    {
      "id": "d7c180aae51dd521b399d733",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1313.6249605809535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.2374614542164,
        1329.0124597076901
      ],
      "voteCount": 1691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.63677405568169
      }
    },
    {
      "id": "b84541dfbf900aec0a14863d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1356.6195325304438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.9477341452293,
        1362.2913309156586
      ],
      "voteCount": 13436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.374239689678921
      }
    },
    {
      "id": "ec0fd818142a8457247d572a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1343.8829125236073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.2746182623164,
        1348.4912067848982
      ],
      "voteCount": 23779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.528206077400983
      }
    },
    {
      "id": "beb4913351b6f27c2f4f3f3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1316.8096427149176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.930155194832,
        1323.6891302350032
      ],
      "voteCount": 9162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.320149908690862
      }
    },
    {
      "id": "8e2638a98b36e4c3ddce0bab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1303.0889398512259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.318184436187,
        1308.8596952662651
      ],
      "voteCount": 12478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.669003005005491
      }
    },
    {
      "id": "ff4201b80495ef78095b4b60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1351.1572788466883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.378381540655,
        1360.9361761527211
      ],
      "voteCount": 4272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.893363949860174
      }
    },
    {
      "id": "dafd2ed256464396658301de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1341.5275964411558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.3222218688811,
        1347.7329710134309
      ],
      "voteCount": 11945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.023971459695828
      }
    },
    {
      "id": "c43f06b73cdad67bbdc1a6d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1297.9544880168287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.1084564427124,
        1305.8005195909448
      ],
      "voteCount": 5786,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.025217068682213
      }
    },
    {
      "id": "54d963500427c9257b01f9f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1344.8935059030805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.9438681670986,
        1355.8431436390624
      ],
      "voteCount": 3666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.21068639428407
      }
    },
    {
      "id": "e10dbb75180c04faa62cd286",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1364.1883039864226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.2471911745768,
        1369.1294167982683
      ],
      "voteCount": 20005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.355553178876854
      }
    },
    {
      "id": "e7b8362617b67cffdd41d0f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1312.303423328383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.1926057952655,
        1317.4142408615
      ],
      "voteCount": 16961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.799618862528482
      }
    },
    {
      "id": "19b1d191a5e5919e98267389",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1313.5416527773243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.8992892138383,
        1318.18401634081
      ],
      "voteCount": 22007,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.610248726208559
      }
    },
    {
      "id": "25576c4ee07bb28142c2e049",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1241.7350191739347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.101193117696,
        1258.368845230173
      ],
      "voteCount": 1448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.02580638862702
      }
    },
    {
      "id": "cdde2f36ddc73bc8dc97a2ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1267.5081511715352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.7701914058293,
        1286.2461109372407
      ],
      "voteCount": 1186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.40046856411784
      }
    },
    {
      "id": "6a288beb6cb2460473234f5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1342.7731444359829,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.676810895045,
        1348.8694779769203
      ],
      "voteCount": 10987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.674783559347427
      }
    },
    {
      "id": "384b823c41631a06244a09e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1285.4820822281818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.0070763667038,
        1292.9570880896595
      ],
      "voteCount": 6365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.545440999685669
      }
    },
    {
      "id": "388db654c739749677b54142",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1325.8639669713189,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.6519983201815,
        1332.0759356224557
      ],
      "voteCount": 11532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.045286523659225
      }
    },
    {
      "id": "e893468e6bd33976f69f7182",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1323.1833623066207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.9585846992404,
        1326.408139914001
      ],
      "voteCount": 69993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.7070941281577343
      }
    },
    {
      "id": "e79ffb1de33cd4f3ac2fc0a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1317.3616381203667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.6683406016193,
        1325.0549356391139
      ],
      "voteCount": 6213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.407382839332097
      }
    },
    {
      "id": "d3a1540e8ac89be7b988f1dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-haiku-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1321.6404155413043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.4355924244624,
        1342.845238658146
      ],
      "voteCount": 883,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.05046036008324
      }
    },
    {
      "id": "1989390051faebe1d1275782",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1343.9385785801621,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.6318760147442,
        1353.24528114558
      ],
      "voteCount": 8100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.5473489848595
      }
    },
    {
      "id": "6a5288969ab6ebf47afeb224",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1397.5768288520176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.5134755715549,
        1404.6401821324798
      ],
      "voteCount": 13607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.987503418195006
      }
    },
    {
      "id": "2a8fae75cce9fc96169299e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1303.2539117931508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.6802174510465,
        1310.8276061352549
      ],
      "voteCount": 12430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.932047606137465
      }
    },
    {
      "id": "77877e73114263752a3d6c67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1347.8199281943366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.3375353569077,
        1352.3023210317656
      ],
      "voteCount": 44433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.230264461198497
      }
    },
    {
      "id": "dbd0944b2f68da0f90ac4e0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1296.109461784934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.8730097557668,
        1301.345913814101
      ],
      "voteCount": 55109,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.138025196587788
      }
    },
    {
      "id": "bdcdecaeff8a471878f61eef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1338.824575582912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.6282213110285,
        1350.020929854796
      ],
      "voteCount": 4314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.633006061711605
      }
    },
    {
      "id": "449b2f2025e420d159da6fd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1365.5851182160839,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.2071040053283,
        1388.9631324268394
      ],
      "voteCount": 936,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.27187481331342
      }
    },
    {
      "id": "abd96d8388488f2d151bbe43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1333.5773365091868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.9903411064433,
        1348.1643319119303
      ],
      "voteCount": 2499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.39052865369829
      }
    },
    {
      "id": "a3cbc8dbe68e103ef8e2480c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1366.2305829307625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.4097552531953,
        1373.0514106083297
      ],
      "voteCount": 14269,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.110943362568278
      }
    },
    {
      "id": "16c4c041a8d542121034a0da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1359.4737454275705,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.8565095774147,
        1365.0909812777263
      ],
      "voteCount": 23249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.213894790774638
      }
    },
    {
      "id": "023edf1c7605fcd649420c08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1321.9534298870283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.675889832104,
        1330.2309699419525
      ],
      "voteCount": 9702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.836367005098676
      }
    },
    {
      "id": "3f04cfeb16c2b557f5e1d9aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1310.2565435803729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.0313633888911,
        1317.4817237718546
      ],
      "voteCount": 13185,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.589428192789427
      }
    },
    {
      "id": "1d5cc163ca885922e2a9a5ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1353.815508188663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.8681856550143,
        1364.7628307223115
      ],
      "voteCount": 4818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.197489352255033
      }
    },
    {
      "id": "e3d533eaa9d5fbf70f15a296",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1356.1040278151388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.8578756626803,
        1363.3501799675976
      ],
      "voteCount": 13749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.668432610477417
      }
    },
    {
      "id": "495c48ca1da9669350f01c82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1338.5209714648843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.8462734719983,
        1346.1956694577702
      ],
      "voteCount": 10038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.332974276518872
      }
    },
    {
      "id": "41f4055b5b6a1b1cde8706d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1348.842223088305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.3291522658446,
        1360.3552939107653
      ],
      "voteCount": 4460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.50532882167884
      }
    },
    {
      "id": "6138da150653d50ffb4f3f4a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1372.7464785645984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.8363383304777,
        1378.6566187987191
      ],
      "voteCount": 22198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.092836658512294
      }
    },
    {
      "id": "b824f9ecb70da6d18f41960a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1329.5901304664428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.5156895571486,
        1335.664571375737
      ],
      "voteCount": 21916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.605421815725778
      }
    },
    {
      "id": "818adde03948b23e59019e93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1335.7088967018935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.590307609879,
        1340.8274857939086
      ],
      "voteCount": 32074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.820313718255737
      }
    },
    {
      "id": "2b7627f4eb51062bd393dddf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1285.6129772716945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.9693270427929,
        1301.256627500596
      ],
      "voteCount": 2127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.70595232360009
      }
    },
    {
      "id": "a0080a3222cab359502ff501",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1290.1891138698923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.0059836642104,
        1309.3722440755741
      ],
      "voteCount": 1715,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.79498353744017
      }
    },
    {
      "id": "5f7bb2b4bce05bd3f9989cf0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1351.4870920812186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.7381603201547,
        1359.236023842283
      ],
      "voteCount": 10574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.631026190924727
      }
    },
    {
      "id": "aa50e343f9e55f2fea164b5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1341.4502929818968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.0005050707382,
        1348.9000808930557
      ],
      "voteCount": 11359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.447464495068564
      }
    },
    {
      "id": "3e83512ca7b04ac4c116b650",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1347.1057158596752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.8951644434446,
        1354.3162672759058
      ],
      "voteCount": 14950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.534455047655749
      }
    },
    {
      "id": "a315178435e2dccc8f404cfa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1342.0738492479109,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.6351160846862,
        1345.5125824111353
      ],
      "voteCount": 82419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.0782279128333596
      }
    },
    {
      "id": "ee09a4407b73df93f9b07193",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1342.860924132874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.75566468651,
        1350.9661835792376
      ],
      "voteCount": 9966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.10163606048953
      }
    },
    {
      "id": "2bbf18c9ac9c402efa05e3b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20240620",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1347.8272855378607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.508425145163,
        1370.1461459305585
      ],
      "voteCount": 1123,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.672489665977
      }
    },
    {
      "id": "c8ead978bf32bfd5cb00b3f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1365.4531612958278,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.0785576698831,
        1373.8277649217725
      ],
      "voteCount": 6595,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.257122922643273
      }
    },
    {
      "id": "365333b49497bf9414752d0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1434.0913100592363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.580323497764,
        1439.6022966207086
      ],
      "voteCount": 14964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.906103982455073
      }
    },
    {
      "id": "15eeeccfebb9cc3b5fce8b18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1368.6243915212399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4663938089504,
        1374.7823892335293
      ],
      "voteCount": 11757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.871493511860722
      }
    },
    {
      "id": "dbdc664efd13d4173698cded",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1382.1722626157957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.3308722336944,
        1386.0136529978968
      ],
      "voteCount": 46459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.8413219447276292
      }
    },
    {
      "id": "257b7cad4fa98976eff88769",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1344.7460863015542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.4531096072417,
        1349.0390629958667
      ],
      "voteCount": 61963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.797565132972057
      }
    },
    {
      "id": "8133386929283d5e01ea6d6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1366.716117742612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.415157537173,
        1376.0170779480513
      ],
      "voteCount": 5021,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.51953353687955
      }
    },
    {
      "id": "0e55bf70c7c2a996d9fe1bd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1392.7616457721624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.447516710632,
        1414.075774833693
      ],
      "voteCount": 814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.26030652841833
      }
    },
    {
      "id": "a19f0fe0668fe3314efc97ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1378.1857036126144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.7304622201857,
        1391.6409450050432
      ],
      "voteCount": 1989,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.128845935621285
      }
    },
    {
      "id": "a4d6142291d95f47e37eacbe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1404.3620310184876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.0795526265852,
        1409.6445094103901
      ],
      "voteCount": 15821,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.264057552977639
      }
    },
    {
      "id": "56ec8994391438eba06b672d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1397.5586835685385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.2287848090332,
        1401.888582328044
      ],
      "voteCount": 27293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.880443639424422
      }
    },
    {
      "id": "d026a2a828dca3b3864c16d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1355.3041131175385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.9523136917373,
        1361.6559125433396
      ],
      "voteCount": 11318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.502613155258834
      }
    },
    {
      "id": "c8e7ff41015b0015ca0e2d43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1363.4497045318399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.8500464348683,
        1369.0493626288114
      ],
      "voteCount": 14310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.162568510187041
      }
    },
    {
      "id": "f1b0090c80fff04742242ab7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1383.0213471434258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.0755528907023,
        1391.9671413961496
      ],
      "voteCount": 5534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.832511435747485
      }
    },
    {
      "id": "3cde121efef004e17a388c46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1376.2015689031196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.4417101847066,
        1381.9614276215325
      ],
      "voteCount": 15643,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.63629522132503
      }
    },
    {
      "id": "649515405f613b2e871b9e38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1357.4194582787306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.5944447306379,
        1364.2444718268234
      ],
      "voteCount": 8624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.125812641988167
      }
    },
    {
      "id": "be2032524c86e0f3588e80f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1384.254460929079,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.3524213851658,
        1394.1565004729919
      ],
      "voteCount": 4554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.52425828464318
      }
    },
    {
      "id": "9033db9d9c84ecc1e310dfd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1407.0749752660959,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.4877722726142,
        1411.6621782595773
      ],
      "voteCount": 25288,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.477718826517028
      }
    },
    {
      "id": "8dd92c1a2f85591c9b2486bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1375.2828601810168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.3992826568297,
        1380.1664377052039
      ],
      "voteCount": 21872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.208404293251256
      }
    },
    {
      "id": "f1e2f73b90a593cf5918982c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1371.1218304883935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.731288684533,
        1375.512372292254
      ],
      "voteCount": 31267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.018108544493905
      }
    },
    {
      "id": "1da58b84efdd324dda1b2679",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1308.2659253386373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.2448408989349,
        1322.28700977834
      ],
      "voteCount": 1965,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.17608128615775
      }
    },
    {
      "id": "37bdf17bf2d23c241b02b707",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1303.503363337522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.9901315448783,
        1322.0165951301656
      ],
      "voteCount": 1256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.22124833456436
      }
    },
    {
      "id": "ca9e4f9e85102f119ff0e679",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1393.0405748346104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.3747993455315,
        1398.7063503236895
      ],
      "voteCount": 13789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.356463882866132
      }
    },
    {
      "id": "f7bfafcd856d82d711bd57ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1350.1276488285334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.4958233616258,
        1356.759474295441
      ],
      "voteCount": 10019,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.44906429468794
      }
    },
    {
      "id": "7e7e36063df3fc6fbc8e5c22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1387.6467008509806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.9348491113642,
        1393.3585525905967
      ],
      "voteCount": 16029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.492932455660613
      }
    },
    {
      "id": "4eb0d24b836d68140db3a9c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1372.3419020212427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.1763724089137,
        1375.507431633572
      ],
      "voteCount": 88350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.608534464186189
      }
    },
    {
      "id": "b18e80c425182aa892957329",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1372.6958852450416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.781998299801,
        1379.6097721902825
      ],
      "voteCount": 9933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.443666565956667
      }
    },
    {
      "id": "6af45a374ae1107d738f9a65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-5-sonnet-20241022",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1362.7200524958196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.8564682833521,
        1382.583636708287
      ],
      "voteCount": 918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.71149482073254
      }
    },
    {
      "id": "f114bcab1119d6bfd913adf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1394.5360001032525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.0524350772478,
        1408.0195651292572
      ],
      "voteCount": 1983,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.32746966623631
      }
    },
    {
      "id": "7a0933a3afeaf9de1e066337",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1451.1044778310727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.2329156970336,
        1458.976039965112
      ],
      "voteCount": 6191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.129677115436124
      }
    },
    {
      "id": "d5bf715b10968f5130a69b92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1392.3879100637848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.890855265619,
        1400.8849648619507
      ],
      "voteCount": 5201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.79492755566965
      }
    },
    {
      "id": "1b413108c83319bbd18317c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1401.9162847185416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.789138690853,
        1407.0434307462303
      ],
      "voteCount": 20338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.843136323011222
      }
    },
    {
      "id": "30b9834bf48a23ce2ef3c9e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1366.749010372204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.2002246342038,
        1372.2977961102047
      ],
      "voteCount": 28713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.014929901207168
      }
    },
    {
      "id": "f4e28cbbc8c1b65a705c7926",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1407.7618827685474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.9162348630398,
        1421.607530674055
      ],
      "voteCount": 1875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.90342858566617
      }
    },
    {
      "id": "0342378f2f09eb463a619b20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1372.7014107791401,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.2562327983492,
        1401.146588759931
      ],
      "voteCount": 474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.6304370621029
      }
    },
    {
      "id": "ca94e74e44fbce276e03de90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1383.7052968475075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.3428863011036,
        1403.0677073939112
      ],
      "voteCount": 999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.59389848144818
      }
    },
    {
      "id": "2587cbeac701882287576015",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1428.1137937760368,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.8928801720922,
        1435.3347073799814
      ],
      "voteCount": 7772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.573383370594167
      }
    },
    {
      "id": "3af06f70475070bf59d7ba66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1416.2182982863849,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.3773135781614,
        1422.0592829946086
      ],
      "voteCount": 13858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.881288061168696
      }
    },
    {
      "id": "60bc9da5acea09ac9b92c571",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1365.0734381955788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.6144064124878,
        1373.5324699786697
      ],
      "voteCount": 5634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.627095082177892
      }
    },
    {
      "id": "4f4f2933bfc6dad9153d9e6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1383.6958415077247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.0648275085941,
        1391.3268555068553
      ],
      "voteCount": 6588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.15892200671957
      }
    },
    {
      "id": "62a575594d679cbc2d5f4098",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1399.3441479459934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.1683086874268,
        1411.51998720456
      ],
      "voteCount": 2512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.59238601018278
      }
    },
    {
      "id": "3b6fda2a5f0aa87ee955b886",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1403.3283960313317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.3953797214676,
        1411.261412341196
      ],
      "voteCount": 6773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.382512662520465
      }
    },
    {
      "id": "e9806892ae35f4897d64d849",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1389.9487195220065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.569892524157,
        1401.327546519856
      ],
      "voteCount": 2559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.70534734082976
      }
    },
    {
      "id": "6d5a70a43892a3859fbc7b40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1411.248214667984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.989035818539,
        1424.507393517429
      ],
      "voteCount": 2278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.7653802806621
      }
    },
    {
      "id": "4a27fa93775ba383f0cceec6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1417.1664352901125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.8795082688825,
        1423.4533623113425
      ],
      "voteCount": 11710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.289177423260723
      }
    },
    {
      "id": "c97ac59ce0eba5b095075e32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1391.5353650280476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.7858274289674,
        1398.284902627128
      ],
      "voteCount": 8873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.859103514525678
      }
    },
    {
      "id": "532cad8f92edc32d88f00853",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1409.4760542581648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.1225531089035,
        1415.8295554074261
      ],
      "voteCount": 10143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.50824146186482
      }
    },
    {
      "id": "6b32df7aa3075860d2052243",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1350.1693466967163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.9716733990595,
        1370.367019994373
      ],
      "voteCount": 934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.19559539236941
      }
    },
    {
      "id": "9eda173a2a4c9874527f8082",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1330.0281515982601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.7902694934446,
        1353.2660337030754
      ],
      "voteCount": 731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.57137923965144
      }
    },
    {
      "id": "d16a986e8ad825ac115a0494",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1427.0078958877036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.1865089657274,
        1434.8292828096796
      ],
      "voteCount": 6155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.924703670832336
      }
    },
    {
      "id": "e8491272c881da6c4097878b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1384.0835912706418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.1818259007082,
        1394.9853566405752
      ],
      "voteCount": 2793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.938373604537755
      }
    },
    {
      "id": "22fc961eaaede973f21de958",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1397.174205746713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.2045119425486,
        1405.1438995508774
      ],
      "voteCount": 6369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.534348615159708
      }
    },
    {
      "id": "3f81fbdb9d9a6b2038aef173",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1386.9377277681908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.7659538728055,
        1391.1095016635759
      ],
      "voteCount": 38827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.530491734146025
      }
    },
    {
      "id": "87ccce25c6f66f9b84883e79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1375.1604165627261,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.4641490287638,
        1385.8566840966885
      ],
      "voteCount": 3002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.782992477171522
      }
    },
    {
      "id": "20a7119d1f6ec3ca6c860cea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1380.8888408353148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.1225746929877,
        1406.6551069776422
      ],
      "voteCount": 550,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.82509117129578
      }
    },
    {
      "id": "2d58e00c545c788d943fd93d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1380.9914656295343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.3152859559832,
        1393.6676453030855
      ],
      "voteCount": 2198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.82929939285744
      }
    },
    {
      "id": "fa0dacf46835093e9df5ba79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1429.4040938685496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.9956298780735,
        1436.812557859026
      ],
      "voteCount": 7146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.287629064904051
      }
    },
    {
      "id": "4a976cade3f4af5fabcf8d48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1375.6116889651712,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.5841428073159,
        1383.6392351230265
      ],
      "voteCount": 5981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.775266981738586
      }
    },
    {
      "id": "dcbf31e707de9371a1d89a6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1384.102148863625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.231882501118,
        1388.972415226132
      ],
      "voteCount": 23512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.174605937199845
      }
    },
    {
      "id": "6d9403db25649b403a997fe2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1346.2620243259323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.9726765576584,
        1351.5513720942065
      ],
      "voteCount": 31745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.282962311877852
      }
    },
    {
      "id": "d3f2e58ba9e05ed33506cfe3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1386.9357258898913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.872941144974,
        1399.9985106348086
      ],
      "voteCount": 2128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.41967316500138
      }
    },
    {
      "id": "f93009d2c31dfbb5b883e838",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1392.9800524062507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.5962016190447,
        1420.3639031934567
      ],
      "voteCount": 505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 195.20586291237922
      }
    },
    {
      "id": "264be6148f00647be4a1be47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1365.121031852918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.835526719694,
        1384.4065369861419
      ],
      "voteCount": 1042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.82017316962923
      }
    },
    {
      "id": "7215c05513b2250118da1f5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1405.1308517674997,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.2970242404058,
        1411.9646792945935
      ],
      "voteCount": 8833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.157151970101843
      }
    },
    {
      "id": "0cfe66df14c7733f426e81f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1397.5630772762477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.0012568588513,
        1403.124897693644
      ],
      "voteCount": 15276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.052629951081006
      }
    },
    {
      "id": "8938f971ff22f0e57af89dec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1369.7637491338078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.4632691565553,
        1378.06422911106
      ],
      "voteCount": 5807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.935365461061362
      }
    },
    {
      "id": "1f78b4f3ec648e7787e78a54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1370.1311562356918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.856418593692,
        1377.4058938776918
      ],
      "voteCount": 7393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.776487066537847
      }
    },
    {
      "id": "8ab3b87b5fc45b48cbd83d2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1395.828923862453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.4778318092042,
        1408.1800159157017
      ],
      "voteCount": 2502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.7113393708747
      }
    },
    {
      "id": "e5afba45aceee4d93fd07885",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1385.123617589959,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6128237944504,
        1392.6344113854675
      ],
      "voteCount": 7489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.685052234519778
      }
    },
    {
      "id": "3988e77ac652aa6ac1729ac7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1362.7015453533627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.4830845087522,
        1372.920006197973
      ],
      "voteCount": 3187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.181585670093593
      }
    },
    {
      "id": "9b3bb4bf3307f39021fe6704",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1381.4382061599918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.9930166045763,
        1394.8833957154075
      ],
      "voteCount": 2264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.05845633622873
      }
    },
    {
      "id": "adf114ed94710d5b10355104",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1405.758964053654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.7929628988181,
        1411.7249652084897
      ],
      "voteCount": 13036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.2655346421416
      }
    },
    {
      "id": "07840e900c6ce4a63a5c0779",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1377.2359350093727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.755025326975,
        1383.7168446917701
      ],
      "voteCount": 9792,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.933916585315453
      }
    },
    {
      "id": "0d12079ba13abbfa6690e692",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1383.5544209013842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6836066453172,
        1389.4252351574512
      ],
      "voteCount": 12322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.972232070682942
      }
    },
    {
      "id": "5ee097d61688300daffbc1be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1339.5028754915525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.524290108873,
        1359.481460874232
      ],
      "voteCount": 920,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.90424381040022
      }
    },
    {
      "id": "ef5a0a9e901b0797733d75a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1330.1677549823914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.4527943629714,
        1353.8827156018117
      ],
      "voteCount": 673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.40254742572665
      }
    },
    {
      "id": "fa288d9fd78059881a316f44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1409.8330198133917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.3640555698003,
        1417.3019840569832
      ],
      "voteCount": 6679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.52193801259268
      }
    },
    {
      "id": "7dd9e3c070586b5ccb77120d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1362.060169942663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.150477138964,
        1371.9698627463622
      ],
      "voteCount": 3357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.563728793516585
      }
    },
    {
      "id": "a1288d1b53ced2138ab9b3b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1396.2797293360602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.6986105840474,
        1403.860848088073
      ],
      "voteCount": 7050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.961337401954781
      }
    },
    {
      "id": "86a0efcef290d8ef0090223b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1370.9325329606538,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.0053387644025,
        1374.8597271569051
      ],
      "voteCount": 43194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.014843051807875
      }
    },
    {
      "id": "bba2a0683b2c1c6ead1497ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1372.359773025551,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.065537992469,
        1382.654008058633
      ],
      "voteCount": 3196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.586206142692674
      }
    },
    {
      "id": "f86acaf52be2c56264d5693c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-7-sonnet-20250219",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1360.2553070163171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.5588668089429,
        1385.9517472236914
      ],
      "voteCount": 560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.8896570683141
      }
    },
    {
      "id": "3ca8a2bca35f9b5f28723386",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1247.3495475621119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.4500053078277,
        1256.249089816396
      ],
      "voteCount": 16707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.61764970878376
      }
    },
    {
      "id": "6224c9ccb7633f25238d0dc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1299.8299003488064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.9369759452943,
        1306.7228247523185
      ],
      "voteCount": 20898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.368323871280348
      }
    },
    {
      "id": "57f9296e9be93e4889fcff0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1214.6417052636152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.0180512585014,
        1222.2653592687293
      ],
      "voteCount": 16718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.129695020181686
      }
    },
    {
      "id": "bf06ae6b87fe83afcf6fcfa0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1269.5535839305471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.718549248371,
        1274.3886186127236
      ],
      "voteCount": 64537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.085594423637347
      }
    },
    {
      "id": "070fdf94481b51297f33499c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1170.5122140427352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.618338116885,
        1176.406089968585
      ],
      "voteCount": 77578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.04285977040273
      }
    },
    {
      "id": "230cd6045d03fd500d9d3043",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1248.0393962817122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.1128073012237,
        1258.9659852622008
      ],
      "voteCount": 6336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.079429019354095
      }
    },
    {
      "id": "2c0f31008f22ccb3f4fb0045",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1279.682579702891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.085886640404,
        1300.2792727653782
      ],
      "voteCount": 1772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.4329852047334
      }
    },
    {
      "id": "af82e3051d8a0799fe2a05a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1246.40786034675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.5730821841569,
        1260.2426385093436
      ],
      "voteCount": 3508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.82510440488921
      }
    },
    {
      "id": "23e48b6eed719d7d45f2577e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1268.8187248791592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.108590740772,
        1275.5288590175464
      ],
      "voteCount": 20673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.721041993888853
      }
    },
    {
      "id": "a8c6dfc5da42d364d073d6a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1263.96748839983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.2368005417093,
        1269.6981762579508
      ],
      "voteCount": 33698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.54903953422502
      }
    },
    {
      "id": "6022fc3cab9f340b8039f197",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1249.3499284030795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.109816966306,
        1257.5900398398533
      ],
      "voteCount": 13237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.675430001922788
      }
    },
    {
      "id": "11e5fd554661f3abb00eb4c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1219.4378906090035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.1432692521726,
        1226.7325119658344
      ],
      "voteCount": 17134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.851899297444493
      }
    },
    {
      "id": "08d2e1752263cd244f1d81e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1286.3516858308192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.4659823766774,
        1297.237389284961
      ],
      "voteCount": 6799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.84727579354906
      }
    },
    {
      "id": "8d7db509f56361962a0663e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1272.7709195910593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.5042561258356,
        1280.0375830562832
      ],
      "voteCount": 20565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.745923197811981
      }
    },
    {
      "id": "b1430d96ddf6c9b67a9d1a1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1237.3078789653446,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.6553120320773,
        1244.960445898612
      ],
      "voteCount": 13491,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.244672246039327
      }
    },
    {
      "id": "30b949d1d9dcdd496d7bed59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1279.9313706590194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.7018621555235,
        1291.1608791625154
      ],
      "voteCount": 6385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.82655551343472
      }
    },
    {
      "id": "37fdfc418c388ec80dfd3ace",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1284.7292277052138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.7804137617322,
        1290.6780416486954
      ],
      "voteCount": 34258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.212226132302117
      }
    },
    {
      "id": "f90143546f80c9b037c0e60e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1245.4127720133326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.1368707819518,
        1251.6886732447133
      ],
      "voteCount": 29876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.253119479992323
      }
    },
    {
      "id": "66e249e2e9a8ffd9d98a0b6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1242.8442441944135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.5238858704324,
        1248.1646025183945
      ],
      "voteCount": 43031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.3686102121070665
      }
    },
    {
      "id": "147650c26aec952e4ba374df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1172.2888764735508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.0132896588618,
        1188.5644632882395
      ],
      "voteCount": 2063,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.95680483036071
      }
    },
    {
      "id": "22b93c465069fd69482aa9f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1208.6449012312453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.1797154416358,
        1227.1100870208547
      ],
      "voteCount": 2364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.75875081831266
      }
    },
    {
      "id": "375407f36dde60de5676472b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1264.2846713575868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.5259938019763,
        1272.0433489131976
      ],
      "voteCount": 13976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.670369050334045
      }
    },
    {
      "id": "bab678b73cddff774c99a037",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1230.7615303828768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.3440535254158,
        1238.1790072403378
      ],
      "voteCount": 14983,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.322413827418833
      }
    },
    {
      "id": "48c318868ae2ad0c39c4d2fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1243.0648070086613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.7753175189632,
        1250.3542964983594
      ],
      "voteCount": 19344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.832416147263729
      }
    },
    {
      "id": "4886ea9992f093193fb4fbdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1260.4813706526047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.7238795759426,
        1264.2388617292668
      ],
      "voteCount": 117701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.6753587244349184
      }
    },
    {
      "id": "041cc8a16a0055544e21c387",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1265.6311701714453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.3640480939262,
        1273.8982922489643
      ],
      "voteCount": 11956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.791498135141616
      }
    },
    {
      "id": "6a5161e41a0f84f7e04007b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-haiku-20240307",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1235.237503167539,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.6050241551393,
        1255.8699821799387
      ],
      "voteCount": 1704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.81706457553264
      }
    },
    {
      "id": "4af50637db062ff15718de6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1323.6122059161926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.6713143365487,
        1331.5530974958365
      ],
      "voteCount": 23348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.415055327409632
      }
    },
    {
      "id": "bc13d25eafb0567ff264a32a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1353.3944398015888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.4675559834236,
        1359.3213236197535
      ],
      "voteCount": 33748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.14443013284178
      }
    },
    {
      "id": "a01e8e96a8a750867d0b270d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1287.1856326877214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.6800572137577,
        1293.6912081616852
      ],
      "voteCount": 28395,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.017302077910015
      }
    },
    {
      "id": "933fb6bb8069ffa647c3f7af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1323.2470174161576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.2646158655796,
        1327.229418966736
      ],
      "voteCount": 108426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.1285154547567
      }
    },
    {
      "id": "9f1aed7587978534ae35db2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1261.5551342412878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.7667274115684,
        1266.3435410710074
      ],
      "voteCount": 133332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.968784526176994
      }
    },
    {
      "id": "5f7cd19f4295472e08dfa06a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1313.5934111941783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.1384825778955,
        1323.0483398104607
      ],
      "voteCount": 10374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.27128294527587
      }
    },
    {
      "id": "6609a467a3bf51975476ca7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1342.1887282368607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.546152192564,
        1360.8313042811571
      ],
      "voteCount": 2847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.47230695149797
      }
    },
    {
      "id": "a702ccff3bc1755b35726ecd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1318.0142376441786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.6421267914395,
        1330.386348496918
      ],
      "voteCount": 5672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.84661403315789
      }
    },
    {
      "id": "36a723843f166f2d7e788cfe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1325.7886070673767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.9780430583742,
        1331.5991710763792
      ],
      "voteCount": 34293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.789018880232552
      }
    },
    {
      "id": "3995cb973f3989d287e923f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1327.7352148943244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.8666066697303,
        1332.6038231189186
      ],
      "voteCount": 55074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.1704022224302015
      }
    },
    {
      "id": "bc78cec16925c10128defd47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1306.3919717353983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.3689345384919,
        1313.4150089323048
      ],
      "voteCount": 21697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.839666848288362
      }
    },
    {
      "id": "f55237be98150e04ce0dcd73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1283.1442254031588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.0546691803374,
        1289.23378162598
      ],
      "voteCount": 29359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.65328452595513
      }
    },
    {
      "id": "0ab4ebaa0383b72b264d4440",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1348.7706562996996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.3156656467345,
        1358.2256469526646
      ],
      "voteCount": 11095,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.27158832630744
      }
    },
    {
      "id": "8c14de64530f45c133882ce3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1339.5362447785783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.3816559608554,
        1345.6908335963012
      ],
      "voteCount": 33790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.860567373827877
      }
    },
    {
      "id": "15c8550f4cad89d51d55a356",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1309.5862201009118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.9974537505404,
        1316.1749864512828
      ],
      "voteCount": 22970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.300873976813456
      }
    },
    {
      "id": "367a9c0ce9d3f15784593697",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1334.6386155832345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.7283651075618,
        1344.5488660589072
      ],
      "voteCount": 10327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.566606092844374
      }
    },
    {
      "id": "3a593c1370e6b26bae9dba9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1340.1256227304466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.0717279669373,
        1345.1795174939557
      ],
      "voteCount": 54971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.648998068918575
      }
    },
    {
      "id": "235a1920154195903a7232be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1314.948713862388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.7010805932964,
        1320.1963471314796
      ],
      "voteCount": 49929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.168540966397974
      }
    },
    {
      "id": "3c6df9797e667c3a94b8022e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1312.112247365992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.6123885138163,
        1316.6121062181678
      ],
      "voteCount": 72001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.271104191049041
      }
    },
    {
      "id": "bcd5a15b6870b21ef73629e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1261.9678946087772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.3093894308968,
        1275.6263997866577
      ],
      "voteCount": 3650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.56352037127369
      }
    },
    {
      "id": "4b9242d30b088485e6fa5f77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1270.431802684127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.8023495846642,
        1287.0612557835902
      ],
      "voteCount": 3906,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.9879408566128
      }
    },
    {
      "id": "f6ca12e0c91d1f24ab044d02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1326.6815542170862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.2048954615539,
        1333.1582129726185
      ],
      "voteCount": 23374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.919577846219093
      }
    },
    {
      "id": "3345e0ebf437071800400dec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1311.8204249825317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.36258200136,
        1318.2782679637035
      ],
      "voteCount": 25769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.856223616093795
      }
    },
    {
      "id": "4a913155a04846ebf16ab7a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1320.2474124391424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.0419426444212,
        1326.4528822338634
      ],
      "voteCount": 31134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.024279100885447
      }
    },
    {
      "id": "04929ac257ddd6f792f7ed67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1321.195264478279,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.135303433597,
        1324.2552255229607
      ],
      "voteCount": 194909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.4374494253404384
      }
    },
    {
      "id": "b41c79d2b3ab861db4c5d4d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1332.684707452322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.689925956829,
        1339.6794889478153
      ],
      "voteCount": 21089,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.736559326399746
      }
    },
    {
      "id": "a6265d5b4de38fb7912bc928",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-opus-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1303.0341392532087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.023972080376,
        1322.0443064260412
      ],
      "voteCount": 2569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.07531690623051
      }
    },
    {
      "id": "392cdd4cd13a08e79b5869c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1275.272952789976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.030156345038,
        1284.5157492349138
      ],
      "voteCount": 15648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.23876139510965
      }
    },
    {
      "id": "eee07b5b55cdfbc2442e21bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1316.780098255192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.4357724524932,
        1324.1244240578906
      ],
      "voteCount": 18888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.041311911405332
      }
    },
    {
      "id": "27200d104e72edcdce6d46a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1244.9595973634487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.7278282120853,
        1253.1913665148122
      ],
      "voteCount": 15592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.639658922361125
      }
    },
    {
      "id": "f6b4e51eba512d19c5bf5235",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1287.7914669477975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.906722949473,
        1292.676210946122
      ],
      "voteCount": 60970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.21137048264753
      }
    },
    {
      "id": "4056e68fa3f1490b4a650035",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1199.323859465072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.4187680818982,
        1205.2289508482459
      ],
      "voteCount": 73557,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.077307833103859
      }
    },
    {
      "id": "614cbf10e39d07a13fee7306",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1267.9433726782536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.010855040141,
        1279.8758903163662
      ],
      "voteCount": 5614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.065339973666255
      }
    },
    {
      "id": "0259fe62609ca6115fcbfa4a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1304.7406397704967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.9484776337522,
        1325.5328019072413
      ],
      "voteCount": 1824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.53901876853985
      }
    },
    {
      "id": "22d8cc8c46db6970792a437c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1273.5691475188164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.6601843490666,
        1288.4781106885666
      ],
      "voteCount": 3097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.86270090923398
      }
    },
    {
      "id": "3c43712d08183309bf1c95d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1285.0706086370324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.8339859584003,
        1292.3072313156647
      ],
      "voteCount": 19193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.632505315632036
      }
    },
    {
      "id": "e2d9fa94e4b9c8dd5f177b85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1281.1599871051892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.175995390145,
        1287.1439788202333
      ],
      "voteCount": 30725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.321499596147476
      }
    },
    {
      "id": "238b6d3d79f728f059871007",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1262.4761282929467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.4245189946405,
        1271.5277375912528
      ],
      "voteCount": 11853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.328259578838406
      }
    },
    {
      "id": "b65af2067e65d6636c202343",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1237.993889579945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.1448554605495,
        1245.8429236993406
      ],
      "voteCount": 15961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.037484581522857
      }
    },
    {
      "id": "bc1f0598b3a6fc3bff9bc1b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1304.65341368201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.7671435814307,
        1316.5396837825895
      ],
      "voteCount": 6062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.778584256279686
      }
    },
    {
      "id": "8b15e7cf8acfcc9f9fb97681",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1299.2948106809908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.5996886669527,
        1306.989932695029
      ],
      "voteCount": 19089,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.41469154685238
      }
    },
    {
      "id": "16f129e57942e6a498e067f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1260.104089338482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.842721805966,
        1268.365456870998
      ],
      "voteCount": 12413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.76673828693495
      }
    },
    {
      "id": "cb77ec4e0ba41d30b0ee2a97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1299.0910470602546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.9234579586305,
        1311.2586361618787
      ],
      "voteCount": 5941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.540104542683295
      }
    },
    {
      "id": "5e29ac4ccbc489d2c38f920c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1306.1990836864816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.0259522381848,
        1312.3722151347783
      ],
      "voteCount": 31448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.920072987028677
      }
    },
    {
      "id": "835a9b9625d4fd7cbd6061cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1268.22507540828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.6293796938144,
        1274.8207711227456
      ],
      "voteCount": 27297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.324656592299164
      }
    },
    {
      "id": "c96831e7d2692238e3a93074",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1265.8243337108458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.176534517154,
        1271.4721329045376
      ],
      "voteCount": 38802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.303521453993335
      }
    },
    {
      "id": "e723adebd4bec2204a54933f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1195.9037839508637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.2601385792323,
        1213.5474293224954
      ],
      "voteCount": 1753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.03645946246152
      }
    },
    {
      "id": "b0d2c559e3077ab14f14b7de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1222.9157440355302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.7686429472387,
        1242.0628451238215
      ],
      "voteCount": 2059,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.43548354867062
      }
    },
    {
      "id": "19b73ababe29001885b1ec90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1284.1935813382097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.450289921855,
        1292.9368727545645
      ],
      "voteCount": 11870,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.900029743775594
      }
    },
    {
      "id": "1a0367f7727a5b0f6fa22a01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1253.2194428716698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.1859761057522,
        1261.2529096375877
      ],
      "voteCount": 13766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.800020849226215
      }
    },
    {
      "id": "d3639eb327f32c233882f87c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1276.520234103853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.5453103643638,
        1284.4951578433422
      ],
      "voteCount": 17062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.556056336737395
      }
    },
    {
      "id": "5a78c7155a82b09a01b4112e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1280.2970510720143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.30496833007,
        1284.2891338139584
      ],
      "voteCount": 109284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.148612639728506
      }
    },
    {
      "id": "76b9628385ad8a0560f246e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1283.1795568308141,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.9650213154696,
        1292.394092346159
      ],
      "voteCount": 10794,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.10297408529976
      }
    },
    {
      "id": "41320d36538dac2aa84c595c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-3-sonnet-20240229",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1263.8415970630076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.8286405658837,
        1285.8545535601313
      ],
      "voteCount": 1448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.14224865143952
      }
    },
    {
      "id": "da749012be662ac5a470783f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1431.325788315421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.8533968275456,
        1441.7981798032965
      ],
      "voteCount": 3794,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.549306030439624
      }
    },
    {
      "id": "4f2d3db8844e38da4a2826b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1479.46414971494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.3110809347086,
        1484.6172184951718
      ],
      "voteCount": 18302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.912508787221537
      }
    },
    {
      "id": "21fd5d602f505c98dd0a32dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1386.7115359108336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.468196438525,
        1392.9548753831425
      ],
      "voteCount": 11467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.147001330980231
      }
    },
    {
      "id": "47b6c115bd5d3ae5dc7227a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1430.5407001399765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.6652849440088,
        1434.4161153359441
      ],
      "voteCount": 36907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.9096717268528116
      }
    },
    {
      "id": "61b1f718a89d5f6f4ffa12d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1397.2146597517838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.1949582638442,
        1401.2343612397233
      ],
      "voteCount": 57064,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.206214567523129
      }
    },
    {
      "id": "78fffd126c54fc654cfd3520",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1452.5570332445566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.808259845412,
        1461.3058066437009
      ],
      "voteCount": 5372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.924991926829033
      }
    },
    {
      "id": "b0be179fba52722fa42a8da6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1423.6281088498129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.7264920118319,
        1440.5297256877939
      ],
      "voteCount": 1713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.36358557302097
      }
    },
    {
      "id": "1901d21b112d027e916deb5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1398.7847647169287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.9946865875334,
        1416.5748428463241
      ],
      "voteCount": 1308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.38715931173412
      }
    },
    {
      "id": "cd190b0b9c17eceba47a4efc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1453.7041961966934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.9209869899141,
        1458.4874054034726
      ],
      "voteCount": 21996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.955833807866911
      }
    },
    {
      "id": "58319af8e7a29147b7cc44ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1438.936858022691,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.2163390734654,
        1442.6573769719164
      ],
      "voteCount": 44441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.60338660328141
      }
    },
    {
      "id": "762297b129345d6d9a0fa40c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1416.973150083763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.3258076902596,
        1422.620492477266
      ],
      "voteCount": 14771,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.302178312481576
      }
    },
    {
      "id": "179336b6fbbdd09fff38c09a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1384.146560002314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.53001739474,
        1389.7631026098877
      ],
      "voteCount": 14551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.211867505322385
      }
    },
    {
      "id": "2fad50fee33a2dbe6cbdee34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1411.8355752751802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.1515307908433,
        1420.5196197595171
      ],
      "voteCount": 5526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.631247431234023
      }
    },
    {
      "id": "8e9e410882dcad429ff944f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1425.997875586262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.9630415884321,
        1432.0327095840917
      ],
      "voteCount": 12456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.48057055438671
      }
    },
    {
      "id": "a17342dc38a67e39e3acedf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1426.8412617654901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.6950656007464,
        1436.9874579302339
      ],
      "voteCount": 3783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.798490213896955
      }
    },
    {
      "id": "6f19d89b76d2f468ebbedc52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1418.6944041600732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.1551944973505,
        1428.2336138227956
      ],
      "voteCount": 4783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.688011569765237
      }
    },
    {
      "id": "ba238fea2880f98c98da946d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1461.0423031570306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.7092775556644,
        1465.375328758397
      ],
      "voteCount": 28318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.887495021670749
      }
    },
    {
      "id": "2a5ee23b2c6835af7e839740",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1397.4520323417514,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.2404534616394,
        1402.6636112218637
      ],
      "voteCount": 17467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.070375003713819
      }
    },
    {
      "id": "e0e7c733c4e9bdf78f4b8f69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1413.6967118884004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.0001494439045,
        1418.3932743328965
      ],
      "voteCount": 22436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.742010997546843
      }
    },
    {
      "id": "60a6d59731e8b6f83b7b7e0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1345.5666845739272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.4368129236175,
        1371.6965562242367
      ],
      "voteCount": 630,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.73721503496034
      }
    },
    {
      "id": "412ddf734a889f8c2a3c445f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1352.0447164160455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.8280990669384,
        1371.2613337651526
      ],
      "voteCount": 1146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.12972560129546
      }
    },
    {
      "id": "2ae92ef83a3c1c85ca13c2de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1437.7351416926474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.8767272518835,
        1442.5935561334115
      ],
      "voteCount": 22921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.144590370477922
      }
    },
    {
      "id": "57daccfb65c170e2f477be9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1394.8162700288342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.8516393313123,
        1403.780900726356
      ],
      "voteCount": 4744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.920334511988766
      }
    },
    {
      "id": "5b1bf035af6a4246e30dd26e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1425.790558551176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.9804827157736,
        1431.6006343865781
      ],
      "voteCount": 13730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.787542126255426
      }
    },
    {
      "id": "da2fff0b2355aebeaa612894",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1410.5571905029888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.663576723486,
        1413.4508042824918
      ],
      "voteCount": 78134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.179640885338721
      }
    },
    {
      "id": "592b01452429d21d3c665604",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1393.8915706504458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.4771733430066,
        1401.3059679578853
      ],
      "voteCount": 7276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.31052368345555
      }
    },
    {
      "id": "c7a839442963bb8c066035c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-haiku-4-5-20251001",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1427.7381652995844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.5687498997856,
        1442.9075806993833
      ],
      "voteCount": 1976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.902025327470334
      }
    },
    {
      "id": "865733b0ad8b7263cb784e12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1461.2627869336252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.3045584062343,
        1473.2210154610161
      ],
      "voteCount": 2570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.22524077128286
      }
    },
    {
      "id": "80ea805d808e01563c50ba70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1512.9323046208342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1506.431118012333,
        1519.4334912293355
      ],
      "voteCount": 9848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.002441856430003
      }
    },
    {
      "id": "e726db518a375e7577ce67b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1444.8193146178319,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.1796600324433,
        1452.4589692032202
      ],
      "voteCount": 6838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.19327029347214
      }
    },
    {
      "id": "6d6e17cc1d5832a36ff59d89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1464.4307414498574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.835218242662,
        1469.0262646570525
      ],
      "voteCount": 23576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.497607688542971
      }
    },
    {
      "id": "b9fe3945c1cdee3ed567cbb3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1450.7079267793772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.952292260439,
        1455.4635612983157
      ],
      "voteCount": 35856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.887362258287032
      }
    },
    {
      "id": "f94b167a40721f4316eee6e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1482.5212327992206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.1766523334743,
        1494.8658132649666
      ],
      "voteCount": 2334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.66947818218309
      }
    },
    {
      "id": "ae8ab36242385f13c302a72e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1474.8176165523212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.0010820998177,
        1497.6341510048246
      ],
      "voteCount": 766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.51993362985127
      }
    },
    {
      "id": "cf71055e5b9e8e758638328b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1451.4138746373962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.9507636513572,
        1470.8769856234355
      ],
      "voteCount": 985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.61167513086318
      }
    },
    {
      "id": "cb818cf52183289173d39f02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1489.057399029867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.2172329926198,
        1494.897565067114
      ],
      "voteCount": 12546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.878798637349906
      }
    },
    {
      "id": "fab85f018050e29a60bdae50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1479.9505829628683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.3747343941764,
        1484.5264315315603
      ],
      "voteCount": 24732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.450635058432384
      }
    },
    {
      "id": "759b13a8f2a121b8c72512b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1446.7445471206172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.122859930451,
        1453.3662343107835
      ],
      "voteCount": 9078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.414085973850769
      }
    },
    {
      "id": "7016a6932ce26a53a1587623",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1433.0969227389999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.4813323578849,
        1439.7125131201149
      ],
      "voteCount": 9043,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.39307698807844
      }
    },
    {
      "id": "1aaa5d70b719f42528dbb2d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1461.0780741298386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.498849701444,
        1471.6572985582334
      ],
      "voteCount": 3196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.13476226880906
      }
    },
    {
      "id": "5573b9e45b78aebe95f3442b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1470.2271508830256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.1646236979366,
        1477.2896780681147
      ],
      "voteCount": 7891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.984465685645528
      }
    },
    {
      "id": "f0cdd398ca381c835a07163d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1449.6635717353768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.8310707736346,
        1461.496072697119
      ],
      "voteCount": 2399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.44659113756477
      }
    },
    {
      "id": "bf5e89b74fa1c18c60925e1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1477.581422508469,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.794946361495,
        1489.367898655443
      ],
      "voteCount": 2653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.16361034896727
      }
    },
    {
      "id": "ed782988026c52f97c9bf4ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1491.6478355842753,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.4310629806664,
        1496.8646081878842
      ],
      "voteCount": 16951,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.0844743281271425
      }
    },
    {
      "id": "7f05e9d1d9c773e0a1a01cea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1444.9577834695115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.766362311292,
        1451.1492046277308
      ],
      "voteCount": 10986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.978942310130217
      }
    },
    {
      "id": "0702a63e10990fc3eb627f14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1459.6948924396372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.9306155997517,
        1465.459169279523
      ],
      "voteCount": 12973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.649549308675676
      }
    },
    {
      "id": "676118668f62ee96da1114bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1413.1770333774614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.5292803097411,
        1437.8247864451819
      ],
      "voteCount": 560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.14610012597944
      }
    },
    {
      "id": "87645bf2a8df260aadc8f8a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1419.7702257935707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.440932476387,
        1439.0995191107545
      ],
      "voteCount": 1052,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.2603371742545
      }
    },
    {
      "id": "bc59fc8961e9be424db863e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1485.0938814462324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.9236253985653,
        1491.2641374938996
      ],
      "voteCount": 11148,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.910833740733155
      }
    },
    {
      "id": "76e36e8018d6414f71da9f4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1443.3119925252927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.7147877518885,
        1453.9091972986967
      ],
      "voteCount": 3028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.233880734186094
      }
    },
    {
      "id": "682148f4edec0d004c554f81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1472.8332913210422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.015579185218,
        1479.6510034568664
      ],
      "voteCount": 8584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.09988208556811
      }
    },
    {
      "id": "2d01be7d8624e48991aad640",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1448.9875094482613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.5340523006225,
        1452.4409665959001
      ],
      "voteCount": 49833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.104645091164184
      }
    },
    {
      "id": "c3b9130e839fc86639a1c1d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1444.5372655632605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.3588234380165,
        1454.7157076885042
      ],
      "voteCount": 3272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.96909922314832
      }
    },
    {
      "id": "2f163273ecf937dbd8593f0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1463.8423396550263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.9060576626698,
        1482.7786216473828
      ],
      "voteCount": 1146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.34546911250095
      }
    },
    {
      "id": "2b48e0c3a68f97aa9d8127b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1465.6638767377792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.6577873050176,
        1475.6699661705406
      ],
      "voteCount": 3839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.063490566932526
      }
    },
    {
      "id": "2187b2f1d845f57b51a8f7a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1504.9529042595952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1499.5003979513747,
        1510.4054105678158
      ],
      "voteCount": 15538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.739201805582211
      }
    },
    {
      "id": "192b2a1524b28eff0a84d91b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1441.9341961720384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.6601877166513,
        1448.2082046274256
      ],
      "voteCount": 10723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.246935847969363
      }
    },
    {
      "id": "6a65dc5dfc5b0993551e3029",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1457.4782232912376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.5186922954524,
        1461.4377542870227
      ],
      "voteCount": 36384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.0812322709605775
      }
    },
    {
      "id": "b1705889a1ea33a8613fbdb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1447.4776302660482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.3464488660097,
        1451.6088116660867
      ],
      "voteCount": 55807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.442754837845782
      }
    },
    {
      "id": "9f683a6217853425436a19a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1465.5975876545608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.7838456199368,
        1475.4113296891849
      ],
      "voteCount": 3890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.071082944667666
      }
    },
    {
      "id": "db86a961ee754e38b36514b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1464.3863227580578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.0306044489005,
        1482.742041067215
      ],
      "voteCount": 1278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.70949016297138
      }
    },
    {
      "id": "b204f8c13d6173b534b41da5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1437.567905187873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.3648744075824,
        1453.7709359681635
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.34336087445072
      }
    },
    {
      "id": "c0ad5080163d0918e194b82a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1482.4846897035238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.4897520106306,
        1487.479627396417
      ],
      "voteCount": 19376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.4947728767731885
      }
    },
    {
      "id": "a3ebaad6e33e2d96f0799b2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1477.3392298174228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.4009606877637,
        1481.277498947082
      ],
      "voteCount": 38916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.037519198194633
      }
    },
    {
      "id": "a2053cbd7f5cd1decf674f93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1446.536934114305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.8533815077076,
        1452.2204867209027
      ],
      "voteCount": 13944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.408985164163699
      }
    },
    {
      "id": "d454154f8e3b88ce8f12dd28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1432.8658013961203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.28585812999,
        1438.4457446622505
      ],
      "voteCount": 14106,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.10519344513151
      }
    },
    {
      "id": "e11d8d9943a6e2f7f7957705",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1458.0413884820202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.440342872997,
        1466.6424340910435
      ],
      "voteCount": 5275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.257784352646482
      }
    },
    {
      "id": "d0099cbc5c9df43d44e1d8fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1463.5856763284937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.6421774454407,
        1469.5291752115468
      ],
      "voteCount": 12088,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.195771872538097
      }
    },
    {
      "id": "f81568394c98c36d49dabdb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1441.2081795107179,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.5544290373978,
        1450.861929984038
      ],
      "voteCount": 3776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.260288226723155
      }
    },
    {
      "id": "6a8ac46c08bc2eda7e36e521",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1474.5094818811183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.8705409974616,
        1484.1484227647752
      ],
      "voteCount": 4356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.185911054967825
      }
    },
    {
      "id": "90941782bb1fcb1c8821c916",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1485.5782691795778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.0880723889427,
        1490.0684659702129
      ],
      "voteCount": 26339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.248492346193238
      }
    },
    {
      "id": "af8b2eada58745951e4074c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1443.6204945373343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4389930932853,
        1448.8019959813832
      ],
      "voteCount": 17221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.98900039486309
      }
    },
    {
      "id": "d30fc92bcc6bc471be6d20a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1455.2211667597333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.323411090131,
        1460.1189224293355
      ],
      "voteCount": 20321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.244505464928176
      }
    },
    {
      "id": "23d066d760dc3e8655c39bcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1404.2793474617215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.9571067812496,
        1423.6015881421933
      ],
      "voteCount": 1042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.18937579203802
      }
    },
    {
      "id": "b3d797d110d5027814a3e132",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1400.3069566268339,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.0114609212806,
        1416.6024523323874
      ],
      "voteCount": 1522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.12560896376566
      }
    },
    {
      "id": "a78baf036d14a48bbbba4d48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1472.4031269634595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.2159783863945,
        1477.5902755405245
      ],
      "voteCount": 17745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.004242819316544
      }
    },
    {
      "id": "5deb6ab390c48c2653d52e9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1433.4098170472173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.7896960892874,
        1442.0299380051472
      ],
      "voteCount": 4723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.343298678369166
      }
    },
    {
      "id": "bbfdc8fc38c6d8bb85fc0654",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1468.7479880935118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.9108458201108,
        1474.5851303669128
      ],
      "voteCount": 13252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.869606967117683
      }
    },
    {
      "id": "87e02715b5a26a3db61f4f5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1446.894516445945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.8985388427914,
        1449.8904940490986
      ],
      "voteCount": 77373,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.3365815481982817
      }
    },
    {
      "id": "e0dd4961f776d0d5ba06f932",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1453.6425150497346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.621775950248,
        1461.6632541492213
      ],
      "voteCount": 5729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.746829448091727
      }
    },
    {
      "id": "3085ffc370c9275194c4bf38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-1-20250805",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1463.0342063561716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.0422279827776,
        1478.0261847295658
      ],
      "voteCount": 1993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.50887020772614
      }
    },
    {
      "id": "f799e898be791ed96ec50f3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1448.5327914960637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.79497572948,
        1462.2706072626477
      ],
      "voteCount": 1896,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.1291436003206
      }
    },
    {
      "id": "cb72272e92bb8f2187066bb3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1498.2189833731204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.447969054392,
        1505.9899976918489
      ],
      "voteCount": 6674,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.72024232475555
      }
    },
    {
      "id": "df4878ed7768f3b1a6740066",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1429.802704141111,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.68738916404,
        1438.918019118182
      ],
      "voteCount": 4522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.62953477038698
      }
    },
    {
      "id": "74a08810a0b5f59ee256be5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1433.7494206472643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.2556236065457,
        1439.243217687983
      ],
      "voteCount": 17472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.856860461972627
      }
    },
    {
      "id": "26fc529b7c89851f62425273",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1415.2354118479957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.50044854358,
        1420.9703751524114
      ],
      "voteCount": 27040,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.561800513340476
      }
    },
    {
      "id": "c8dad89c8fd44db056207493",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1446.719135926404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.2815179547292,
        1461.1567538980787
      ],
      "voteCount": 1709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.26188914823856
      }
    },
    {
      "id": "dfcd2ee50f23fab8f012cf2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1446.928870070489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.4967488876591,
        1475.3609912533188
      ],
      "voteCount": 470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.43711586866684
      }
    },
    {
      "id": "2db2db5d6f2378716f328321",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1444.3319705278811,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.07745956954,
        1464.5864814862223
      ],
      "voteCount": 900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.79411997118171
      }
    },
    {
      "id": "9618a64c05abce015dca2169",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1462.4352801452949,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.3847391183742,
        1469.4858211722158
      ],
      "voteCount": 8390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.94042994929492
      }
    },
    {
      "id": "16c4837865c8ae1b6130648a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1455.8117185754033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.2173145927875,
        1461.406122558019
      ],
      "voteCount": 16387,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.147257951095897
      }
    },
    {
      "id": "4e1ba1a0cbae43c7dbdedd2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1410.7537965543784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.6898913067116,
        1418.8177018020453
      ],
      "voteCount": 6117,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.927571237532966
      }
    },
    {
      "id": "dbbfc15ecceab2511a411729",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1420.0201681938217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.2042819185287,
        1427.8360544691145
      ],
      "voteCount": 6356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.902312407782924
      }
    },
    {
      "id": "7c28b48da57588eb5c664341",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1433.9769021544685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.7191485728856,
        1446.2346557360513
      ],
      "voteCount": 2466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.11340193402337
      }
    },
    {
      "id": "8c7229ee1f40a052bef53eb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1437.202270145994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.02642833451,
        1445.3781119574778
      ],
      "voteCount": 5970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.40078247521867
      }
    },
    {
      "id": "e2f4d4ddfe0a675c7c21b339",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1425.381538977085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.6064365949114,
        1438.1566413592586
      ],
      "voteCount": 2047,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.48470398689012
      }
    },
    {
      "id": "8d2a0454f6205dbc2f5e1b31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1442.98954777568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.0206893731577,
        1455.9584061782025
      ],
      "voteCount": 2248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.78318136813527
      }
    },
    {
      "id": "c2d2561df03d4e5dde0d066e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1466.2782656550874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.1008924403152,
        1472.4556388698595
      ],
      "voteCount": 12296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.933710503159887
      }
    },
    {
      "id": "1b5772b44c9823e971e35a01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1429.8131578223806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.5851724045992,
        1437.0411432401622
      ],
      "voteCount": 7896,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.599982620722736
      }
    },
    {
      "id": "c97d965f6ed0e4b0325bd33a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1443.3538283858234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.5443741557267,
        1450.16328261592
      ],
      "voteCount": 9133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.070588043790174
      }
    },
    {
      "id": "ad4b7a8dff1fc9da7f8d6dc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1386.265856856334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.699370781334,
        1408.832342931334
      ],
      "voteCount": 755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.5658604043429
      }
    },
    {
      "id": "bbb6fb65f7a53e4cf7741e64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1380.756546617483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.1159949984265,
        1403.3970982365397
      ],
      "voteCount": 724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.43747819286602
      }
    },
    {
      "id": "3894d9f96923f7550cb701e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1464.6886746603195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.0609699438703,
        1472.316379376769
      ],
      "voteCount": 6931,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.145777153177814
      }
    },
    {
      "id": "9018b5e745101c474028ef45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1419.8606567997274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.685567810059,
        1432.0357457893958
      ],
      "voteCount": 2239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.58763007110997
      }
    },
    {
      "id": "ae2c7ff39dc6e81cd7c6ff7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1437.1501314112934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.0955259413167,
        1445.2047368812698
      ],
      "voteCount": 6314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.888549976764867
      }
    },
    {
      "id": "623791584c6fdd1d32424db3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1424.308500857695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.965377210672,
        1428.651624504718
      ],
      "voteCount": 36900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.910302021647512
      }
    },
    {
      "id": "88e56690e3870d58b4bc95fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1437.3422009670924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.851800312162,
        1449.8326016220228
      ],
      "voteCount": 2121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.61220380139262
      }
    },
    {
      "id": "1133afe8da9dc9c707eb042e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514-thinking-16k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1419.979008333744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.8925911164843,
        1442.065425551004
      ],
      "voteCount": 766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.98556675058424
      }
    },
    {
      "id": "df2dd50debb6e7de8148fb52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1445.6741566279875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.5350789252404,
        1457.8132343307343
      ],
      "voteCount": 2420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.359699882634835
      }
    },
    {
      "id": "22515f2c9da39270f3088008",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1463.8709207130435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.6288483598566,
        1471.1129930662303
      ],
      "voteCount": 7903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.65304547487405
      }
    },
    {
      "id": "65094889f02f49efa6d410a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1416.5718959139538,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.0785248091847,
        1425.0652670187226
      ],
      "voteCount": 5485,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.778634912007057
      }
    },
    {
      "id": "b17f7fc0a50f19dcaa6732ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1424.528134073702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.2197436871227,
        1429.8365244602812
      ],
      "voteCount": 21452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.33549669842235
      }
    },
    {
      "id": "fecdf9b3b518efd21cb5a237",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1399.6928736852005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.0220773180633,
        1405.3636700523377
      ],
      "voteCount": 32075,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.371281051953192
      }
    },
    {
      "id": "d118b4579a6464ece6f4087e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1434.8962751645088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.309004368515,
        1447.4835459605029
      ],
      "voteCount": 2219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.24458792533723
      }
    },
    {
      "id": "20a08ab488656911ec64eabd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1425.521320218236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.9640077855906,
        1451.0786326508817
      ],
      "voteCount": 580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.03337775252555
      }
    },
    {
      "id": "7bf648048a32a7b6a514a357",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1431.0552993818985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.6311944263596,
        1448.4794043374375
      ],
      "voteCount": 1231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.03232799636704
      }
    },
    {
      "id": "168a9466dd6828dfb8cbf585",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1442.285819278882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.5888822675981,
        1448.9827562901658
      ],
      "voteCount": 9919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.674982715290298
      }
    },
    {
      "id": "381fb90c1c6993ac7fc713c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1434.834394057985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.4144465161214,
        1440.2543415998489
      ],
      "voteCount": 19166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.647050958429357
      }
    },
    {
      "id": "8ac0ad14a7981a612e94b6ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1403.3567447835776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.7160195080378,
        1410.9974700591176
      ],
      "voteCount": 7179,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.197529235970086
      }
    },
    {
      "id": "b0d28132e547d27177d0a3f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1399.1915720811949,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.870273725175,
        1406.512870437215
      ],
      "voteCount": 7593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.953399507788522
      }
    },
    {
      "id": "1f9ec291edd0be35eae57c5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1438.9956712141995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.8668828597447,
        1450.1244595686544
      ],
      "voteCount": 2915,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.24033785578116
      }
    },
    {
      "id": "21d07e1e304dfe6f00d936fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1430.1445782342253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.4440773786826,
        1437.845079089768
      ],
      "voteCount": 7074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.436248621688966
      }
    },
    {
      "id": "93d7d2c729c1a1f14f944989",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1409.200411569057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.7953753608786,
        1420.6054477772357
      ],
      "voteCount": 2639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.86079533357043
      }
    },
    {
      "id": "cf2d888011ae7a8720d26053",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1447.7438071939112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.693450362498,
        1459.7941640253243
      ],
      "voteCount": 2636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.801029906172026
      }
    },
    {
      "id": "a20ea8a46192e507c4d49578",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1441.2885665370004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.3773897544254,
        1447.1997433195754
      ],
      "voteCount": 14859,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.09602642793414
      }
    },
    {
      "id": "b72b0ec0d1210e726e715c66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1418.2760026947344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.4242182554378,
        1425.127787134031
      ],
      "voteCount": 9436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.221125409357622
      }
    },
    {
      "id": "ca4a8088cb5b2c3e9ac180a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1413.200271847171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.7369449778569,
        1419.6635987164855
      ],
      "voteCount": 10699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.874669277868778
      }
    },
    {
      "id": "66d470e5f7ea5fb6e1b3bff1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1380.6010844381758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.7761452099915,
        1400.4260236663604
      ],
      "voteCount": 974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.312229219781
      }
    },
    {
      "id": "aaae634d1725f5cfdf8c5b3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1363.9447879281763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.8729891416804,
        1384.0165867146723
      ],
      "voteCount": 963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.87607061027445
      }
    },
    {
      "id": "4b506b0e1a03d8536484b201",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1446.6460114098686,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.5064705807924,
        1453.7855522389445
      ],
      "voteCount": 8361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.269189031898195
      }
    },
    {
      "id": "5b70d8e5ebd98ebc4403b1f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1402.8037867339917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.7877277008768,
        1413.8198457671065
      ],
      "voteCount": 2768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.59048743860941
      }
    },
    {
      "id": "3621a315042c44610f0e78d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1428.2507103162463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.725539430835,
        1435.7758812016575
      ],
      "voteCount": 7694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.741326016455844
      }
    },
    {
      "id": "677f9ed8d474773865f0660c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1412.1833793448789,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.9094474528417,
        1416.457311236916
      ],
      "voteCount": 44223,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.755092966081084
      }
    },
    {
      "id": "1b2450fc9a2714a520b4f5ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1426.7204480356254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.5828125085307,
        1437.8580835627204
      ],
      "voteCount": 2816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.29161912817033
      }
    },
    {
      "id": "b13b6a41267c8c9b0ad091e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1396.4574209481273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.574986692482,
        1417.3398552037725
      ],
      "voteCount": 872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.51834831397301
      }
    },
    {
      "id": "ea2604063864a2dddacb1167",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1496.9851459525737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.9311087473213,
        1511.039183157826
      ],
      "voteCount": 1828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.41691502785084
      }
    },
    {
      "id": "a292761268397b4ce25cd559",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1530.0828346974247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1522.6852096537166,
        1537.4804597411328
      ],
      "voteCount": 7628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.245852641317365
      }
    },
    {
      "id": "34e405cebeb69859e2e07f7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1467.9761573421172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.5334748448283,
        1476.418839839406
      ],
      "voteCount": 5546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.555161223138764
      }
    },
    {
      "id": "7b57c469c68025a435e0063b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1483.6374755779711,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.26602645589,
        1489.0089247000524
      ],
      "voteCount": 17029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.510809569447212
      }
    },
    {
      "id": "28c68f0c65f039b638e42706",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1483.6180990766757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.1724028142175,
        1489.0637953391335
      ],
      "voteCount": 26818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.719881734301828
      }
    },
    {
      "id": "d2acda3a3899539ab46368fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1504.5483055094098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.574376892261,
        1517.5222341265585
      ],
      "voteCount": 2204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.81742239591584
      }
    },
    {
      "id": "a7324c2591c152ad1c5f892e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1492.1076928666853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.0025676440468,
        1515.2128180893235
      ],
      "voteCount": 766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.96981237386692
      }
    },
    {
      "id": "1722dc6d7d3331a44029a73d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1477.9788984161066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.7018558279126,
        1502.2559410043007
      ],
      "voteCount": 614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.42473376364023
      }
    },
    {
      "id": "d99a0d7936deee57ca852f55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1504.9640301254392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.196546253221,
        1511.7315139976572
      ],
      "voteCount": 9405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.922251441044082
      }
    },
    {
      "id": "58e121893dc98e28d80cca62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1499.077143714089,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.9208160709939,
        1504.2334713571843
      ],
      "voteCount": 19787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.9212546597448386
      }
    },
    {
      "id": "4e5eb265dc2c148d72956b04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1467.0159049836861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.3273947980501,
        1474.7044151693224
      ],
      "voteCount": 6877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.388213601610166
      }
    },
    {
      "id": "b7c4a05fbbd169cefa7e3e46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1455.4280681294956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.7621733522185,
        1463.093962906773
      ],
      "voteCount": 6788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.297819260670261
      }
    },
    {
      "id": "69384e85567934dbd3cd11de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1485.2593491080731,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.535550745244,
        1496.9831474709022
      ],
      "voteCount": 2672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.78001339278565
      }
    },
    {
      "id": "1fdaa5760c3a21ee43daa895",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1488.7307556184408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.4522495862336,
        1497.009261650648
      ],
      "voteCount": 5824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.840530205893863
      }
    },
    {
      "id": "6276e7cb3e11cfcd020027e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1470.643819718083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.6942465329078,
        1485.5933929032583
      ],
      "voteCount": 1554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.178350686713145
      }
    },
    {
      "id": "07bdf360a36f65428176f06a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1487.8338266724616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.9599349694638,
        1500.7077183754595
      ],
      "voteCount": 2338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.14430931491067
      }
    },
    {
      "id": "77efe5802e7cedc1acc90965",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1511.8188864276838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1505.8046061023517,
        1517.833166753016
      ],
      "voteCount": 12738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.416101934197277
      }
    },
    {
      "id": "31a085671cba718eb3e41e19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1465.0706909738421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.9560396907025,
        1472.1853422569818
      ],
      "voteCount": 8327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.176833396728814
      }
    },
    {
      "id": "d71ee82a2fde4bfcb64256aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1484.268106680981,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.4536464269186,
        1491.0825669350434
      ],
      "voteCount": 9460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.08834214336432
      }
    },
    {
      "id": "80f9b463ce8821394ad14c6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1456.82325364014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.864167899996,
        1491.782339380284
      ],
      "voteCount": 311,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 318.14415638221334
      }
    },
    {
      "id": "02f730d7ca3338c331d856c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1402.4466138667601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.2003967717799,
        1428.6928309617404
      ],
      "voteCount": 550,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.32351847321314
      }
    },
    {
      "id": "208774612248b5f57c5f48e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1494.5366244271802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.66963231147,
        1501.4036165428906
      ],
      "voteCount": 9258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.275435692086228
      }
    },
    {
      "id": "db803d98c6fe45489ebf79ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1469.9888437764253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.6067301476942,
        1482.3709574051563
      ],
      "voteCount": 2265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.9110715671043
      }
    },
    {
      "id": "ace49eab2f6114f1752f08b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1487.2103530760905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.2751822806617,
        1495.1455238715193
      ],
      "voteCount": 6474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.391412349240987
      }
    },
    {
      "id": "4f32f48247d59abe0e84b517",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1472.5918107206244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.690507247813,
        1476.4931141934358
      ],
      "voteCount": 37130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.9620804224110002
      }
    },
    {
      "id": "c1391ae36d865e7e1d4e3b7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1466.386174462317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.6203831485252,
        1476.151965776109
      ],
      "voteCount": 3851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.826682892125486
      }
    },
    {
      "id": "6844c4cfde6febc37e890fb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1471.1606516257664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.4008400063199,
        1490.9204632452127
      ],
      "voteCount": 984,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.64111434245659
      }
    },
    {
      "id": "59fdd1fd1683a25822064640",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1501.0695085231482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.9112587411562,
        1512.22775830514
      ],
      "voteCount": 3349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.41126457652022
      }
    },
    {
      "id": "98bf2bf0a90b7c320cd93ac7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1521.1782696814673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1515.4106571076322,
        1526.9458822553022
      ],
      "voteCount": 15711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.659563034401808
      }
    },
    {
      "id": "a28dfaa7af412e256c158ca2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1462.8973845644912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.1546969738288,
        1469.6400721551533
      ],
      "voteCount": 10245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.835044462888986
      }
    },
    {
      "id": "0e7bf46a5f5c7e4e60980d9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1478.5626637457287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.143659853968,
        1482.9816676374894
      ],
      "voteCount": 30790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.083380118563201
      }
    },
    {
      "id": "84249809600ca726575f780b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1478.336085265273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.8459348419185,
        1482.8262356886273
      ],
      "voteCount": 48465,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.248383951362342
      }
    },
    {
      "id": "318e4c0940a00c12ad1b8ede",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1502.2903290874024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.9139781471147,
        1511.6666800276898
      ],
      "voteCount": 4614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.886086005093965
      }
    },
    {
      "id": "7dd6390e4ebdfdaa9794a2d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1506.3088031112784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.9177007757798,
        1523.6999054467772
      ],
      "voteCount": 1677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.73322468393279
      }
    },
    {
      "id": "54d0606f2a78192159657a6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1468.1743938011336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.5696007556683,
        1487.7791868465993
      ],
      "voteCount": 1025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.05259155324872
      }
    },
    {
      "id": "8fb34d558c141d7e4e41b76d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1498.6292709732877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.2452864909849,
        1504.0132554555905
      ],
      "voteCount": 18389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.545906453434323
      }
    },
    {
      "id": "0a5fc59084790f0fa32ecde9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1497.8988231215137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.6750034392317,
        1502.1226428037958
      ],
      "voteCount": 37926,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.6442389574306215
      }
    },
    {
      "id": "eb2beff36f4116f3864cb330",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1471.7329604629545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.499986250376,
        1477.965934675533
      ],
      "voteCount": 12541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.113336976406314
      }
    },
    {
      "id": "08b913a20f37ce92777f2e86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1452.8484216673578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.6527340769976,
        1459.0441092577178
      ],
      "voteCount": 12451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.992699781279134
      }
    },
    {
      "id": "ece098814040a94e02ebf52d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1479.7400671220914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.5247983301078,
        1488.955335914075
      ],
      "voteCount": 4820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.106492057400597
      }
    },
    {
      "id": "a4f07a8bb2de64f794bf1354",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1487.0578963917471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.4768147489265,
        1493.6389780345676
      ],
      "voteCount": 10310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.274528144399754
      }
    },
    {
      "id": "5644d7e56b1596256c368846",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1478.9091931046353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.7646434186295,
        1490.053742790641
      ],
      "voteCount": 3115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.33172435293998
      }
    },
    {
      "id": "d334dd3d890fbe7745259050",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1489.278296336643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.469849803429,
        1499.0867428698573
      ],
      "voteCount": 4337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.044033500152953
      }
    },
    {
      "id": "d39249270cfa52bde69b25a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1506.0469947666174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1501.1547346905263,
        1510.9392548427084
      ],
      "voteCount": 24146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.230499861974167
      }
    },
    {
      "id": "c764e3a5072dc308c9af0149",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1465.4727628435442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.707140045872,
        1471.2383856412164
      ],
      "voteCount": 15054,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.653589117227746
      }
    },
    {
      "id": "f9fe07b886dcb1c22470bfed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1476.2323584346243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.9218493603278,
        1481.5428675089208
      ],
      "voteCount": 18864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.3413533619734235
      }
    },
    {
      "id": "814dcaa97256f3c41e80c4e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1436.4504463528922,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.7785909603147,
        1464.12230174547
      ],
      "voteCount": 530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 199.33353879591016
      }
    },
    {
      "id": "bf40d32401e5918846569584",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1449.3151160831608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.1975794271245,
        1469.432652739197
      ],
      "voteCount": 1005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.35458012116169
      }
    },
    {
      "id": "ae050b07d1472a35bfb4c38c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1491.9536024187946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.6288297681606,
        1497.2783750694286
      ],
      "voteCount": 20053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.380842826740595
      }
    },
    {
      "id": "7ff6abe9bf4a1a47dcd035e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1467.2701022707818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.70019799942,
        1476.8400065421438
      ],
      "voteCount": 4078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.84070011883697
      }
    },
    {
      "id": "5b35ef8f91f4feafc3a8fb44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1484.0923387529126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.6857646697206,
        1490.4989128361044
      ],
      "voteCount": 11654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.684532465197739
      }
    },
    {
      "id": "8953401c1f3498abe71a24b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1469.0605545014603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.763804154227,
        1472.3573048486937
      ],
      "voteCount": 66107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.829280062416318
      }
    },
    {
      "id": "76461f7321dd5535e2a578ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1472.843293196202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.1181409369399,
        1480.568445455464
      ],
      "voteCount": 7035,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.53523809946708
      }
    },
    {
      "id": "9aaf8995d4af70e1a72e8e79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-5-20251101",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1463.384377000807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.400200953238,
        1479.368553048376
      ],
      "voteCount": 1750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.50959852629984
      }
    },
    {
      "id": "67856ca7cc32061abaf81c97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1550.4511501381155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1535.1937642472485,
        1565.7085360289827
      ],
      "voteCount": 1827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.59880766358709
      }
    },
    {
      "id": "b97b64f4ed8b90952b2f4e9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1551.4362335029068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1543.9983942246886,
        1558.874072781125
      ],
      "voteCount": 8335,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.401157401606687
      }
    },
    {
      "id": "9ea727e7e2032c310536ee9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1497.157943930508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.2576854357887,
        1506.0582024252276
      ],
      "voteCount": 5508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.620968483663585
      }
    },
    {
      "id": "d33d33c9d3ac6ab592f9974e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1515.6173602634933,
      "unit": "Arena rating",
      "confidenceInterval": [
        1509.9610661889324,
        1521.2736543380543
      ],
      "voteCount": 15739,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.328518969294143
      }
    },
    {
      "id": "41aa23345e0b82f934542b4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1523.0145380444771,
      "unit": "Arena rating",
      "confidenceInterval": [
        1517.1646364552794,
        1528.8644396336751
      ],
      "voteCount": 25591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.90842521048222
      }
    },
    {
      "id": "72d19f8d202c0f320bf53c0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1545.96070682077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1533.2734224646342,
        1558.6479911769056
      ],
      "voteCount": 2574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.90261873075616
      }
    },
    {
      "id": "66404bfeb257c27b141b251c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1505.953925708635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.1489360936348,
        1527.7589153236356
      ],
      "voteCount": 936,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.77005567493379
      }
    },
    {
      "id": "d46a2feda2baecfb2e2bf66e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1519.3515625211485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.9492852792785,
        1545.7538397630183
      ],
      "voteCount": 518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.46237564785392
      }
    },
    {
      "id": "136b1962006fbfa766ea3659",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1541.9218068021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1535.0008715524036,
        1548.8427420517964
      ],
      "voteCount": 9816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.469050682634876
      }
    },
    {
      "id": "9ade45ae45986a152ced4a24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1533.20303509045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1527.8825389310289,
        1538.5235312498708
      ],
      "voteCount": 20448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.368992016761648
      }
    },
    {
      "id": "2bcf8e5ad3144b4b9809da37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1500.6157136160728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.5867653755618,
        1508.6446618565838
      ],
      "voteCount": 6618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.7811273939821
      }
    },
    {
      "id": "32a5d502ae7a9611fa6c9f58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1491.1766034497487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.0285201031886,
        1499.3246867963087
      ],
      "voteCount": 6710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.282825437262506
      }
    },
    {
      "id": "73fa5222a7b5d2d8ce43acf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1512.7942362919346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.2037290707513,
        1525.3847435131179
      ],
      "voteCount": 2627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.26580017797097
      }
    },
    {
      "id": "d199ee98684993df807af976",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1521.4668703135237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1512.9016500330367,
        1530.0320905940107
      ],
      "voteCount": 5556,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.097692277229374
      }
    },
    {
      "id": "100006e997e9aea70c066730",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1526.5278759948887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1511.3147301280883,
        1541.7410218616894
      ],
      "voteCount": 1703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.24789486685964
      }
    },
    {
      "id": "6ed79d362597cd2cd5773871",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1513.761758835614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.9535931737255,
        1526.5699244975026
      ],
      "voteCount": 2451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.70489813365664
      }
    },
    {
      "id": "a349eef6c95e44cb1c4968c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1539.9064693443695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1533.67210468608,
        1546.140834002659
      ],
      "voteCount": 12520,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.117849626071207
      }
    },
    {
      "id": "7357888212974c0b95f0daf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1497.0405832092779,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.6546268045004,
        1504.4265396140556
      ],
      "voteCount": 8071,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.200946713108184
      }
    },
    {
      "id": "7fad0fad784ec98a5fe7b57e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1515.1771578081687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1508.323482903629,
        1522.0308327127084
      ],
      "voteCount": 10045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.22787016330162
      }
    },
    {
      "id": "010250abb2e211597777bede",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1490.1826032271172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.5125561916343,
        1528.8526502626
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 389.2720467731738
      }
    },
    {
      "id": "b54a8a7e954aa85fabe4c22a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1430.726348676408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.6912266483414,
        1456.7614707044745
      ],
      "voteCount": 561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.45056491685523
      }
    },
    {
      "id": "751af94b55106c1df7c3e903",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1525.5498118251953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1518.9606894160536,
        1532.138934234337
      ],
      "voteCount": 11853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.302095414577062
      }
    },
    {
      "id": "2ecc7a9f432415f80511cb29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1514.4584330425012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.827984707266,
        1528.0888813777362
      ],
      "voteCount": 1981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.36421018459345
      }
    },
    {
      "id": "02e5e17d9cbfb46e9b34f073",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1511.3637293437962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.84066237109,
        1519.8867963165021
      ],
      "voteCount": 5772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.910178141153818
      }
    },
    {
      "id": "36ff89ff06682306d7353b3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1502.1675383788238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.908027964492,
        1506.4270487931553
      ],
      "voteCount": 34186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.723056999091204
      }
    },
    {
      "id": "6c0bd217a7397b47509cd485",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1504.5207842754319,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.158896148495,
        1514.8826724023688
      ],
      "voteCount": 3704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.949987378950322
      }
    },
    {
      "id": "703ce18e81dada73385a705f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1499.9908396000624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.9434555209577,
        1519.0382236791668
      ],
      "voteCount": 1148,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.44402691563135
      }
    },
    {
      "id": "ec2e3a5ee81cefc844c093fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1545.3744505625502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1530.5553496286238,
        1560.1935514964766
      ],
      "voteCount": 1875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.16728012464243
      }
    },
    {
      "id": "ff8d0524b0c0bf0b752c1259",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1546.4555807029644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1539.4471260180837,
        1553.4640353878451
      ],
      "voteCount": 9596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.786402083870708
      }
    },
    {
      "id": "888e23d4dc52ca4b1debbe2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1477.253497227355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.582760054973,
        1485.9242343997369
      ],
      "voteCount": 5665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.571128215020018
      }
    },
    {
      "id": "c43b1d795cc85a3b6ed8f869",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1507.6915756225414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.2166864124438,
        1513.1664648326393
      ],
      "voteCount": 17146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.802872101966069
      }
    },
    {
      "id": "a024b23e961f6fe45747a129",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1518.9002014866105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1513.130287902187,
        1524.670115071034
      ],
      "voteCount": 27011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.666473942755282
      }
    },
    {
      "id": "b95095c3f102067c7e283415",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1542.0711390014508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1530.4059131079425,
        1553.736364894959
      ],
      "voteCount": 3125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.4233903051414
      }
    },
    {
      "id": "6bf67c650131abca6d5759ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1502.6711480478996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.82659620409,
        1523.5156998917091
      ],
      "voteCount": 1019,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.10685909962432
      }
    },
    {
      "id": "e186b4ae13e491fefaa6cd8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1500.095881019937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.872420676132,
        1525.3193413637418
      ],
      "voteCount": 576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 165.62014104853554
      }
    },
    {
      "id": "d63b6f93d25a72e8a6772599",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1533.1019002579787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1526.4989470120881,
        1539.7048535038693
      ],
      "voteCount": 10956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.349592330014847
      }
    },
    {
      "id": "c0d02f023658a8fcba644a27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1528.7454922040545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1523.5815979783367,
        1533.909386429772
      ],
      "voteCount": 22297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.941582565131376
      }
    },
    {
      "id": "36ee021e5c1477ae8dfb12fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1507.2251468016825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1499.467918709251,
        1514.982374894114
      ],
      "voteCount": 7121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.664514572912703
      }
    },
    {
      "id": "ddc79bd17c854776424a05a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1476.489793843515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.6242645244863,
        1484.3553231625433
      ],
      "voteCount": 6969,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.1049628165266
      }
    },
    {
      "id": "afc24c00d6fb8f1e64dab082",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1508.6335246103877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.4832890901785,
        1520.783760130597
      ],
      "voteCount": 2733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.430250091781744
      }
    },
    {
      "id": "e0a3c4a8aa33b25561739d6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1516.5366389744204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1508.22571922966,
        1524.8475587191808
      ],
      "voteCount": 5916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.980509548028483
      }
    },
    {
      "id": "fb4779482a9eed1e7dc5b230",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1521.6334802406366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.3829729941913,
        1535.8839874870819
      ],
      "voteCount": 1934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.864540858021165
      }
    },
    {
      "id": "55cdb8f1fedb414b49a6b9a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1520.2221087519304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.4888460133684,
        1532.955371490492
      ],
      "voteCount": 2558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.20687700615566
      }
    },
    {
      "id": "04b365ccd354efb8b68f134c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1534.3117439907287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1528.3022830907116,
        1540.3212048907455
      ],
      "voteCount": 13769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.401017164179077
      }
    },
    {
      "id": "1bbe8b98eaa3f2fdbabc8991",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1485.1480134013996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.964480745311,
        1492.331546057488
      ],
      "voteCount": 8423,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.433214783691236
      }
    },
    {
      "id": "426adf650747c4d407a53e4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1501.573005672946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.0707325793906,
        1508.0752787665015
      ],
      "voteCount": 11194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.00611964272895
      }
    },
    {
      "id": "9baa401f5cb541f3bcb5a634",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1487.291771061865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.0662398166994,
        1525.5173023070306
      ],
      "voteCount": 276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 380.3740472509083
      }
    },
    {
      "id": "8f29f9363facddd15ee8af6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1449.118283484845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.4356284885052,
        1473.8009384811849
      ],
      "voteCount": 661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.5942961008378
      }
    },
    {
      "id": "e6f370b79d515b5c1f708a6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1517.0897327317377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1510.7215629841469,
        1523.4579024793286
      ],
      "voteCount": 13077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.556819121857162
      }
    },
    {
      "id": "68147be07760976feee7af4a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1505.917700729411,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.0624974577115,
        1518.7729040011109
      ],
      "voteCount": 2230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.0191390485498
      }
    },
    {
      "id": "8a0bc2805c75540f7ebe15bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1512.852912719291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.7016439417841,
        1521.0041814967976
      ],
      "voteCount": 6380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.296341255885174
      }
    },
    {
      "id": "22df3af04c0ea0e3155d8864",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1498.3786384120808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.221964217637,
        1502.535312606525
      ],
      "voteCount": 36512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.497754932495826
      }
    },
    {
      "id": "f69d5018f401f8bb551eedf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1504.1299561016413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.07010844962,
        1514.1898037536625
      ],
      "voteCount": 3954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.344297701880024
      }
    },
    {
      "id": "3f335fda5e3b60037d912d92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1497.491374813613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.638112534767,
        1516.344637092459
      ],
      "voteCount": 1211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.52878011867632
      }
    },
    {
      "id": "32b34c4748bbf2eff071a20d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1545.1606937383315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1526.7135898385284,
        1563.6077976381348
      ],
      "voteCount": 1107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.58500329534814
      }
    },
    {
      "id": "1b7eafeb322400c262e4e9f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1555.1689507557132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1546.4128784676632,
        1563.9250230437633
      ],
      "voteCount": 5578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.95825166744987
      }
    },
    {
      "id": "c57b81935def956937449c56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1484.8566290275655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.6967853764747,
        1496.0164726786563
      ],
      "voteCount": 3245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.42052463139161
      }
    },
    {
      "id": "16ca05e6f3a3bf35e53f951d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1509.3116686662165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.5126573396378,
        1516.1106799927954
      ],
      "voteCount": 9600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.03359379252538
      }
    },
    {
      "id": "6115f1e1d7d01a18eaa56635",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1518.1649623658543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1511.1870391096513,
        1525.1428856220575
      ],
      "voteCount": 15008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.675240121580215
      }
    },
    {
      "id": "7f87dd33736a1faa926d8f34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1523.1863387215194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1509.0748736669009,
        1537.2978037761382
      ],
      "voteCount": 1911,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.83797491593067
      }
    },
    {
      "id": "0c16e960ccf6d988f8afe354",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1516.1182535798268,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.3837923677343,
        1541.8527147919194
      ],
      "voteCount": 625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.3986966381252
      }
    },
    {
      "id": "0e2b4d63949a0a4c492ef7ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1491.8371011217655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.82832948802,
        1524.8458727555108
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 283.6367785329725
      }
    },
    {
      "id": "13963bf5c6269836d44bedc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1529.4129297601858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1521.302940066973,
        1537.5229194533988
      ],
      "voteCount": 6529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.121602988349913
      }
    },
    {
      "id": "deeca2aad8fd26b2528b2671",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1524.48366473854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1518.199555167271,
        1530.7677743098088
      ],
      "voteCount": 12966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.279957419035167
      }
    },
    {
      "id": "cddabfd9a826b87b4ac27bb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1500.4259835496841,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.323507746431,
        1510.5284593529373
      ],
      "voteCount": 3877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.56803629014898
      }
    },
    {
      "id": "72a9c2ae6afb7b5a2c794a3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1479.3456641506546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.29585771126,
        1489.395470590049
      ],
      "voteCount": 4121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.291732954473623
      }
    },
    {
      "id": "eff139882ea85dc9e73d8173",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1507.6077247090186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.7729182271198,
        1523.4425311909176
      ],
      "voteCount": 1555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.2723634491231
      }
    },
    {
      "id": "b30f27c2cb54b90d0dc6da6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1524.638610111526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1514.0923543747563,
        1535.1848658482957
      ],
      "voteCount": 3445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.953456292745205
      }
    },
    {
      "id": "662b01a2f5e44135b831261c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1505.2619275004645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.0066746166374,
        1523.5171803842916
      ],
      "voteCount": 1149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.75200578936867
      }
    },
    {
      "id": "ccd04409b8ad87d8f95daa14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1523.8469011300904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.6390247522622,
        1540.0547775079185
      ],
      "voteCount": 1492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.38424383565064
      }
    },
    {
      "id": "d63d04b9e9d60b286f6bec68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1542.199524858467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1534.7776393606762,
        1549.6214103562577
      ],
      "voteCount": 7960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.339444183437159
      }
    },
    {
      "id": "01425c1733f8dca48361b4d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1492.8829839980287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.536588818556,
        1502.2293791775014
      ],
      "voteCount": 4656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.740085714386016
      }
    },
    {
      "id": "5c0e7b10531466ab926aee83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1504.0009428877645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.9342923835102,
        1512.067593392019
      ],
      "voteCount": 6576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.93909876301338
      }
    },
    {
      "id": "8b64a77e5ded790b4a98216a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1427.5574439761215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6445359537274,
        1477.4703519985153
      ],
      "voteCount": 146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 648.5292446273818
      }
    },
    {
      "id": "959cbecbab476261fe6249d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1465.210727222981,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.9275172324,
        1496.493937213562
      ],
      "voteCount": 388,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.75718288135883
      }
    },
    {
      "id": "03e39cf45a7c4a341e145418",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1515.1989676016021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.575316451273,
        1522.8226187519315
      ],
      "voteCount": 8256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.1296836891286
      }
    },
    {
      "id": "40837458aacccc7b76986c4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1500.4833161282106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.901898105342,
        1518.0647341510792
      ],
      "voteCount": 1161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.46585271972032
      }
    },
    {
      "id": "ee99d705df87ac6eb3391d1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1520.2280234271595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1509.3350539976072,
        1531.1209928567118
      ],
      "voteCount": 3390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.888469337209237
      }
    },
    {
      "id": "1d0b8ac2c5e6b4d375e46894",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1499.6959225834823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.4596624468295,
        1504.9321827201352
      ],
      "voteCount": 19973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.137502052864653
      }
    },
    {
      "id": "7de3cbaf0610fce0bfad71c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1501.7831987522798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.9048954776395,
        1515.6615020269198
      ],
      "voteCount": 2049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.139103599211225
      }
    },
    {
      "id": "30f84a752698c50c4558f57f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7-thinking",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1485.723764295089,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.7706733626649,
        1509.676855227513
      ],
      "voteCount": 681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.35746860701866
      }
    },
    {
      "id": "eefe1fc9343f71ba91d2e1c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1544.6323611235985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1525.1389566237476,
        1564.1257656234495
      ],
      "voteCount": 1031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.91888387499381
      }
    },
    {
      "id": "d4ed80c7dac03c5849688231",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1546.1797239383511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1537.6443125950116,
        1554.7151352816907
      ],
      "voteCount": 5903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.9649948627706
      }
    },
    {
      "id": "9fb784c66d68572b7e2ad88c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1483.7567455395545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.7586596521926,
        1494.7548314269163
      ],
      "voteCount": 3398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.487489214821256
      }
    },
    {
      "id": "cb1fd920a7fef6b3f10a51cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1500.5669513806004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.8480672096389,
        1507.2858355515618
      ],
      "voteCount": 9993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.751630463824457
      }
    },
    {
      "id": "b24b4c75480c530a72b6bd4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1509.4467845284353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.5157671332215,
        1516.3778019236493
      ],
      "voteCount": 15664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.505405986384297
      }
    },
    {
      "id": "38fb2c630ef6b7fc5d49b60a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1530.968434384293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1516.9496819908807,
        1544.9871867777053
      ],
      "voteCount": 2005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.15905905566686
      }
    },
    {
      "id": "23bc063ca83688c72fef6793",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1527.24291429659,
      "unit": "Arena rating",
      "confidenceInterval": [
        1501.9868321960737,
        1552.498996397106
      ],
      "voteCount": 690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.04881448469038
      }
    },
    {
      "id": "d3276fee037567499e3e1145",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1478.0689545031964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.4582380625195,
        1514.6796709438734
      ],
      "voteCount": 266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 348.91550862894945
      }
    },
    {
      "id": "1a74249bbf13026ff3cc7eef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1520.0965091363955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1512.1804030827068,
        1528.0126151900843
      ],
      "voteCount": 6872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.312744188658264
      }
    },
    {
      "id": "d31342d2386bcd93fcf435f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1517.19461638149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1510.9602193577734,
        1523.4290134052064
      ],
      "voteCount": 13563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.117954679077362
      }
    },
    {
      "id": "78f6fe1bb8e1a095d3f6e038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1494.9489681875632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.001420142277,
        1504.8965162328495
      ],
      "voteCount": 4072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.75940983154903
      }
    },
    {
      "id": "a740f6ff5c72918df78081cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1477.0621213712575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.2391821237966,
        1486.8850606187182
      ],
      "voteCount": 4372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.118097046754297
      }
    },
    {
      "id": "347b87c1ae73baba6d53f39c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1487.5098453558053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.3281583846288,
        1502.6915323269818
      ],
      "voteCount": 1647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.99898217030564
      }
    },
    {
      "id": "2b17ccdc8dddc8180ec7924c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1511.4354426541909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.808505726662,
        1522.0623795817198
      ],
      "voteCount": 3466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.3981515181961
      }
    },
    {
      "id": "7d5bc154a3e6a7edf084bc42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1501.198797300037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.4033691371858,
        1518.9942254628884
      ],
      "voteCount": 1186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.43671955905073
      }
    },
    {
      "id": "4c1687509416bf4b3ecb6916",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1516.483175585609,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.439001480128,
        1532.52734969109
      ],
      "voteCount": 1513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.0098352584902
      }
    },
    {
      "id": "1654aebc2a21aed41012c3ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1529.0866171104612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1521.7417520493732,
        1536.4314821715493
      ],
      "voteCount": 8238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.043373958605383
      }
    },
    {
      "id": "9399e079927faf558ee1ce3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1486.787232811968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.5906176524347,
        1495.9838479715013
      ],
      "voteCount": 4958,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.017086305060097
      }
    },
    {
      "id": "99971ec031ed0477ed6a966a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1494.0461026609898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.213399408985,
        1501.8788059129947
      ],
      "voteCount": 6962,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.970818144259836
      }
    },
    {
      "id": "a97617e54ccc0878ece2dc25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1463.2831563268714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.5066051510162,
        1508.059707502727
      ],
      "voteCount": 192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 521.92139205119
      }
    },
    {
      "id": "678cdf7e24ebe484a7f90fe2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1462.5947465025674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.7317551050367,
        1493.4577379000984
      ],
      "voteCount": 377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 247.95898705792982
      }
    },
    {
      "id": "21bd957d5662f6df1abba8ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1507.8510968614617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.336219989734,
        1515.3659737331893
      ],
      "voteCount": 8671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.701022979343797
      }
    },
    {
      "id": "717ee65c9f7bc6740d88f0dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1493.5406410606831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.1854019129844,
        1510.8958802083819
      ],
      "voteCount": 1170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.40883891588645
      }
    },
    {
      "id": "32e5aed6d7b481ecbd8a2e73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1513.4262831724684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.8321463177213,
        1524.0204200272153
      ],
      "voteCount": 3612,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.216956613588657
      }
    },
    {
      "id": "3991f7ac34b5921a1c532213",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1493.6378244509865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.3760178211005,
        1498.8996310808725
      ],
      "voteCount": 20724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.207316361472861
      }
    },
    {
      "id": "0cb45bc79a74deb8790c9035",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1495.1298941067903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.632899482888,
        1508.6268887306924
      ],
      "voteCount": 2196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.42179270445164
      }
    },
    {
      "id": "1d8580ad13a87304af242b0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-opus-4-7",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1468.4878951041076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.7633807071543,
        1491.2124095010608
      ],
      "voteCount": 732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.42902258783732
      }
    },
    {
      "id": "f867fde53fd83be27885f9ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1414.1783687329867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.1388794776071,
        1428.2178579883664
      ],
      "voteCount": 1801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.31052231774391
      }
    },
    {
      "id": "a54dd8cbc565e29551f70c85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1473.074520641687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.3238794777517,
        1480.8251618056227
      ],
      "voteCount": 6414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.637923314048507
      }
    },
    {
      "id": "2d7f2709a2c60593d18f4c88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1395.6008738281228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.2930553916935,
        1404.9086922645522
      ],
      "voteCount": 4312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.552756150560647
      }
    },
    {
      "id": "ef9a862843e652d5de706af4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1416.001285107595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.469267859523,
        1421.5333023556673
      ],
      "voteCount": 16798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.966560689940702
      }
    },
    {
      "id": "d41392f87b5c375c3750fbc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1381.8252423253668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.0249666114207,
        1387.625518039313
      ],
      "voteCount": 25805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.757922426905994
      }
    },
    {
      "id": "66e80d271f5f0ea21dd46c44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1433.265508841651,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.692159332635,
        1447.8388583506667
      ],
      "voteCount": 1653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.28694327473182
      }
    },
    {
      "id": "3627978e09157deaea5a483d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1423.5976077713628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.5128922304839,
        1451.6823233122418
      ],
      "voteCount": 425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.3259669902086
      }
    },
    {
      "id": "bfb6229e7f8a01dd5a34516c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1379.2935445374408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.9984369624308,
        1400.5886521124507
      ],
      "voteCount": 815,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.04932131208109
      }
    },
    {
      "id": "9b6608d073d7b03e99ea0248",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1447.8817568658553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.7869025837492,
        1454.9766111479614
      ],
      "voteCount": 8116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.103604550737668
      }
    },
    {
      "id": "a542c30a9eb16ec977c931e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1430.7902992045013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.1800475028137,
        1436.4005509061888
      ],
      "voteCount": 15621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.193482118493934
      }
    },
    {
      "id": "8562a9d9c262f7ff1f6d8cbc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1382.2709268695032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.0594070104737,
        1390.4824467285328
      ],
      "voteCount": 5875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.55298222435506
      }
    },
    {
      "id": "98c76d461395885b19c00aea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1388.865674071373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.9574889112967,
        1396.7738592314493
      ],
      "voteCount": 6118,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.28011530128821
      }
    },
    {
      "id": "3fc4f1eb97bab507abefa425",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1407.5267497869947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.6503810817703,
        1420.4031184922192
      ],
      "voteCount": 2280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.16091328109655
      }
    },
    {
      "id": "28fce3772f4e7eaa3156b9c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1416.064317771394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.8333543033434,
        1424.2952812394446
      ],
      "voteCount": 5695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.63620613278976
      }
    },
    {
      "id": "fddaf73255c6fabec551568e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1411.5379527059106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.2549716752349,
        1424.820933736586
      ],
      "voteCount": 1909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.929838974404966
      }
    },
    {
      "id": "a0f104367a8abc2f81fe9a75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1416.285513415754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.0691783337882,
        1429.5018484977197
      ],
      "voteCount": 2163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.470099030564754
      }
    },
    {
      "id": "67e0a4d94d69486e2fd3f69c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1443.135454135825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9629687545585,
        1449.3079395170919
      ],
      "voteCount": 11824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.917996667491646
      }
    },
    {
      "id": "3321d81f89a8764506bc12ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1397.4433386778485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.145473132079,
        1404.741204223618
      ],
      "voteCount": 7496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.86422294499748
      }
    },
    {
      "id": "f4a217102e2d762c5848f6a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1414.7860869687077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.8829584259772,
        1421.6892155114383
      ],
      "voteCount": 8555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.40497058584924
      }
    },
    {
      "id": "bf95d814667c1d35a817bc6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1344.5862820351285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.6751482730278,
        1367.4974157972292
      ],
      "voteCount": 736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.64601776728765
      }
    },
    {
      "id": "c306b2a2fa9bf56d349782f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1335.4951781573054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.114280136364,
        1358.8760761782469
      ],
      "voteCount": 684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.30697705797152
      }
    },
    {
      "id": "fc5f6d1e1e0013552a5c7d3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1440.703343034085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.0908685368813,
        1448.3158175312888
      ],
      "voteCount": 6725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.085354464402439
      }
    },
    {
      "id": "282421ee3c88430253c8df6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1402.7414681828436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.9753776740918,
        1415.5075586915952
      ],
      "voteCount": 2023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.42478560480674
      }
    },
    {
      "id": "27084102084cbdf06cce1cfe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1419.5729461433807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.3868864574604,
        1427.759005829301
      ],
      "voteCount": 5922,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.444303403815102
      }
    },
    {
      "id": "0bdb2f5be56a4217c97ff922",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1399.1073863178826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.708032642468,
        1403.5067399932973
      ],
      "voteCount": 35127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.038271569415783
      }
    },
    {
      "id": "8bd4edc8fa932194f9a812d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1404.7159218886236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.5910191488467,
        1417.8408246284007
      ],
      "voteCount": 1948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.84313901807758
      }
    },
    {
      "id": "9ab9f6d7d8f071374de6652f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1398.3654011513706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.5699685807963,
        1421.160833721945
      ],
      "voteCount": 737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.26937820609132
      }
    },
    {
      "id": "3e08eba933709b337593cc95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1407.336958045994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.3561215634688,
        1420.317794528519
      ],
      "voteCount": 2209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.86409529586175
      }
    },
    {
      "id": "ce92b334f8271a490d21dbea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1448.659398993612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.2982835414489,
        1456.0205144457752
      ],
      "voteCount": 7396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.105584161978435
      }
    },
    {
      "id": "f9727ca11ae0ce7591a4f566",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1383.7928126744528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.0323155157068,
        1392.5533098331987
      ],
      "voteCount": 5001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.978428521726702
      }
    },
    {
      "id": "3c73e245857c0e0341de87b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1396.6678102979915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.2665782861116,
        1402.0690423098713
      ],
      "voteCount": 19487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.5943303333093075
      }
    },
    {
      "id": "e7649d944c3128dbb9e2c253",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1368.1722616251684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4275110225908,
        1373.917012227746
      ],
      "voteCount": 29539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.591048616226681
      }
    },
    {
      "id": "4ff5bb6c551d8f9bb047ee2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1399.2973687113843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.0429544697101,
        1412.5517829530584
      ],
      "voteCount": 2049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.73249515093052
      }
    },
    {
      "id": "af4088857c017f42623c803c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1431.1067193093213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.9202752228982,
        1457.2931633957444
      ],
      "voteCount": 529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.50766750311135
      }
    },
    {
      "id": "b784fec7ab76ea9078139b77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1398.4902843946177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.2392920986292,
        1417.741276690606
      ],
      "voteCount": 1022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.47394952765323
      }
    },
    {
      "id": "1cb7e529b20fefe655e469c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1424.233804253068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.3950786469773,
        1431.0725298591585
      ],
      "voteCount": 9266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.174585254814414
      }
    },
    {
      "id": "9304a68e9c352c571bb585c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1417.6344473949978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.1093185315283,
        1423.1595762584673
      ],
      "voteCount": 17676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.9467333590806835
      }
    },
    {
      "id": "e0bbd5d7d89648339fbced01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1387.473072584814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.589479120893,
        1395.356666048735
      ],
      "voteCount": 6652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.17902177411531
      }
    },
    {
      "id": "b2bc4653fe65aa6f413c4344",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1374.173744397093,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.4800509924485,
        1381.8674378017377
      ],
      "voteCount": 6933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.408968563139467
      }
    },
    {
      "id": "7e227ddfda27caad78f8380a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1412.05190143449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.1715235041813,
        1423.9322793647987
      ],
      "voteCount": 2682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.7421301008406
      }
    },
    {
      "id": "a4d2dbf971cbc224e59c933b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1410.7819449578258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.776849612669,
        1418.7870403029829
      ],
      "voteCount": 6442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.6815666849906
      }
    },
    {
      "id": "87656267f1c86e0c9d9b1bcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1390.5273534026296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.2330873298063,
        1402.8216194754527
      ],
      "voteCount": 2326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.346765206781456
      }
    },
    {
      "id": "601e87b19f9b84ec3c4e8430",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1422.3665468526833,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.4466451522364,
        1435.2864485531304
      ],
      "voteCount": 2398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.453247253357425
      }
    },
    {
      "id": "a32661d62002c1248e830e82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1427.089179968792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.0833858661597,
        1433.0949740714243
      ],
      "voteCount": 13742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.389548212492826
      }
    },
    {
      "id": "4c0fa85d1566ec505154baff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1387.4038599912237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.4052812555421,
        1394.4024387269053
      ],
      "voteCount": 8612,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.75039161051957
      }
    },
    {
      "id": "fe617c2cc67b27ef8071e3c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1393.0127671615744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.4382773275547,
        1399.5872569955943
      ],
      "voteCount": 9986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.251953644480203
      }
    },
    {
      "id": "4891ddb28fd27c4004e1eb1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1345.6438991049533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.8437181916952,
        1366.4440800182117
      ],
      "voteCount": 875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.62583987457577
      }
    },
    {
      "id": "e55f8901f9c3152aa3a65b5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1353.6620718661395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.860627526039,
        1374.46351620624
      ],
      "voteCount": 895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.63952233545253
      }
    },
    {
      "id": "0061cc31d1414e0718d4510b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1426.4116259987336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.1443878348623,
        1433.678864162605
      ],
      "voteCount": 7690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.748097531573876
      }
    },
    {
      "id": "708063f6971046fc1d951329",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1388.0869512331114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.4903409977428,
        1399.68356146848
      ],
      "voteCount": 2474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.00789029068867
      }
    },
    {
      "id": "79fce2a5caf48c834478b366",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1408.0265722780387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.2519850172455,
        1415.8011595388318
      ],
      "voteCount": 7154,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.734701293704253
      }
    },
    {
      "id": "a109ec19ad94c36da413222f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1388.82938515576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.4711884235005,
        1393.1875818880194
      ],
      "voteCount": 40323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.944444192595747
      }
    },
    {
      "id": "75387a7b9c9bd93349850c3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1392.2389048637062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.8089540092533,
        1403.668855718159
      ],
      "voteCount": 2626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.008896784581324
      }
    },
    {
      "id": "bf8f1ccee44844e098823fe1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-20250514",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1400.1438162755828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.1923253885443,
        1422.0953071626216
      ],
      "voteCount": 782,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.4387915257336
      }
    },
    {
      "id": "8355175126f4ba1ecb609f4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1484.978390733274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.4149521284448,
        1495.5418293381033
      ],
      "voteCount": 3582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.047880080577077
      }
    },
    {
      "id": "ac02c31a7d11b4de510bb7da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1519.9715559415358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1514.7901898871758,
        1525.1529219958957
      ],
      "voteCount": 17763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.988635162415492
      }
    },
    {
      "id": "c5ac2c7f797cdc1f336fea8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1446.2669442128897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.0883781191944,
        1452.4455103065852
      ],
      "voteCount": 11650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.937547363130236
      }
    },
    {
      "id": "e2d1da43e005262bd8661a74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1472.2822340945404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.4376388241476,
        1476.1268293649334
      ],
      "voteCount": 36624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.847734280920196
      }
    },
    {
      "id": "aa4929438be494a92f6715e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1458.2150789782777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.2720865595736,
        1462.1580713969815
      ],
      "voteCount": 56666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.047209651240616
      }
    },
    {
      "id": "3e4da914065722320ca4e82f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1499.3791688960807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.4260896744856,
        1508.332248117676
      ],
      "voteCount": 5012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.866454982244143
      }
    },
    {
      "id": "27b13d8a89d30b46260f1706",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1471.8962872377904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.9308667911303,
        1488.8617076844505
      ],
      "voteCount": 1676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.92609041685539
      }
    },
    {
      "id": "65c9f349c32293cf1ba0b9b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1455.560722816565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.8669713729248,
        1473.2544742602051
      ],
      "voteCount": 1247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.4973828335215
      }
    },
    {
      "id": "6f2a0d69317777149bc0dff5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1497.5899452785047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.7735949358714,
        1502.4062956211383
      ],
      "voteCount": 21335,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.038651383693232
      }
    },
    {
      "id": "60aa0d94b014e8d4f007618e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1486.2355488575831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.5131575688722,
        1489.9579401462938
      ],
      "voteCount": 43559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.6070143018652425
      }
    },
    {
      "id": "210de6b1790ff5a58b5198c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1456.4226911209985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.807633852989,
        1462.0377483890077
      ],
      "voteCount": 14679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.207524691707423
      }
    },
    {
      "id": "389a93a0df8b9ff7914102d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1442.991188937059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.4250938699117,
        1448.5572840042062
      ],
      "voteCount": 14693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.065012731523208
      }
    },
    {
      "id": "88f55c697fea72b126ad02e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1460.1073711928486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.4871351984082,
        1468.7276071872893
      ],
      "voteCount": 5339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.343814958927847
      }
    },
    {
      "id": "0eb3d42cf4da7fcd97e3a29e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1469.0806840709995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.150241239284,
        1475.011126902715
      ],
      "voteCount": 12347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.155415643344027
      }
    },
    {
      "id": "f05f79f1b3c1ede974c393c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1471.3754062549333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.2789914659804,
        1481.4718210438864
      ],
      "voteCount": 3629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.536166687885473
      }
    },
    {
      "id": "7d6c3ddddcb3e9a6d2b5f9ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1469.9667452916872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.6873700261904,
        1479.2461205571842
      ],
      "voteCount": 4849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.41513168228078
      }
    },
    {
      "id": "f030f4b62d69ce4929e6f425",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1499.8853776600433,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.577234707445,
        1504.1935206126416
      ],
      "voteCount": 27914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.83152275381375
      }
    },
    {
      "id": "b7cd5a8041a1cfa98338d60c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1449.9029498857778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.7484657620519,
        1455.0574340095038
      ],
      "voteCount": 17698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.916306492371029
      }
    },
    {
      "id": "d161afdb0ea2368e4a07818b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1464.53977151013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.7971702509099,
        1469.28237276935
      ],
      "voteCount": 21913,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.855136747214105
      }
    },
    {
      "id": "2a77fc9a18db9708279660da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1398.7077670438482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.3065525411737,
        1423.108981546523
      ],
      "voteCount": 641,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.99821734336572
      }
    },
    {
      "id": "e8e306760c2d56976faba68a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1385.9801057663499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.728961839714,
        1404.231249692986
      ],
      "voteCount": 1211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.7129572849601
      }
    },
    {
      "id": "908c8c5080b87aa2ba3e9ce2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1485.060175761993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.151794411066,
        1489.9685571129198
      ],
      "voteCount": 22126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.271629766363995
      }
    },
    {
      "id": "44eee314813f9d2825152ba0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1454.1107858760715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.30152256759,
        1462.920049184553
      ],
      "voteCount": 4651,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.20147127963667
      }
    },
    {
      "id": "a108a701e2a23a6202dca9a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1470.37110936353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.5159706600762,
        1476.2262480669835
      ],
      "voteCount": 13170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.92438285476345
      }
    },
    {
      "id": "3ff7668d4a5b8e62e917bfed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1454.8848024689005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.0081554084609,
        1457.7614495293399
      ],
      "voteCount": 77813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.1541551521408273
      }
    },
    {
      "id": "88bc4b983c7886934c196525",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1447.290065159226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.959030046803,
        1454.621100271649
      ],
      "voteCount": 7393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.990538055505573
      }
    },
    {
      "id": "e02d3fa164a1c5f7086d21e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929-thinking-32k",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1452.7612076326423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.2344980685928,
        1467.2879171966918
      ],
      "voteCount": 2120,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.93363344712762
      }
    },
    {
      "id": "799f14b7d92df0cddbb3b8c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1480.543190040888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.8265516302536,
        1491.2598284515225
      ],
      "voteCount": 3594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.896543002258735
      }
    },
    {
      "id": "a9463b7fb68c2a84bdfd059e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1514.6375710415018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1509.2890118480693,
        1519.9861302349343
      ],
      "voteCount": 17609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.446932735955302
      }
    },
    {
      "id": "180d1e117abc5d9a9ffe800f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1454.552278688938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.157640091538,
        1460.946917286338
      ],
      "voteCount": 11254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.64475885334893
      }
    },
    {
      "id": "25b499004a6e2f16e594f2d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1469.1427404811195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.180495621532,
        1473.104985340707
      ],
      "voteCount": 36294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.0868287440058895
      }
    },
    {
      "id": "2d2d2157b71f5067d0a04de7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1459.133483739853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.039734803651,
        1463.227232676055
      ],
      "voteCount": 55135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.36260835658977
      }
    },
    {
      "id": "31de3aaa68143a969b52a55f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1487.9636309378163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.123671746339,
        1496.8035901292935
      ],
      "voteCount": 5115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.342500637001187
      }
    },
    {
      "id": "f063b17c5995bd69e9fedbc6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1474.5759674236533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.4013431323358,
        1491.7505917149708
      ],
      "voteCount": 1638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.78533945461233
      }
    },
    {
      "id": "f0443830c6e7c0cdf9b48c27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1442.944727116992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.245391883844,
        1460.64406235014
      ],
      "voteCount": 1243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.54882879591938
      }
    },
    {
      "id": "b9fdd66d762d5315cb16406e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1491.488492553318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.5636480662392,
        1496.413337040397
      ],
      "voteCount": 21582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.3137715003616375
      }
    },
    {
      "id": "1cb2cc538fe269f5505eda54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1483.1170110098592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.2947960231415,
        1486.9392259965769
      ],
      "voteCount": 43125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.803067554958097
      }
    },
    {
      "id": "2d222e5e4ab0aebbb4927822",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1460.9705748749207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.2589806004428,
        1466.6821691493983
      ],
      "voteCount": 14409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.492166824881364
      }
    },
    {
      "id": "2651c169c5e9f839b473188e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1443.4123311930305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.6248357589977,
        1449.199826627063
      ],
      "voteCount": 14195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.71937067723019
      }
    },
    {
      "id": "32bd2992915fb22cbe231526",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1462.0131930853238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.3923745632371,
        1470.6340116074107
      ],
      "voteCount": 5394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.346429432068014
      }
    },
    {
      "id": "f2a7eac27d64571f46020888",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1471.4570509203497,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.4421196938013,
        1477.4719821468984
      ],
      "voteCount": 12283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.418140177687121
      }
    },
    {
      "id": "7437a69489ef9a20b0c36a94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1452.21773766307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.0102778053392,
        1462.4251975208008
      ],
      "voteCount": 3702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.123090890860347
      }
    },
    {
      "id": "791b00af8b9a65fbf3f0acea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1473.3554757238444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.9611986667858,
        1482.749752780903
      ],
      "voteCount": 4777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.973678892340732
      }
    },
    {
      "id": "e73d87bac62b5f7f46685739",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1498.7365531587695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.2954107471057,
        1503.1776955704336
      ],
      "voteCount": 27661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.134441586208468
      }
    },
    {
      "id": "72db9fd1fa49f1a0bf436faf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1453.8800554776133,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.5821635204359,
        1459.1779474347907
      ],
      "voteCount": 17182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.306510495107736
      }
    },
    {
      "id": "e6716bdc65a95cd5f04b57b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1463.471313215634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.5969150018655,
        1468.3457114294024
      ],
      "voteCount": 21466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.185087243000904
      }
    },
    {
      "id": "994d199510fb47a4a4bc26bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1408.0837023055678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.2729684253934,
        1432.894436185742
      ],
      "voteCount": 624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.24446555478252
      }
    },
    {
      "id": "3336e3d8534eb097644063fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1414.4780820374367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.7655219167248,
        1433.1906421581484
      ],
      "voteCount": 1172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.15284651365435
      }
    },
    {
      "id": "c70d00092f9b9b8f00915a01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1484.19710651557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.2141416491927,
        1489.1800713819478
      ],
      "voteCount": 22429,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.463674353553514
      }
    },
    {
      "id": "c0e1ce1a66484ef9cc0797e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1426.5148643786597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.705123751303,
        1435.3246050060166
      ],
      "voteCount": 4673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.203660521675488
      }
    },
    {
      "id": "7b44cb36249892a0e99b82d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1479.1676860343496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.2048857878585,
        1485.1304862808406
      ],
      "voteCount": 13166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.255594928680878
      }
    },
    {
      "id": "ae167bc80522c244792a5b27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1455.1023040675225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.1087497316605,
        1458.0958584033845
      ],
      "voteCount": 76121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.3328032344073457
      }
    },
    {
      "id": "6710c4b30bbf3185d4ffc1d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1451.9639724107792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.513724415383,
        1459.4142204061752
      ],
      "voteCount": 7308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.449249044110394
      }
    },
    {
      "id": "32eeb9b01454eb3d5218d77c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-5-20250929",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1466.9918187309343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.1925129712702,
        1481.7911244905986
      ],
      "voteCount": 1996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.01465541896786
      }
    },
    {
      "id": "6fccc654a3a2022d8d8b514b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1501.7826331670706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.6500636364906,
        1518.9152026976503
      ],
      "voteCount": 1303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.40975796458403
      }
    },
    {
      "id": "4aa6699b63f4975679bd5f73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1521.6479449501767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1513.9544773978578,
        1529.3414125024956
      ],
      "voteCount": 7216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.408063900028537
      }
    },
    {
      "id": "06ec670deaff8b65e8567108",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1449.7153723889608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.0840678719815,
        1459.3466769059398
      ],
      "voteCount": 4266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.147604081832547
      }
    },
    {
      "id": "2c1cb2c15b1143f7ec775a45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1481.2528215752573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.301405546116,
        1487.2042376043987
      ],
      "voteCount": 13083,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.220286980850622
      }
    },
    {
      "id": "81fed5623a3149b99264a958",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1478.7922553706032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.6685536499933,
        1484.9159570912132
      ],
      "voteCount": 20257,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.761844266294728
      }
    },
    {
      "id": "c8c4c26de2f7057038e96201",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1505.2169543414789,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.500592379428,
        1517.9333163035296
      ],
      "voteCount": 2457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.09490953769298
      }
    },
    {
      "id": "7cf76e521feefd9c288b7ece",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1479.9893015931598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.4118468165534,
        1503.5667563697664
      ],
      "voteCount": 738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.7097052682902
      }
    },
    {
      "id": "91da1e847cd334f7c91dda33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1465.2990389738036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.0752577336389,
        1492.5228202139683
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.93042034443235
      }
    },
    {
      "id": "0a7fe3c70028e9e09d11a9a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1505.3516295151321,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.1499265308883,
        1512.5533324993762
      ],
      "voteCount": 8415,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.501257801820337
      }
    },
    {
      "id": "591c5a6741b959390b622d1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1501.23575691791,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.6090407643749,
        1506.8624730714453
      ],
      "voteCount": 16911,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.241643643789702
      }
    },
    {
      "id": "dfc753a7d83497399ef22c71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1478.6000442047857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.9645014425018,
        1487.2355869670696
      ],
      "voteCount": 5308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.412572743850802
      }
    },
    {
      "id": "505289cecfb470a293599c52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1447.814762913229,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.0664222665205,
        1456.5631035599376
      ],
      "voteCount": 5319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.923020821820415
      }
    },
    {
      "id": "e662abf9ef6580dbcbd80316",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1483.7038389954278,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.8563883917848,
        1497.5512895990705
      ],
      "voteCount": 2069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.91642424678726
      }
    },
    {
      "id": "a6851356730eaa337f95ff55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1496.2769634814442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.9550358300378,
        1505.598891132851
      ],
      "voteCount": 4397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.621180961235826
      }
    },
    {
      "id": "1870d217be695a073945c8a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1483.6029891062226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.7292606967997,
        1499.4767175156458
      ],
      "voteCount": 1510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.59363652649854
      }
    },
    {
      "id": "16ce1ef37e6548b95b305f88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1482.487417610972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.8779939471551,
        1496.0968412747886
      ],
      "voteCount": 2041,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.2151237606628
      }
    },
    {
      "id": "6af36c6fa0b119ca0c0c61dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1510.7742018658817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.1798042040623,
        1517.3685995277008
      ],
      "voteCount": 10371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.32019957833356
      }
    },
    {
      "id": "a860e7de4836801065c16073",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1455.1645878184756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.2323512788314,
        1463.0968243581196
      ],
      "voteCount": 6282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.37929220584375
      }
    },
    {
      "id": "b03b2fc73d5e421430f4c3c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1476.9553174947469,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.8876859292866,
        1484.022949060207
      ],
      "voteCount": 8514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.003241288439778
      }
    },
    {
      "id": "dd4959e7abc3fbf92a7267e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1395.9153800587192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.5978282478898,
        1439.2329318695483
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 488.46294662214353
      }
    },
    {
      "id": "a5ceb10145b44217014882bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1442.0939749410957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.491884383316,
        1471.6960654988752
      ],
      "voteCount": 425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 228.11223711950353
      }
    },
    {
      "id": "38261f3969480caacf78b197",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1494.868196806701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.0013121423053,
        1501.735081471097
      ],
      "voteCount": 9992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.2750515351336
      }
    },
    {
      "id": "df378d8bf5f0dd3cdd047b59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1457.7235889115088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.4092886618303,
        1472.0378891611874
      ],
      "voteCount": 1719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.338900975365846
      }
    },
    {
      "id": "8691f6d85b01b0d19b933148",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1480.7772574480243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.880602549884,
        1489.6739123461643
      ],
      "voteCount": 4987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.604273551030854
      }
    },
    {
      "id": "83ab7cd1b23b311d72176e56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1469.5435181735024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.9951225383481,
        1474.0919138086565
      ],
      "voteCount": 27474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.3854287705607105
      }
    },
    {
      "id": "8c4ebb3ac17ad1a824e68331",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1458.5316026173548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.3320624694372,
        1469.7311427652724
      ],
      "voteCount": 3023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.65157987614528
      }
    },
    {
      "id": "99ead72c9b41b5acea9ed26c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "claude-sonnet-4-6",
      "organization": "anthropic",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1469.4031533843358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.6004397826996,
        1491.205866985972
      ],
      "voteCount": 861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.74421868957612
      }
    },
    {
      "id": "cb11a94ca3bc51dab6bde2e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1084.6676649678661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1045.62831487089,
        1123.7070150648422
      ],
      "voteCount": 249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 396.7427290340903
      }
    },
    {
      "id": "140845b2f134c30a4b697fd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1157.7254237810291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.384495396165,
        1178.0663521658932
      ],
      "voteCount": 853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.70735464591314
      }
    },
    {
      "id": "ded8d7609968d59605aee581",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1086.1603715051729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1069.4522876651245,
        1102.8684553452213
      ],
      "voteCount": 1507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.6703262058257
      }
    },
    {
      "id": "b53a180da96d5dcf1d6dfe5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1159.9380240291293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.1712899571776,
        1169.704758101081
      ],
      "voteCount": 5804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.83147650011485
      }
    },
    {
      "id": "29d61023a549a0c93d4c5a01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 981.3717940746296,
      "unit": "Arena rating",
      "confidenceInterval": [
        968.4078707436222,
        994.3357174056372
      ],
      "voteCount": 5094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.74986586524769
      }
    },
    {
      "id": "c3bf4d66003620f899455776",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1144.7285189683798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.607567536726,
        1160.8494704000339
      ],
      "voteCount": 1278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.6527036191896
      }
    },
    {
      "id": "2d0b32ea4d189a61d636ef6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1131.6862594740621,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.9272338201893,
        1146.4452851279352
      ],
      "voteCount": 1540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.70471776977694
      }
    },
    {
      "id": "b789e9254a82006332532472",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1129.1339686751096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.4443116246343,
        1153.8236257255849
      ],
      "voteCount": 639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.6842899333566
      }
    },
    {
      "id": "bb30aba9bdbcb9018b852a64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1079.8963921842392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1063.0316993321699,
        1096.7610850363085
      ],
      "voteCount": 1375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.03902482631534
      }
    },
    {
      "id": "ec893b1fc0adb0300f95f68a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1159.050098627501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.79866026811,
        1191.3015369868922
      ],
      "voteCount": 383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 270.77090365936846
      }
    },
    {
      "id": "5054bac20a6d8940937c1a3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1163.5801929510897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.808124489004,
        1181.3522614131753
      ],
      "voteCount": 1225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.22043555942213
      }
    },
    {
      "id": "4c8dedf31496ed81b7b60e6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1115.2730493503818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1093.8692856409834,
        1136.6768130597802
      ],
      "voteCount": 667,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.25706412882519
      }
    },
    {
      "id": "c3aebd30ece7c632c9bb1a4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1139.4931633830247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.405916254042,
        1171.580410512007
      ],
      "voteCount": 340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 268.0209463055895
      }
    },
    {
      "id": "5ea544746e553b8d7d19f5a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1161.1711691870883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.167372319136,
        1176.1749660550404
      ],
      "voteCount": 1769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.60115413500574
      }
    },
    {
      "id": "c17b0961f73d39d48d71d778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1103.068112064048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.4598211308664,
        1117.6764029972294
      ],
      "voteCount": 2003,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.55237578985962
      }
    },
    {
      "id": "430a655db05eb0200dea3e15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1101.6832339073912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.6336776838064,
        1114.7327901309761
      ],
      "voteCount": 2294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.32975220641129
      }
    },
    {
      "id": "ea897f087cbadc0973fc2944",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1095.8641141261314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.8482556743313,
        1128.8799725779318
      ],
      "voteCount": 320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 283.75858240030226
      }
    },
    {
      "id": "cce74e51e4c29aa49e6e8617",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1108.3613257972947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.0127946739165,
        1127.709856920673
      ],
      "voteCount": 770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.45403350821137
      }
    },
    {
      "id": "ffea17f810dfda1797da12ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1072.4146694090555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.8102914770714,
        1091.0190473410396
      ],
      "voteCount": 1155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.10193637154688
      }
    },
    {
      "id": "ff5eabe89f5a1a09dde5a882",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-34b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1135.6994502815548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.8049910294317,
        1144.5939095336778
      ],
      "voteCount": 7366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.594104760800814
      }
    },
    {
      "id": "47ecc597a1796ac90c3c9a43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1151.7141698856808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.696700363251,
        1173.7316394081104
      ],
      "voteCount": 695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.19397650695821
      }
    },
    {
      "id": "5a3307e18bc86d4a4e350bfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 957.9906523486425,
      "unit": "Arena rating",
      "confidenceInterval": [
        930.0403992110735,
        985.9409054862116
      ],
      "voteCount": 809,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 203.36457760414785
      }
    },
    {
      "id": "ebf26ae3183a4259692f87c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1182.0468685265573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.6997990211103,
        1218.3939380320044
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 343.90827112786315
      }
    },
    {
      "id": "b4c782f1f842daa17533a125",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1158.3680647303108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.5949817696555,
        1189.1411476909666
      ],
      "voteCount": 306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 246.51640928752025
      }
    },
    {
      "id": "f286ae969e311224c374164b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1161.2467421782094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.7643625063051,
        1192.7291218501136
      ],
      "voteCount": 325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 258.0114159929586
      }
    },
    {
      "id": "8f938e177abba8fa4c6641fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1054.1771305469933,
      "unit": "Arena rating",
      "confidenceInterval": [
        1017.1709576554385,
        1091.183303438548
      ],
      "voteCount": 262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.4939508663497
      }
    },
    {
      "id": "12ea2d8256fcc4858704ae98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1095.084023909158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.1061862484867,
        1125.0618615698293
      ],
      "voteCount": 358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.93996727711365
      }
    },
    {
      "id": "669630bacf184e78be45d114",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "codellama-70b-instruct",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1118.2485182257883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.0864671784975,
        1136.410569273079
      ],
      "voteCount": 1143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.86844572364676
      }
    },
    {
      "id": "9629dd42555fde28fd99a98d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1357.3920597139481,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.16856856976,
        1368.615550858136
      ],
      "voteCount": 3028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.79138456075
      }
    },
    {
      "id": "939c00a1df81328c7a2272e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1389.9815457582977,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.7832489922048,
        1396.1798425243908
      ],
      "voteCount": 10219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.001117959040252
      }
    },
    {
      "id": "a9c4fbc5abc685aa1b7fb3b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1336.3720950679601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.2081667133302,
        1343.5360234225902
      ],
      "voteCount": 7623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.359994696233487
      }
    },
    {
      "id": "a10507e2d9c0141fa993d045",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1365.5845500444507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.248512241892,
        1369.9205878470093
      ],
      "voteCount": 28507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.894292690041305
      }
    },
    {
      "id": "8d95ce4a3d91b47db30b7f5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1314.6818425068363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.7385826563077,
        1319.625102357365
      ],
      "voteCount": 38900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.361077676587924
      }
    },
    {
      "id": "2345cc6dd04c4745037595e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1338.8066191394175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.4344066337876,
        1350.1788316450475
      ],
      "voteCount": 2781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.66617301128219
      }
    },
    {
      "id": "922442eca01e7340b2d49e4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1384.237614372863,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.6971978305673,
        1407.7780309151588
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.25540838796832
      }
    },
    {
      "id": "dfe79ce5b935ad4e91e9539f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1358.648178338934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.9531342262371,
        1375.343222451631
      ],
      "voteCount": 1290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.55694019766463
      }
    },
    {
      "id": "1e63b0f69d2fdef3698f2319",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1376.288595748761,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.521770258324,
        1382.0554212391978
      ],
      "voteCount": 12736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.657199722667494
      }
    },
    {
      "id": "a1800a7bb9ddddb830960e42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1367.912166173385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.264134039895,
        1372.560198306875
      ],
      "voteCount": 23789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.623957908275234
      }
    },
    {
      "id": "f0c521d5f5ace050d12082cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1351.3008922841123,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.5124369718458,
        1358.0893475963787
      ],
      "voteCount": 8840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.996256546702298
      }
    },
    {
      "id": "958673768b52b28624820662",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1329.3683638942452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.122605141576,
        1335.614122646915
      ],
      "voteCount": 10073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.154866736147358
      }
    },
    {
      "id": "2bd846f4cc6a940803b86ecd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1376.2140968390065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.9939492343397,
        1386.4342444436734
      ],
      "voteCount": 3479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.190560132648006
      }
    },
    {
      "id": "7985ed9547bf3702fd67a154",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1369.1214140620937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.5886584525201,
        1375.6541696716668
      ],
      "voteCount": 9408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.109554428778079
      }
    },
    {
      "id": "5414ae9cd6fcd186d1c23839",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1325.519611012312,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.9528257027619,
        1335.0863963218621
      ],
      "voteCount": 3637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.82516263508609
      }
    },
    {
      "id": "a3c3bf61e57030e050cbd741",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1374.9236711163185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.8682024706613,
        1385.9791397619756
      ],
      "voteCount": 3067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.81691973806597
      }
    },
    {
      "id": "cde5271c76264d50133eea20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1380.6110917842075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.542418105298,
        1385.679765463117
      ],
      "voteCount": 18202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.687941759226729
      }
    },
    {
      "id": "0921e6e638463830949a3b71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1347.6981534533654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.9546219838421,
        1353.4416849228887
      ],
      "voteCount": 12814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.587402672051832
      }
    },
    {
      "id": "c8084f9dd074d9d66ddd80d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1341.4354750669704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.1566182453996,
        1346.7143318885414
      ],
      "voteCount": 15480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.254100757901694
      }
    },
    {
      "id": "b8ff5790450e4d39c1796e9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1310.5065075284397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.821952459677,
        1329.1910625972023
      ],
      "voteCount": 1114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.88021358889442
      }
    },
    {
      "id": "e764e01d39945ecb4e606a6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1313.1193110171039,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.162705675325,
        1332.0759163588828
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.54594253310836
      }
    },
    {
      "id": "4c18b9cb23e37a28d0365636",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1369.2559620796187,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.1019483375935,
        1375.409975821644
      ],
      "voteCount": 10525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.858724746187253
      }
    },
    {
      "id": "5876fde9584f45d96a14f36e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1309.348105122996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.1580887204018,
        1318.5381215255902
      ],
      "voteCount": 3991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.98550223289709
      }
    },
    {
      "id": "2089413640a29ec49ef0ae6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1360.067884799247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.5105678573655,
        1366.6252017411286
      ],
      "voteCount": 9476,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.193249097101711
      }
    },
    {
      "id": "ce8bfb5c1f812563b11abc50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1353.862126351832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.4193218367984,
        1357.304930866866
      ],
      "voteCount": 56283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.085521277720111
      }
    },
    {
      "id": "a8893ff00091b8e5c976d39e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1342.467810710544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.0154035968044,
        1351.9202178242836
      ],
      "voteCount": 3716,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.258872322814256
      }
    },
    {
      "id": "2417ffa8aef4b2108cee864c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-a-03-2025",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1355.080042623251,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.1523338615652,
        1374.007751384937
      ],
      "voteCount": 1039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.26096560953407
      }
    },
    {
      "id": "6a9eadbfc1674002c559a3c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1260.45583819477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.0455451332605,
        1280.8661312562797
      ],
      "voteCount": 834,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.44319366709558
      }
    },
    {
      "id": "a568eb665ddcf4562dc045b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1280.0466246341816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.5690669218475,
        1293.5241823465155
      ],
      "voteCount": 1783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.285307579184526
      }
    },
    {
      "id": "ff39550005d1b20b792136ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1209.027395431148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.3904067724884,
        1224.6643840898078
      ],
      "voteCount": 1421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.65170778190775
      }
    },
    {
      "id": "b65c80ea0384ee3e767f18b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1261.2045141262124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.8330180595299,
        1269.576010192895
      ],
      "voteCount": 5416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.243576116695102
      }
    },
    {
      "id": "13d020a477f4a2d3ea5937bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1142.507297780237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.7176469338165,
        1153.2969486266572
      ],
      "voteCount": 6414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.305300882185346
      }
    },
    {
      "id": "f1313af924a1f88f83a19a39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1226.2669827014029,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.0214142339132,
        1248.5125511688923
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.82223643161254
      }
    },
    {
      "id": "6008c22a9c59a9f8af85103f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1244.7358422572236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.2433726312981,
        1278.228311883149
      ],
      "voteCount": 275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.0102945268183
      }
    },
    {
      "id": "50e54d9e34707b205e5f4d3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1262.034553118765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.0582993884846,
        1275.0108068490454
      ],
      "voteCount": 1822,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.8331292178701
      }
    },
    {
      "id": "1f0381f1297f4d956181982e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1255.2664637612625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.8670294698036,
        1265.6658980527218
      ],
      "voteCount": 2976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.15290717156083
      }
    },
    {
      "id": "eb4a79e4830b2be40f113710",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1229.701734166535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.1533797607392,
        1247.2500885723312
      ],
      "voteCount": 1152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.16348911317311
      }
    },
    {
      "id": "de9cfedd327061c7f297628e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1214.4730032959844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.1578393300047,
        1228.7881672619642
      ],
      "voteCount": 1593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.345338044221165
      }
    },
    {
      "id": "e96892054c9a371277deaa30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1302.0692804591095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.696727588303,
        1326.4418333299154
      ],
      "voteCount": 569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.63430982006676
      }
    },
    {
      "id": "f4aba65d486c57faf3f654cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1290.0890144265259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.5552553977218,
        1304.62277345533
      ],
      "voteCount": 1620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.98696234082699
      }
    },
    {
      "id": "c694c0fcce19902edd9272c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1223.8230635590878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.3637229905798,
        1238.2824041275958
      ],
      "voteCount": 1361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.42529503370321
      }
    },
    {
      "id": "871d5595f40e38b312660a4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1288.7715847265317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.3001086794147,
        1315.2430607736487
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.4148264555573
      }
    },
    {
      "id": "e2fc2b55f18ce85d66ab3681",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1267.3548821952918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.2413957977978,
        1278.4683685927857
      ],
      "voteCount": 2845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.151738616051055
      }
    },
    {
      "id": "6056d3df50d75751498e233e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1237.3946399739862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.6461052040963,
        1249.1431747438764
      ],
      "voteCount": 2597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.93115940635715
      }
    },
    {
      "id": "a7869f922877cbfa89c3f6fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1233.750641255288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.5096970749164,
        1242.9915854356595
      ],
      "voteCount": 4153,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.229848953402175
      }
    },
    {
      "id": "8dcb91058986c30b6ab54095",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1211.6598140564474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.9770760483966,
        1245.3425520644982
      ],
      "voteCount": 254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 295.3374987666765
      }
    },
    {
      "id": "9b6dc4468a0a6f617ec14c6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1241.636030594108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.581231020323,
        1292.6908301678927
      ],
      "voteCount": 152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 678.5423666336078
      }
    },
    {
      "id": "f05ed8792cff3fc30f5e5d54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1261.2907322026513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.2347572712597,
        1276.3467071340428
      ],
      "voteCount": 1421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.00945232408543
      }
    },
    {
      "id": "257227a89e13ff5de953a764",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1205.4437235293526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.8674351629752,
        1219.02001189573
      ],
      "voteCount": 1601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.980627779768675
      }
    },
    {
      "id": "d1ed2e4eb0c08dcc5a1f4d8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1210.9496318850856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.1947349175105,
        1224.7045288526608
      ],
      "voteCount": 1851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.251391052116496
      }
    },
    {
      "id": "a8684597333b0fc09dfd85a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1249.4375806854605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.8400495569892,
        1256.0351118139315
      ],
      "voteCount": 10140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.330960195814821
      }
    },
    {
      "id": "b9d897f95cf05cc1cf40f388",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1227.8309671849493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.1303897973985,
        1243.5315445725003
      ],
      "voteCount": 1350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.17044716827972
      }
    },
    {
      "id": "b2b1c903b845fe474819b5f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1292.5997096302754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.9462578827474,
        1312.2531613778028
      ],
      "voteCount": 845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.54986493974843
      }
    },
    {
      "id": "d4392628711bd84c9c6867b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1279.1649228857063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.2906616024568,
        1293.0391841689561
      ],
      "voteCount": 1675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.10990228995776
      }
    },
    {
      "id": "d4dd516ff6810b71256d1e91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1263.1339022979055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.0742146854336,
        1278.1935899103773
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.038558415227264
      }
    },
    {
      "id": "4e8eff5a2f74583786529fe3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1285.9462723086976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.5669748357925,
        1294.325569781603
      ],
      "voteCount": 5305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.27759437669824
      }
    },
    {
      "id": "878b9ff9e787f7f651337c36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1189.602950916556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.176019092571,
        1200.029882740541
      ],
      "voteCount": 6203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.301984307718577
      }
    },
    {
      "id": "017a3a0bd4111a2fd8142f64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1245.9977854220647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.3559653095772,
        1270.6396055345522
      ],
      "voteCount": 524,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.06997466303028
      }
    },
    {
      "id": "e579ecf09acb2ed76b413bb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1260.5807086662198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.0570862328568,
        1294.1043310995824
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.5537701980605
      }
    },
    {
      "id": "4408d922be0f2431768ca218",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1269.6289694753477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.3303406685072,
        1282.9275982821878
      ],
      "voteCount": 1735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.03811635033147
      }
    },
    {
      "id": "c8d05e6644f8c0688507193d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1259.8362326351573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.2182909299736,
        1270.454174340341
      ],
      "voteCount": 2822,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.348404165454234
      }
    },
    {
      "id": "77a4541077a9d32202b80a54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1271.4384620429296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.2552657637139,
        1288.6216583221449
      ],
      "voteCount": 1132,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.86200689682089
      }
    },
    {
      "id": "388436405544ae9e7ecea9ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1257.6002033354252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.8164420541818,
        1272.383964616669
      ],
      "voteCount": 1450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.89494742034001
      }
    },
    {
      "id": "0e02596c0cbe3f6f8da85369",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1320.0256831931947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.610241429712,
        1343.4411249566772
      ],
      "voteCount": 592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.72778612786888
      }
    },
    {
      "id": "e35881e22682199cb42dde83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1302.2743884674628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.7386662226218,
        1316.8101107123039
      ],
      "voteCount": 1639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.00181859062232
      }
    },
    {
      "id": "ae70de79f2bf704db822e8d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1246.1235802818112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.2053103410553,
        1261.0418502225673
      ],
      "voteCount": 1243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.934963880479714
      }
    },
    {
      "id": "e350677a75f82733cd99bca6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1300.4873664965553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.7091069437997,
        1325.2656260493109
      ],
      "voteCount": 547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.82525783076898
      }
    },
    {
      "id": "f2a3077f315d2dacc30bd6ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1272.928126133578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.825337063557,
        1284.0309152035989
      ],
      "voteCount": 2714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.08987285489081
      }
    },
    {
      "id": "ce9651025abc510107d53077",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1276.2841656723976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.9722557027449,
        1287.5960756420504
      ],
      "voteCount": 2672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.310081699225236
      }
    },
    {
      "id": "e72a2e2ba3d30932d706b0ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1252.2868457510544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.9660047034738,
        1261.6076867986353
      ],
      "voteCount": 4024,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.61590762505365
      }
    },
    {
      "id": "a53becd6c88235c689bc6038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1215.3329027917664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.4113576806217,
        1253.2544479029114
      ],
      "voteCount": 210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 374.34830118958666
      }
    },
    {
      "id": "6368a53030d1a93c3125d07a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1280.1048550758849,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.689861938909,
        1295.5198482128608
      ],
      "voteCount": 1369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.85723302119861
      }
    },
    {
      "id": "47b3decade755d10bf262847",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1230.4267171261524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.515309648746,
        1244.3381246035588
      ],
      "voteCount": 1467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.37858455227971
      }
    },
    {
      "id": "68e1a41bdf1e0ed7bbea6144",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1249.0444759110214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.4406932177792,
        1262.6482586042637
      ],
      "voteCount": 1826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.17516266685326
      }
    },
    {
      "id": "1b9e4b84e8d1280d5e1c2eaf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1275.737507406886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.1639783218484,
        1282.3110364919232
      ],
      "voteCount": 9866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.248665324499152
      }
    },
    {
      "id": "7cee03a4a534366488141e45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus-08-2024",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1268.593682080916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.5301995390098,
        1283.6571646228226
      ],
      "voteCount": 1354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.068316720708715
      }
    },
    {
      "id": "735798212724adcb2e586da5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1266.2540424725375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.4450770676563,
        1276.0630078774184
      ],
      "voteCount": 10474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.046683253724822
      }
    },
    {
      "id": "d2c154928cca0bd7d22f96a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1271.3925039622932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.636775332127,
        1279.1482325924592
      ],
      "voteCount": 13937,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.658459296957721
      }
    },
    {
      "id": "77c5349b45265add8843caf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1236.1873952654655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.5219629266535,
        1244.8528276042773
      ],
      "voteCount": 11012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.54718796255622
      }
    },
    {
      "id": "4b0fb068c233757aa9242b89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1270.5634208499707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.2726273264002,
        1275.8542143735413
      ],
      "voteCount": 42376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.286944209387186
      }
    },
    {
      "id": "f2ab81334c7f7518d1455913",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1170.5322568519389,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.133296247082,
        1176.9312174567958
      ],
      "voteCount": 51313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.659152872322503
      }
    },
    {
      "id": "1979e3862553cb4352182764",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1237.3563504427323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.9423597908228,
        1249.7703410946415
      ],
      "voteCount": 4031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.11683349968783
      }
    },
    {
      "id": "6e32a40220512c6c5b346d17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1279.3340864265338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.5741569492857,
        1302.094015903782
      ],
      "voteCount": 1226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.8483516258825
      }
    },
    {
      "id": "9019bbd75f58690471e10da8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1252.5140843762144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.4653277607404,
        1267.5628409916885
      ],
      "voteCount": 2864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.95288385021641
      }
    },
    {
      "id": "de7846beb3acae650cfe03d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1256.5978947763774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.9486177034787,
        1264.2471718492761
      ],
      "voteCount": 13980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.23156760727759
      }
    },
    {
      "id": "728b59091458831323578cb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1250.617493482745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.184182853598,
        1257.0508041118924
      ],
      "voteCount": 22394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.773898037938393
      }
    },
    {
      "id": "8f3fc6a235dff85ffbc7055f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1260.0996849726816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.5821126375176,
        1269.6172573078456
      ],
      "voteCount": 8504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.58067270358279
      }
    },
    {
      "id": "4296e3e988fc056a10cf9172",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1236.8753021089087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.486978782231,
        1245.2636254355866
      ],
      "voteCount": 11264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.316991413218126
      }
    },
    {
      "id": "40b07e5af60bfa4140222fae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1313.4549205317849,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.0604548806446,
        1325.8493861829254
      ],
      "voteCount": 4403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.99073944245556
      }
    },
    {
      "id": "052998a77d9c8a666c0abd8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1287.9039732342596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.533365596525,
        1296.2745808719942
      ],
      "voteCount": 13227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.239704106014464
      }
    },
    {
      "id": "b9cbc0d942b30393bea52a16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1219.4843935216215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.6829252708344,
        1228.2858617724087
      ],
      "voteCount": 8796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.16573572318414
      }
    },
    {
      "id": "ab4d29b12f0b5217a1c778d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1285.908354965265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.0982732920925,
        1298.7184366384377
      ],
      "voteCount": 4198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.71767579268239
      }
    },
    {
      "id": "7ee3794b51164f766bf67538",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1270.1935750995176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.5668914031753,
        1276.8202587958601
      ],
      "voteCount": 22666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.431317856333493
      }
    },
    {
      "id": "17716a8062ee97f0328ced07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1258.514747914163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.364289636023,
        1265.6652061923032
      ],
      "voteCount": 19567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.309801295276003
      }
    },
    {
      "id": "accd7013c9b3d0aad606ba70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1239.0415078011345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.9575381282598,
        1245.1254774740091
      ],
      "voteCount": 28069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.635580832223958
      }
    },
    {
      "id": "4921a81cda800d4ea4f8e327",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1219.0274848940592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.3705804580136,
        1237.6843893301048
      ],
      "voteCount": 1487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.61143158963849
      }
    },
    {
      "id": "f8c399f982080e42bca9a211",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1213.1423353604737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.4120441889245,
        1232.8726265320227
      ],
      "voteCount": 1919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.33764485955516
      }
    },
    {
      "id": "78dd3ea44c09bd5e4eeb768f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1259.913515411666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.8444839098947,
        1268.982546913437
      ],
      "voteCount": 9149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.410442287457506
      }
    },
    {
      "id": "f941a604e9838ed4a5bfe572",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1212.7231097856384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.2861918570184,
        1221.1600277142586
      ],
      "voteCount": 9769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.5298313627139
      }
    },
    {
      "id": "e4d6870447740ef67f507bb0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1236.0581529427284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.5962998018667,
        1244.5200060835898
      ],
      "voteCount": 12101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.639522618797596
      }
    },
    {
      "id": "9d48de3e2ad1999472cd9fda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1260.9682025952372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.645700406558,
        1265.2907047839165
      ],
      "voteCount": 77554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.863783797573206
      }
    },
    {
      "id": "e204a58b0ccecdce439a0ee0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1256.8855141824442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.3987001426476,
        1266.3723282222409
      ],
      "voteCount": 7778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.428505894908515
      }
    },
    {
      "id": "2e5bd9a0e58f3138be391d26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r-plus",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1248.340363536867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.4951150773315,
        1271.1856119964025
      ],
      "voteCount": 1174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.8612447871042
      }
    },
    {
      "id": "90a0748bb10c6fe94addcd32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1236.6268398116258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.8362447084178,
        1247.4174349148338
      ],
      "voteCount": 8202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.310605453878043
      }
    },
    {
      "id": "3b8c36377770f4409a10ef36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1241.7927971455038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.0620921318693,
        1250.5235021591384
      ],
      "voteCount": 9645,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.842776818138347
      }
    },
    {
      "id": "88534ac8f97e28e9a7124120",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1194.8024498297573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.0091407415694,
        1204.5957589179452
      ],
      "voteCount": 7836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.96679188128171
      }
    },
    {
      "id": "0b10334f4b9ba67e97eb3ba7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1236.584430428211,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.672134318314,
        1242.4967265381079
      ],
      "voteCount": 29623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.099471560855068
      }
    },
    {
      "id": "81c13f70bf1258325f754711",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1115.3973756718262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1108.1599579887966,
        1122.634793354856
      ],
      "voteCount": 35666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.635500772898062
      }
    },
    {
      "id": "e98bbecdbd5a1bd0d577f905",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1209.5371444672228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.6851183096787,
        1223.3891706247668
      ],
      "voteCount": 2830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.949417038034085
      }
    },
    {
      "id": "1df3745130f42822ed44bc7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1238.1815770053677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.801573168364,
        1263.5615808423713
      ],
      "voteCount": 843,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.68228551514775
      }
    },
    {
      "id": "b64fc5a4c69bbc502fedf146",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1193.398276642647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.0294960210201,
        1211.767057264274
      ],
      "voteCount": 1361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.83436638909144
      }
    },
    {
      "id": "992435ed2c1708513d6a9a55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1222.0346604255199,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.3736506154778,
        1230.695670235562
      ],
      "voteCount": 9264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.527240673658838
      }
    },
    {
      "id": "e0439f53ac4b62bdcd8e3a75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1213.3819876399268,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.1534756483438,
        1220.6104996315098
      ],
      "voteCount": 15124,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.601964267058996
      }
    },
    {
      "id": "7172daa081ee2e7e4b9548b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1224.3470142573315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.7805327674046,
        1234.9134957472588
      ],
      "voteCount": 5984,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.06461745092905
      }
    },
    {
      "id": "cb69a032c322df6fc0cb8d5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1193.4188016421558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.0676979049317,
        1202.76990537938
      ],
      "voteCount": 7973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.763003636344468
      }
    },
    {
      "id": "b852bdd0ed41b5437d44a448",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1281.982578147707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.1314142878,
        1295.8337420076143
      ],
      "voteCount": 3073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.94319846420546
      }
    },
    {
      "id": "86c00ace518aaa0b4bf8e118",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1248.9330459724447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.6123602022121,
        1258.2537317426772
      ],
      "voteCount": 9216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.615154107448546
      }
    },
    {
      "id": "8ca2653c44d8032e9fc3bb29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1187.618559638719,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.603448956176,
        1197.633670321262
      ],
      "voteCount": 5906,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.110508185914245
      }
    },
    {
      "id": "e46d020bf59b22f2441bcae2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1246.3650409599384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.1437523837199,
        1260.5863295361569
      ],
      "voteCount": 2900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.64798041790295
      }
    },
    {
      "id": "c2c5823d215335c7dc5043fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1239.2959333605895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.8268198864594,
        1246.76504683472
      ],
      "voteCount": 15749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.52251831749523
      }
    },
    {
      "id": "4be56f41a8a273f1b8dc79bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1207.378982737649,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.486384441128,
        1215.2715810341706
      ],
      "voteCount": 13537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.216003028504296
      }
    },
    {
      "id": "f042f489274b3984abb6a00c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1197.1961602661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.4326563113907,
        1203.959664220809
      ],
      "voteCount": 19085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.90823275234301
      }
    },
    {
      "id": "4f77ee4efc2ce7b3b9016564",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1163.7222108359078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.344103643831,
        1186.100318027985
      ],
      "voteCount": 856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.36185076418417
      }
    },
    {
      "id": "b3fb3fd6513528e527dc760a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1180.2737953785968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.5158792532627,
        1202.031711503931
      ],
      "voteCount": 1154,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.23623295577472
      }
    },
    {
      "id": "b4a35315ac69e60059785799",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1230.79323796804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.698063715567,
        1240.8884122205134
      ],
      "voteCount": 6160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.52964614348814
      }
    },
    {
      "id": "3f36d5313a4feffa6da6ff7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1175.058104549734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.594614391415,
        1184.521594708053
      ],
      "voteCount": 6682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.313446832788784
      }
    },
    {
      "id": "674bb8d8348870a8b3493d9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1195.7689245310078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.2795579336885,
        1205.2582911283268
      ],
      "voteCount": 8273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.441115113149976
      }
    },
    {
      "id": "c14e4e71b13a842d4b7707c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1225.9296877947986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.1473621964012,
        1230.7120133931958
      ],
      "voteCount": 54036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.953633553451411
      }
    },
    {
      "id": "684d52e12474fba7d8c97ef3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1212.9191251369855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.298439099957,
        1223.5398111740142
      ],
      "voteCount": 5283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.363577006079268
      }
    },
    {
      "id": "b2f092cb5e7259be87ae108b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "command-r",
      "organization": "cohere",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1217.2898140022614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.3968612011777,
        1244.1827668033452
      ],
      "voteCount": 698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.26985895702884
      }
    },
    {
      "id": "429390c6c025b354f124c69f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1176.9244684625355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.8261301558261,
        1190.022806769245
      ],
      "voteCount": 5019,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.66180021839
      }
    },
    {
      "id": "d3fe882ee489b86165b49b9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1249.5532074181497,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.6249656231455,
        1260.4814492131538
      ],
      "voteCount": 5502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.08883221309553
      }
    },
    {
      "id": "c5e494c37329f98997c5dbd1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1162.9073319182517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.163952151053,
        1174.65071168545
      ],
      "voteCount": 4808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.89963469443805
      }
    },
    {
      "id": "ffdc872524bc434f2cfc04ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1224.8871277848457,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.266029358307,
        1232.5082262113847
      ],
      "voteCount": 18053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.119553257764025
      }
    },
    {
      "id": "8b8aee36143fb6330a27818b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1067.0171165936622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1057.6108203943106,
        1076.423412793014
      ],
      "voteCount": 21404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.032502057109173
      }
    },
    {
      "id": "63f0da1f0e5698e48dd0e09f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1185.236520145147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.0354434117367,
        1201.4375968785573
      ],
      "voteCount": 1678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.32687777567283
      }
    },
    {
      "id": "e4ed00ed34c5f3f661576df6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1190.4146248096713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.0625603674732,
        1220.7666892518694
      ],
      "voteCount": 538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 239.8171785522043
      }
    },
    {
      "id": "800c35d0dbb1b4a76e0488f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1139.4790141976746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.1600456709298,
        1162.7979827244194
      ],
      "voteCount": 742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.55411226120026
      }
    },
    {
      "id": "42591f5d33a18c8ba4df3a4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1235.9504060600943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.1397340415278,
        1246.7610780786606
      ],
      "voteCount": 5516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.423501838266628
      }
    },
    {
      "id": "324b56e37a819df2f4a92d10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1215.6299151371613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.537555816844,
        1224.7222744574788
      ],
      "voteCount": 8865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.520729980082137
      }
    },
    {
      "id": "26d9a6cea39b27f85a0a1a38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1175.7396679151639,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.3805441845557,
        1189.0987916457716
      ],
      "voteCount": 3376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.45792007148086
      }
    },
    {
      "id": "c3110f8787b7744e2c138456",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1169.308857702768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.8024635999986,
        1180.8152518055372
      ],
      "voteCount": 4630,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.46531940808858
      }
    },
    {
      "id": "cc202e6338cda1b1e0b2c583",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1210.2357865046188,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.383064110516,
        1227.0885088987216
      ],
      "voteCount": 1748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.93395721508162
      }
    },
    {
      "id": "20ee9c706206c6aea97edc72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1212.106012458145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.4711408469566,
        1223.7408840693329
      ],
      "voteCount": 5642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.23927854688589
      }
    },
    {
      "id": "9d940612f248118e4b15b541",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1189.7704938008144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.7479576137953,
        1201.7930299878335
      ],
      "voteCount": 3599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.62668900406539
      }
    },
    {
      "id": "85b18a20b642aa9fc04d7294",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1201.9236741472434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.109196587293,
        1219.738151707194
      ],
      "voteCount": 1705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.61330539959656
      }
    },
    {
      "id": "9ccdd4d19459fd139ed220f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1223.9792191402594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.6480740470392,
        1233.31036423348
      ],
      "voteCount": 9343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.66593833615464
      }
    },
    {
      "id": "f40323ecbf3b6c087b539bb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1174.9385080018947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.076039937421,
        1184.800976066368
      ],
      "voteCount": 7999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.320660942341295
      }
    },
    {
      "id": "ac05b7f6416170671a824efd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1184.71103415896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.1715148888259,
        1193.2505534290942
      ],
      "voteCount": 11274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.983254218983415
      }
    },
    {
      "id": "90708f99f5e6a7bc38eb1dcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1079.3354580198393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1048.7275276223204,
        1109.9433884173582
      ],
      "voteCount": 426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 243.87750772506718
      }
    },
    {
      "id": "618f442a8b55ac515cf78569",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1110.666123309672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.0538456787422,
        1141.2784009406014
      ],
      "voteCount": 442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 243.9467883151181
      }
    },
    {
      "id": "d3c165ea86127659ff53d328",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1185.9078472211033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1173.258740089278,
        1198.5569543529286
      ],
      "voteCount": 3489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.650820352535746
      }
    },
    {
      "id": "90804929304c8981b520f3a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1195.227520319832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.76845988512,
        1206.686580754544
      ],
      "voteCount": 4001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.18234378538907
      }
    },
    {
      "id": "a4efb175d0c74f03c0f91145",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1173.2927813614206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.5403748680747,
        1185.045187854766
      ],
      "voteCount": 4918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.954845497960235
      }
    },
    {
      "id": "ce12dcff05319fb96389ae0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1194.1934448724755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.079302840769,
        1200.3075869041822
      ],
      "voteCount": 32191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.731389695627573
      }
    },
    {
      "id": "19d37b285ce676b783671f47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1157.5479035160702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.5009189010093,
        1170.5948881311315
      ],
      "voteCount": 3044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.312282258145196
      }
    },
    {
      "id": "1c9e739f8986b1e71af4bc2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dbrx-instruct-preview",
      "license": "DBRX LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1149.784196158158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.850345939377,
        1182.7180463769391
      ],
      "voteCount": 404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 282.350674798363
      }
    },
    {
      "id": "9f7bc2e57d43bda1dfa5ac62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1288.6891919440895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.7311809604553,
        1303.6472029277236
      ],
      "voteCount": 1712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.244042961285935
      }
    },
    {
      "id": "ebaf663111de09b3d2b7b892",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1341.941946677999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.0739662952726,
        1353.8099270607258
      ],
      "voteCount": 2671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.66548697750511
      }
    },
    {
      "id": "479db50752673888e0657665",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1203.3764051205364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.1644305824955,
        1216.5883796585777
      ],
      "voteCount": 2271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.440099540701105
      }
    },
    {
      "id": "8900ddd8812e1da62500a615",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1269.2395190901616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.372080618169,
        1277.1069575621543
      ],
      "voteCount": 8140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.112781888262923
      }
    },
    {
      "id": "32389cdabfefe0074686903b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1176.0082809647674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.6213252133257,
        1185.3952367162092
      ],
      "voteCount": 9900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.937884379977003
      }
    },
    {
      "id": "29c1a84554985930b7fd58dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1262.972481199317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.4941706180723,
        1284.4507917805618
      ],
      "voteCount": 769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.08922832629875
      }
    },
    {
      "id": "20905474a3204a1ce479db15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1261.8093277391013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.610586642078,
        1304.0080688361245
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 463.5566417061942
      }
    },
    {
      "id": "02ad18c89158bbca5238cdcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1234.9817796403208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.8596536522177,
        1261.103905628424
      ],
      "voteCount": 516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.6318575803538
      }
    },
    {
      "id": "9d8cb4b9b4c5ab4764cb327a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1297.8616484082472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.0689535701572,
        1309.654343246337
      ],
      "voteCount": 2699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.201781155416235
      }
    },
    {
      "id": "4796db6f395b77577802e6c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1287.4981055116018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.7361015871152,
        1297.2601094360884
      ],
      "voteCount": 4439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.807429955600593
      }
    },
    {
      "id": "d83f040b3d390fa23fff0a7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1251.7830090214406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.3714748868301,
        1266.1945431560512
      ],
      "voteCount": 1796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.06600091459903
      }
    },
    {
      "id": "920380271856c9f6b1ff4fe4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1211.2797480917316,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.9062665951228,
        1223.6532295883403
      ],
      "voteCount": 2513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.855443333701416
      }
    },
    {
      "id": "f8974c393cc811d4cdfb694e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1276.791916172234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.4851921040108,
        1297.0986402404574
      ],
      "voteCount": 888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.34542829446443
      }
    },
    {
      "id": "4de274cd2311b9e7f42011d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1269.7163445538708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.984896167165,
        1282.4477929405766
      ],
      "voteCount": 2552,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.19484981855517
      }
    },
    {
      "id": "a4682e3062c0bbe95cabcead",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1269.8870856554022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.0057734195527,
        1283.7683978912514
      ],
      "voteCount": 1669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.16084731954022
      }
    },
    {
      "id": "5a5ffefb4ed44c24819a4b3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1255.8383242276132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.3392530631409,
        1276.3373953920852
      ],
      "voteCount": 847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.38863026264661
      }
    },
    {
      "id": "36b08ed2e2f56f8df3e7ccbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1324.8990125623573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.8252950736637,
        1334.9727300510508
      ],
      "voteCount": 4344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.416991247005683
      }
    },
    {
      "id": "474e53b424f284ee4025505c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1240.3076679183614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.6283792149611,
        1250.9869566217621
      ],
      "voteCount": 3882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.688514841341153
      }
    },
    {
      "id": "d16eb263036272e31d5ba80d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1250.6496361912345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.5980054161464,
        1259.7012669663225
      ],
      "voteCount": 5614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.328360790215388
      }
    },
    {
      "id": "e1c45d41503daa50944853a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1193.8756962125399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.9465656194898,
        1224.8048268055898
      ],
      "voteCount": 345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 249.0228748746769
      }
    },
    {
      "id": "6d001bcde0cf70f719df95f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1203.2156125430079,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.810680008402,
        1234.6205450776133
      ],
      "voteCount": 399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.7435533058562
      }
    },
    {
      "id": "c081c06c58813ae2e1bfb758",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1285.8341903831847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.8470952826715,
        1299.821285483698
      ],
      "voteCount": 1842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.92826410031693
      }
    },
    {
      "id": "28dadc7f199e485d06fb7a2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1270.8859903099844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.4023997213667,
        1284.3695808986022
      ],
      "voteCount": 1858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.32764911654268
      }
    },
    {
      "id": "3e14602c27235f8679279d96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1235.0494079501657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.6750436467078,
        1247.4237722536236
      ],
      "voteCount": 2683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.86113064385862
      }
    },
    {
      "id": "7c3a39394486261e296e5f16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1264.0039788826011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.7244229303026,
        1270.2835348349
      ],
      "voteCount": 15147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.265064601401525
      }
    },
    {
      "id": "115799df995ef8908db9f6af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1256.7544445618532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.6967134903725,
        1270.812175633334
      ],
      "voteCount": 1823,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.44394671458886
      }
    },
    {
      "id": "923b8c064fee4c98b31253a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-coder-v2",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1223.403979260699,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.1522250580047,
        1260.6557334633935
      ],
      "voteCount": 245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 361.24119922941725
      }
    },
    {
      "id": "aa810b0ef06bb437aa9e765a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1233.0461347668518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.3321122720404,
        1274.7601572616632
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 452.9684564946613
      }
    },
    {
      "id": "25711ff6a666f8469492f8f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1216.4314515486583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.8561059515282,
        1240.0067971457884
      ],
      "voteCount": 649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.6838156978318
      }
    },
    {
      "id": "9ffd401bc67cd09f6792e877",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1134.1022704023983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.3768740361077,
        1155.8276667686887
      ],
      "voteCount": 789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.86812622584502
      }
    },
    {
      "id": "c4266a9289bd5fbda12c5daa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1204.5144329884831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.7881595950425,
        1217.240706381924
      ],
      "voteCount": 3820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.160554634120246
      }
    },
    {
      "id": "9497e262398ce9642873f3d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1054.6853825964783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1037.9073862171667,
        1071.4633789757897
      ],
      "voteCount": 3443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.27975533350202
      }
    },
    {
      "id": "24b3ea9450dcbc7c22744e90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1188.7131671172347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.8112878845309,
        1208.6150463499382
      ],
      "voteCount": 946,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.10791172858475
      }
    },
    {
      "id": "17c136172585cd3298e29d6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1173.8850738895637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.400872142947,
        1192.3692756361804
      ],
      "voteCount": 1120,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.94165736439953
      }
    },
    {
      "id": "59837ab48d7b9c0b2e83fa96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1161.8134779643356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.66344278223,
        1189.963513146441
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.2821750125121
      }
    },
    {
      "id": "5bc9afc8c179416b7cdd3472",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1139.6524246888416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.3879951326835,
        1160.9168542449995
      ],
      "voteCount": 802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.70943942257307
      }
    },
    {
      "id": "217dca624e09b32c41c37584",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1202.3603509338088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.446824948121,
        1237.2738769194966
      ],
      "voteCount": 300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 317.3154662459815
      }
    },
    {
      "id": "abe7aab56ea240de8c1f6874",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1181.3274999228138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.6695028759495,
        1202.9854969696785
      ],
      "voteCount": 876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.10695414853708
      }
    },
    {
      "id": "183b6f45e01a03bd32b9a1d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1148.3860631590796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.8674538981454,
        1174.9046724200139
      ],
      "voteCount": 484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.0649943052211
      }
    },
    {
      "id": "1e3d9578e4752720cc41f392",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1208.024467104632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.1711650434324,
        1236.877769165832
      ],
      "voteCount": 385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 216.7179393802288
      }
    },
    {
      "id": "d35e5c1144ebd6efdff83577",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1205.4543014738802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.8855472325629,
        1224.0230557151976
      ],
      "voteCount": 1219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.75721208229393
      }
    },
    {
      "id": "bf31e7bcbc82d26847c486d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1168.9508445902609,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.1980536166716,
        1187.7036355638502
      ],
      "voteCount": 1142,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.54521386632844
      }
    },
    {
      "id": "a98cc3646da097ba9bb20785",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1154.997953979764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.12180600294,
        1171.8741019565875
      ],
      "voteCount": 1525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.13963908747276
      }
    },
    {
      "id": "abaf636c8d31a35f91cd789b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1181.4485525266257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.7105647076366,
        1218.1865403456145
      ],
      "voteCount": 243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 351.3456246666998
      }
    },
    {
      "id": "a2e03ce7e996582d3ee35c27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1155.151673779223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.669428860483,
        1178.6339186979633
      ],
      "voteCount": 576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.54333917447897
      }
    },
    {
      "id": "41c8110a84172efe0b43b9b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1150.9195340974811,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.565276881359,
        1175.2737913136034
      ],
      "voteCount": 620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.4022394184776
      }
    },
    {
      "id": "5c91542fb8fc2baaa8f5d6b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-llm-67b-chat",
      "organization": "deepseek",
      "license": "DeepSeek License",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1183.5284730576773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.032751681262,
        1195.0241944340924
      ],
      "voteCount": 4932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.401412622793835
      }
    },
    {
      "id": "cd807e578c9f4301b44b3b1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1447.4984798843718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.4181624835462,
        1466.5787972851972
      ],
      "voteCount": 1011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.7709006159442
      }
    },
    {
      "id": "05f52ad8ffda4aaee545fb0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1464.6469324521483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.361523373012,
        1475.9323415312847
      ],
      "voteCount": 2728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.15419064167911
      }
    },
    {
      "id": "e98a6029937024e5ce4762fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1394.4870669126615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.993726478088,
        1406.9804073472349
      ],
      "voteCount": 2435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.631323280966974
      }
    },
    {
      "id": "564d21cb88a24a425c4d43c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1431.905999706635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.7389495526904,
        1439.0730498605792
      ],
      "voteCount": 8887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.37164090694908
      }
    },
    {
      "id": "d0c1dcb92692c8b7991bffc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1412.9618901239683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.0786384577848,
        1420.845141790152
      ],
      "voteCount": 13300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.17761890290361
      }
    },
    {
      "id": "c36c1ed936f3a1692d5710c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1420.513064370755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.8920605192925,
        1440.1340682222176
      ],
      "voteCount": 881,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.2181228821663
      }
    },
    {
      "id": "299945ce0cf70a7b01fcbda5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1422.2635045465886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.4823241321715,
        1462.0446849610057
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 411.96388898904297
      }
    },
    {
      "id": "ccac6f6b529d5ee31a8ed209",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1382.9439378104241,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.3231031254697,
        1408.5647724953785
      ],
      "voteCount": 560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.8796581177843
      }
    },
    {
      "id": "49aceda111a84bc21a118715",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1438.5993291064597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.3959788369757,
        1448.8026793759436
      ],
      "voteCount": 3499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.10125542956274
      }
    },
    {
      "id": "02e3b47493ddff86686938df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1433.629869924105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.94729059758,
        1441.3124492506297
      ],
      "voteCount": 6955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.364482053118518
      }
    },
    {
      "id": "6528e6f0c4a61f61ba11862d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1403.167414464164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.9663360469383,
        1414.3684928813896
      ],
      "voteCount": 2887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.66054995382374
      }
    },
    {
      "id": "5d2f282933c5686173b5654d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1390.6710459704473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.006719721014,
        1401.3353722198804
      ],
      "voteCount": 3212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.605381617445346
      }
    },
    {
      "id": "792189b763975e62c3acb038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1413.735480439958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.453280348184,
        1430.017680531732
      ],
      "voteCount": 1390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.01285480411879
      }
    },
    {
      "id": "c111b9cbd0d6668a6a166c7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1424.7490783831545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.1840617321413,
        1435.3140950341676
      ],
      "voteCount": 3428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.056559511944982
      }
    },
    {
      "id": "8f6d35f801e7eb132460adee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1416.100518380919,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.0824969819178,
        1435.1185397799206
      ],
      "voteCount": 949,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.15306913729249
      }
    },
    {
      "id": "9d5cd4d96621ee334d51084c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1441.13529941404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.44211107445,
        1458.8284877536298
      ],
      "voteCount": 1242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.4921956038659
      }
    },
    {
      "id": "09a9e7d3a9c90ec2a9531a5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1456.0356077819263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.7303105094943,
        1464.3409050543585
      ],
      "voteCount": 5676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.9561895631632
      }
    },
    {
      "id": "42bacd6cacdc71220df9f80f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1391.1687993798712,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.6164781136988,
        1400.7211206460436
      ],
      "voteCount": 4228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.753174466069833
      }
    },
    {
      "id": "7bebd8da3bf4c1d299b02ffd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1392.0434377943236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.5498591899632,
        1401.5370163986843
      ],
      "voteCount": 4048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.461929158695813
      }
    },
    {
      "id": "7298919f156f2412c5a2fdcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1381.998288235098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.3719464466903,
        1408.6246300235057
      ],
      "voteCount": 549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.55542806131143
      }
    },
    {
      "id": "da959614b386eb76da5b201d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1348.5166224230609,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.5147795716132,
        1384.5184652745083
      ],
      "voteCount": 298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 337.40637325539
      }
    },
    {
      "id": "09ce2e0bdc209dc741901a04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1407.6736217454375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.0304352078936,
        1418.3168082829814
      ],
      "voteCount": 3138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.488125464920778
      }
    },
    {
      "id": "8b8aa1976b16a2d43a170208",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1396.4617556354403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.7242942793428,
        1416.199216991538
      ],
      "voteCount": 869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.41131246411587
      }
    },
    {
      "id": "17d136229d3f506043cb0621",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1405.8144620096982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.9328047000295,
        1416.6961193193672
      ],
      "voteCount": 2958,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.824348595691614
      }
    },
    {
      "id": "8f4eec023f84609643cb8887",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1422.303599238661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.6475561895647,
        1427.959642287757
      ],
      "voteCount": 18467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.327779748905032
      }
    },
    {
      "id": "9b475aee136efef6510662dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1414.590245749456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.2832253749118,
        1430.897266124
      ],
      "voteCount": 1251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.2234189947004
      }
    },
    {
      "id": "bda350265b9a8f03d7ac5140",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1-0528",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1395.902346709122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.390137419443,
        1434.414555998801
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 386.1007845202004
      }
    },
    {
      "id": "7d852bcb47ce6d93a38025da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1428.8760630454399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.7623267198335,
        1446.989799371046
      ],
      "voteCount": 1151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.41219859134205
      }
    },
    {
      "id": "0966db38ffcf0e189a96f958",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1444.462932183191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.6548132720668,
        1456.2710510943152
      ],
      "voteCount": 2317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.29654220634183
      }
    },
    {
      "id": "f990ee314138d8fe5c068b4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1374.208563553323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.8799743806449,
        1384.5371527260013
      ],
      "voteCount": 3289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.770635916562902
      }
    },
    {
      "id": "6ddda7325c5477906bf4066a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1412.6036241069041,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.50377303858,
        1418.7034751752283
      ],
      "voteCount": 10721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.685951299358791
      }
    },
    {
      "id": "8873842d275a0544bf0a03be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1383.1790289321123,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.8900600356583,
        1390.4679978285662
      ],
      "voteCount": 12504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.830440479347414
      }
    },
    {
      "id": "9d7e4cfa5abaa7ddd2d00509",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1399.392186927804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.5999013293795,
        1419.1844725262288
      ],
      "voteCount": 848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.97547012591058
      }
    },
    {
      "id": "b47a370b3306e6ffe1a19570",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1391.9061977940032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.1980992003955,
        1433.614296387611
      ],
      "voteCount": 188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 452.83981151196525
      }
    },
    {
      "id": "b072a04366be5227d8a1e6b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1397.548402927067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.1553749476332,
        1425.941430906501
      ],
      "voteCount": 436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.8588258965766
      }
    },
    {
      "id": "4cfe1fc2569bb3b32ad1b76d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1433.1532929704117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.9721011583583,
        1444.3344847824653
      ],
      "voteCount": 2656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.54468059489524
      }
    },
    {
      "id": "27d01f8e560e713793b23716",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1418.366899715477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.3679300265098,
        1427.3658694044445
      ],
      "voteCount": 4116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.08091202922712
      }
    },
    {
      "id": "8adee6cdab720930178499af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1388.2525781003214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.3727346993066,
        1402.1324215013365
      ],
      "voteCount": 1798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.15023245827398
      }
    },
    {
      "id": "2e7033e702ad764fb2e4c2a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1372.275615789825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4618480491913,
        1382.0893835304587
      ],
      "voteCount": 3571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.071214286686264
      }
    },
    {
      "id": "c2f969651c14bf5590702c10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1398.7224041243326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.0678530678101,
        1416.376955180855
      ],
      "voteCount": 1097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.13666905090896
      }
    },
    {
      "id": "a8f0a639f4b152530cc74573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1410.7779652358654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.5314767762873,
        1421.0244536954438
      ],
      "voteCount": 3309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.330899705778815
      }
    },
    {
      "id": "8a51c943e315cc799e6ec8ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1413.5629079784492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.8136662886654,
        1428.3121496682331
      ],
      "voteCount": 1504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.62956199133467
      }
    },
    {
      "id": "d4ab213fb407ed4159fa344c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1412.0345352480115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.5405829528572,
        1432.528487543166
      ],
      "voteCount": 830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.33400572029899
      }
    },
    {
      "id": "0c5c6d359e5f7c03cc396c6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1430.4639077636718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.254323398556,
        1439.6734921287878
      ],
      "voteCount": 3954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.079227745792025
      }
    },
    {
      "id": "75c4b20076e7da03acf2bf77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1382.0789405803907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9092261816484,
        1390.2486549791329
      ],
      "voteCount": 5355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.37471009645134
      }
    },
    {
      "id": "4d8c9f71a6403728ea121e5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1396.6613789238158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.1853778595998,
        1404.137379988032
      ],
      "voteCount": 6426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.549314341488051
      }
    },
    {
      "id": "ad640e6ca428fb656223096b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1337.7879519936155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.0265886218494,
        1363.5493153653815
      ],
      "voteCount": 468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.75932757552062
      }
    },
    {
      "id": "e11b9f100e7504741b8cfdd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1356.112787548939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.9921908762594,
        1396.2333842216185
      ],
      "voteCount": 215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 419.02369711748486
      }
    },
    {
      "id": "2ef06720dcd49f22c5c372cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1398.7203536153067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.7339208733936,
        1410.7067863572202
      ],
      "voteCount": 2303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.40104386969583
      }
    },
    {
      "id": "1306564c87ebaa02db1037d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1410.9990421361929,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.9761143590595,
        1425.021969913326
      ],
      "voteCount": 1606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.189538303358944
      }
    },
    {
      "id": "240e054495484f11da8fce60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1410.1921278014943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.284511176518,
        1422.0997444264706
      ],
      "voteCount": 2418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.91080402152815
      }
    },
    {
      "id": "43e1b352397ca10f417f5ca4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1397.9428437604695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.0740265432703,
        1402.8116609776687
      ],
      "voteCount": 18524,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.1709319820878346
      }
    },
    {
      "id": "606afc42bb338d8f1ad17736",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1380.5382295871188,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.7057521737415,
        1393.3707070004964
      ],
      "voteCount": 1904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.86717214765969
      }
    },
    {
      "id": "4c09b5ecf32796ab96d9c3fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-r1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1394.6217309877843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.7824161182425,
        1446.4610458573263
      ],
      "voteCount": 114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 699.5557395192737
      }
    },
    {
      "id": "4e9c80424e55097c6be324fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1354.354717256636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.8211679820906,
        1380.8882665311817
      ],
      "voteCount": 446,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.2713221633657
      }
    },
    {
      "id": "496f4c1e544c61c4b09a335c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1374.5896255661073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.7097893195764,
        1391.4694618126382
      ],
      "voteCount": 1079,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.17204895566668
      }
    },
    {
      "id": "219d13cd62af234baeb9bf69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1309.9720144642454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.8407636026964,
        1327.1032653257944
      ],
      "voteCount": 1090,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.39799612072764
      }
    },
    {
      "id": "99d9c9fa8585f424a367d134",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1336.052934822039,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.699329267922,
        1346.406540376156
      ],
      "voteCount": 3776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.90532268438444
      }
    },
    {
      "id": "2de217377318ccb59eaaf638",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1270.4563154809944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.2438912204136,
        1283.668739741575
      ],
      "voteCount": 4213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.44319306539916
      }
    },
    {
      "id": "dd0cdedb98fe4504534065d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1305.9051297765345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.7046766973267,
        1332.1055828557419
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.69871150453207
      }
    },
    {
      "id": "ebeae1e0d5eb28a579c5ab31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1288.75421405701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.3691548861166,
        1336.1392732279035
      ],
      "voteCount": 140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 584.5029030464409
      }
    },
    {
      "id": "4814714a130849f6894cd746",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1337.520251446338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.2326361073497,
        1353.8078667853265
      ],
      "voteCount": 1132,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.05876798724061
      }
    },
    {
      "id": "949a95b4ad3609f2c683104b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1328.6550715328167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.3312458171565,
        1341.9788972484769
      ],
      "voteCount": 1790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.212738438052625
      }
    },
    {
      "id": "2dc4683fb522081aad7691d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1306.2529990591265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.7413726066557,
        1327.7646255115972
      ],
      "voteCount": 715,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.46206772744289
      }
    },
    {
      "id": "bea63ec21bc494912860bcfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1302.2843230745225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.3007106224218,
        1318.2679355266228
      ],
      "voteCount": 1216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.50490840684863
      }
    },
    {
      "id": "dedddb73d6f748b8f54508d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1326.585508933299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.1089308190285,
        1356.06208704757
      ],
      "voteCount": 375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.18195271183595
      }
    },
    {
      "id": "f593426c7f44e917c49c5281",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1331.0817090280116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.3805781626286,
        1347.7828398933948
      ],
      "voteCount": 1137,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.60985609947258
      }
    },
    {
      "id": "eb49b24e8f29ba2ab3bfa550",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1287.1792457728966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.4327716171588,
        1304.9257199286344
      ],
      "voteCount": 893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.98378784218325
      }
    },
    {
      "id": "8cd241aa6e2c5925958e2ca6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1336.1364712850689,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.7596344995427,
        1368.513308070595
      ],
      "voteCount": 291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.8805928074982
      }
    },
    {
      "id": "8dc79f6dc1448899468cab03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1365.0068860662318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.8334114678496,
        1379.180360664614
      ],
      "voteCount": 1688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.29455567994052
      }
    },
    {
      "id": "8a05c9b79f449ed9ae6f7944",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1314.312916038472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.8741377994859,
        1327.7516942774582
      ],
      "voteCount": 1930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.013587542248985
      }
    },
    {
      "id": "aa95232d9dba886983e3fbd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1314.251198373524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.9985621597962,
        1325.5038345872517
      ],
      "voteCount": 2970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.96191047952371
      }
    },
    {
      "id": "ab2d537787e66e32f7e41840",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1252.0012504701647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.2067513653737,
        1293.7957495749556
      ],
      "voteCount": 161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 454.7179175813059
      }
    },
    {
      "id": "d8ad37f5e977792fd2b614cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1337.2765267105206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.9046480044622,
        1354.6484054165785
      ],
      "voteCount": 1037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.55926195337139
      }
    },
    {
      "id": "d9ed04bfe294fbfe0d9e0050",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1292.5717849906641,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.8845971231817,
        1309.2589728581465
      ],
      "voteCount": 1031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.48866951913219
      }
    },
    {
      "id": "1a635da4a53e3fbdd2315018",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1322.798111640985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.489586631915,
        1339.1066366500554
      ],
      "voteCount": 1178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.23619395285128
      }
    },
    {
      "id": "6eaa9fab4ea71e825b8673fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1323.353871124716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.087622695504,
        1331.6201195539284
      ],
      "voteCount": 6795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.787738013837753
      }
    },
    {
      "id": "7f67723e3d429dcd4c3aec4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5-1210",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1321.6665148470893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.335332823724,
        1338.9976968704545
      ],
      "voteCount": 1034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.19161530742198
      }
    },
    {
      "id": "840044106f82fad965d6bdd3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1329.8328339782533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.7553413757855,
        1342.9103265807216
      ],
      "voteCount": 2242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.51975688150281
      }
    },
    {
      "id": "f23cb6efd820259f31e423d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1368.329377620752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.970219472595,
        1377.6885357689093
      ],
      "voteCount": 4252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.802233560423655
      }
    },
    {
      "id": "553b3c1b475ffe726fdb1885",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1265.0504501171329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.3561001538988,
        1275.7448000803672
      ],
      "voteCount": 3450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.77231475709626
      }
    },
    {
      "id": "2c13b7edd4a4d6ad658df93c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1318.4960112762428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.3326031797847,
        1324.6594193727012
      ],
      "voteCount": 12845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.888847215762677
      }
    },
    {
      "id": "5b406304d1758f47fad2d192",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1243.6057994533958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.030209244936,
        1251.1813896618555
      ],
      "voteCount": 15337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.939524197773283
      }
    },
    {
      "id": "4e8c1d6ab4abb00a5b56dfb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1294.8565443573639,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.9872915049614,
        1309.7257972097666
      ],
      "voteCount": 1523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.554874517367146
      }
    },
    {
      "id": "a2c8eaa264541196801f9bed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1327.8402927471718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.0714968906966,
        1365.609088603647
      ],
      "voteCount": 222,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 371.3386000036161
      }
    },
    {
      "id": "c27f325dada5e9a4a912a3aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1260.426468030314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.1761863184188,
        1284.6767497422093
      ],
      "voteCount": 563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.08667632678555
      }
    },
    {
      "id": "acd4e1356700baf39ddd3646",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1330.55404614183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.2353349443601,
        1339.8727573392998
      ],
      "voteCount": 4055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.605573152065606
      }
    },
    {
      "id": "abed529e49c2f789fb51288f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1321.432945585725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.8316059064907,
        1329.0342852649596
      ],
      "voteCount": 6869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.04125583953606
      }
    },
    {
      "id": "6704389f8b3905bbd52e5eb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1300.7559791040903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.2199969213848,
        1312.291961286796
      ],
      "voteCount": 2825,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.64279877290369
      }
    },
    {
      "id": "4362468936926e2e145370ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1263.7344902527543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.5651556445755,
        1273.9038248609336
      ],
      "voteCount": 3664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.92085772623792
      }
    },
    {
      "id": "17890f5c807e6d5252abfa77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1331.0626530619083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.6688557414943,
        1346.4564503823221
      ],
      "voteCount": 1518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.687240968306476
      }
    },
    {
      "id": "e07311242d3e44f8be1f4bf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1320.894419870172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.3572977538774,
        1330.4315419864668
      ],
      "voteCount": 4318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.67764500588412
      }
    },
    {
      "id": "294354034e92203433235cee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1295.6993990114534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.377718473339,
        1306.0210795495677
      ],
      "voteCount": 3039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.73349763818113
      }
    },
    {
      "id": "ef301f3f3ecb15037f0cf7b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1313.9422973083065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.3530667790847,
        1331.5315278375288
      ],
      "voteCount": 1214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.53738047209224
      }
    },
    {
      "id": "fff884643836babed7a7dbb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1349.7187487751182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.7061845948767,
        1357.7313129553595
      ],
      "voteCount": 6692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.712709347978247
      }
    },
    {
      "id": "f207216bcd65e9e6dda48bac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1283.112329306076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.8449318933956,
        1291.379726718756
      ],
      "voteCount": 6613,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.792683240801015
      }
    },
    {
      "id": "e138a40ba8808a2575979c53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1290.977154928277,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.246711972653,
        1297.7075978839011
      ],
      "voteCount": 10175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.792098911716636
      }
    },
    {
      "id": "f75ac02ab32079b5694f2941",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1227.4181516930735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.9930420552348,
        1253.8432613309124
      ],
      "voteCount": 479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.7763646482669
      }
    },
    {
      "id": "ab2fc965584218b65feedfda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1254.208415879928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.8469325159465,
        1287.5698992439097
      ],
      "voteCount": 344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 289.7307049731995
      }
    },
    {
      "id": "27b6d50df22dc19f5bbc20fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1313.859993718511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.676640821313,
        1324.0433466157092
      ],
      "voteCount": 3499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.99512895211359
      }
    },
    {
      "id": "c52b7a07b998899ffae670dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1287.49681101792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.7743374637485,
        1297.2192845720915
      ],
      "voteCount": 3649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.606925760168437
      }
    },
    {
      "id": "31db56d5f17e7a79631f7bf8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1292.579680980076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.9493921493058,
        1302.2099698108464
      ],
      "voteCount": 4473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.14251129400328
      }
    },
    {
      "id": "6cad4d94baf833a9bd755393",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1306.9453791641795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.24838308555,
        1311.6423752428088
      ],
      "voteCount": 24572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.743071367526431
      }
    },
    {
      "id": "5d2203ff7a18d5d42ca86f0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1289.4603082240974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.173293692636,
        1299.7473227555593
      ],
      "voteCount": 3519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.547521113705802
      }
    },
    {
      "id": "cfc713948a56105ed949e03c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v2.5",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1282.2444868279895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.7444344157734,
        1316.7445392402053
      ],
      "voteCount": 293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 309.8441691041167
      }
    },
    {
      "id": "cf981be2372edebc4ab61130",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1414.1447259748577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.083983332097,
        1426.2054686176184
      ],
      "voteCount": 2472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.86621694635915
      }
    },
    {
      "id": "b58a7c36e9dd0c9d5abce574",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1428.625094046381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.847967929757,
        1435.4022201630053
      ],
      "voteCount": 8372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.956249056531753
      }
    },
    {
      "id": "e74c403c0e9d4e0f962fd0ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1390.0329193558332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.0168901066859,
        1398.0489486049805
      ],
      "voteCount": 6041,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.72716744405297
      }
    },
    {
      "id": "8bb4a033b917c4809c843b3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1407.6437280591958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.8039714550034,
        1412.4834846633883
      ],
      "voteCount": 23267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.09748667918624
      }
    },
    {
      "id": "4de1021dd8b77c820ecb9324",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1376.4556770527856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.0455117160357,
        1381.8658423895356
      ],
      "voteCount": 31872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.619472272693138
      }
    },
    {
      "id": "d8a5a816450019f0a6c7d042",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1397.271603884277,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.7821190533568,
        1409.7610887151973
      ],
      "voteCount": 2293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.606248465159446
      }
    },
    {
      "id": "78ab62f339df1bb6b2bdf843",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1422.3263213789267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.0940221803103,
        1448.558620577543
      ],
      "voteCount": 540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.13338483253267
      }
    },
    {
      "id": "c59dfa73e5d4aa7d5429c55e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1396.984072313924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.919157128504,
        1415.0489874993439
      ],
      "voteCount": 1156,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.95240373224888
      }
    },
    {
      "id": "f14ce13cfd0df84d0a8e1376",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1418.1951133122016,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.8314053019699,
        1424.558821322433
      ],
      "voteCount": 10240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.542031433820778
      }
    },
    {
      "id": "076bf265f0777542754b8a81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1408.652250459357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.4575897632878,
        1413.8469111554261
      ],
      "voteCount": 18706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.024544842682971
      }
    },
    {
      "id": "3b9f0a9f8585c9a964df5947",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1390.5594343469127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.0390087922772,
        1398.0798599015482
      ],
      "voteCount": 6932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.722740282452433
      }
    },
    {
      "id": "35d11f6dc77758241f2e8a50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1382.440639185988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.4900257487616,
        1389.3912526232143
      ],
      "voteCount": 8061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.5762189336764
      }
    },
    {
      "id": "ed3bfae5d28757e37015f5fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1409.9253483524176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.8398072232544,
        1421.0108894815808
      ],
      "voteCount": 2940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.990248460912703
      }
    },
    {
      "id": "f929d5fd42f429bf75bc28aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1413.9444666613197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.7798977278376,
        1421.109035594802
      ],
      "voteCount": 7669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.36238403132063
      }
    },
    {
      "id": "54a6266f9e86e508579c3a5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1368.3601589179164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.6024610061386,
        1379.1178568296943
      ],
      "voteCount": 2930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.126071829180734
      }
    },
    {
      "id": "162961ca1fc49b269490aa7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1427.4207031277845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.6903904119931,
        1439.151015843576
      ],
      "voteCount": 2665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.81978691766795
      }
    },
    {
      "id": "2d931aaac802946ef0aa791a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1424.0384063723322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.4011904176664,
        1429.675622326998
      ],
      "voteCount": 14632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.27243117857942
      }
    },
    {
      "id": "1d3226f81af5a098a64eb5d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1386.2224656153064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.827387090985,
        1392.6175441396279
      ],
      "voteCount": 10339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.646223541932416
      }
    },
    {
      "id": "7893ff81b9856df165ff01c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1378.2491435508678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.388035555228,
        1384.1102515465075
      ],
      "voteCount": 12395,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.942588880946376
      }
    },
    {
      "id": "aa49f237fec70ea014e06e74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1336.7717374894073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.063061157358,
        1356.4804138214565
      ],
      "voteCount": 961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.11573256206026
      }
    },
    {
      "id": "507c0d291950c40ff5c4fa2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1333.4051640603066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.375842267233,
        1353.43448585338
      ],
      "voteCount": 924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.43265181689459
      }
    },
    {
      "id": "4811ed7623f25c504c74227f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1393.4250362596028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.6845458818138,
        1400.1655266373918
      ],
      "voteCount": 8461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.827332441599998
      }
    },
    {
      "id": "78672f661431cf9eb954cfb0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1370.088087816863,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.8069350393619,
        1380.3692405943643
      ],
      "voteCount": 3191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.51613576199198
      }
    },
    {
      "id": "9e2c6f7ee66b3d3b74401989",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1410.4546037203354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.3027378261968,
        1417.6064696144742
      ],
      "voteCount": 7859,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.315042059594896
      }
    },
    {
      "id": "904ca692e02de93d2507e826",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1395.3663815599457,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.4995279879265,
        1399.233235131965
      ],
      "voteCount": 45518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.8924162005559966
      }
    },
    {
      "id": "0b771a284addbc4a4eaa9209",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1398.4139482846256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.1723752144953,
        1408.655521354756
      ],
      "voteCount": 3101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.30468393563728
      }
    },
    {
      "id": "7175f2b8e684e6beb1a1bad8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3-0324",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1362.8884796307138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.0216170775489,
        1383.7553421838786
      ],
      "voteCount": 893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.34911374476148
      }
    },
    {
      "id": "60ffdff620dde14207a3d723",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1463.3848969688117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.75422316319,
        1487.0155707744332
      ],
      "voteCount": 636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.36372002727498
      }
    },
    {
      "id": "7f4ecc0bbc00885ec9b30d44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1385.0876604725113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.1400392554658,
        1413.0352816895568
      ],
      "voteCount": 440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 203.32627997566811
      }
    },
    {
      "id": "0038014245b37a4da278139a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1428.895250293091,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.6757165669599,
        1443.1147840192225
      ],
      "voteCount": 1676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.63498811944847
      }
    },
    {
      "id": "3555f1c088ccb2a3a1c4de76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1402.9820760577272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.6848936207316,
        1417.2792584947229
      ],
      "voteCount": 2495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.211406181310934
      }
    },
    {
      "id": "4f2af96f086ceb7691bbca3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1449.9849355299154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.9284720448995,
        1470.0413990149314
      ],
      "voteCount": 840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.71587652033979
      }
    },
    {
      "id": "c2b5e9f8f146ad6b334f9195",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1445.7538835043501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.414262143002,
        1460.0935048656984
      ],
      "voteCount": 1679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.52777431300979
      }
    },
    {
      "id": "dac3d1e216bc39aa920eea54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1419.5804169651499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.4056261083983,
        1441.7552078219012
      ],
      "voteCount": 699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.0038059738509
      }
    },
    {
      "id": "a005976f96bb540613c14fa6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1384.4887621289229,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.7867280386513,
        1408.1907962191945
      ],
      "voteCount": 617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.24298898898138
      }
    },
    {
      "id": "4dc29879711b3c356bef2444",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1462.3845418872374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.9979364554247,
        1497.7711473190502
      ],
      "voteCount": 262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 325.97299683158906
      }
    },
    {
      "id": "e746d667bea71b185177953f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1448.3903458984137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.2216036015154,
        1473.559088195312
      ],
      "voteCount": 538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.90235048080314
      }
    },
    {
      "id": "b1230fe8427818b845ae915d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1464.916056226686,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.7163333256235,
        1502.1157791277483
      ],
      "voteCount": 228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 360.2327783552228
      }
    },
    {
      "id": "194f5d636e88daca5c1b3be1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1446.1325441133558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.7729378768645,
        1463.4921503498472
      ],
      "voteCount": 1175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.44830382213375
      }
    },
    {
      "id": "d7c54cee05ff8da03a22f22e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1410.1741028859044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.0346955740868,
        1431.313510197722
      ],
      "voteCount": 772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.32938483879987
      }
    },
    {
      "id": "72c1823e9518f99c34b53fcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1419.9321044423364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.8976998796916,
        1439.9665090049812
      ],
      "voteCount": 864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.48566154542199
      }
    },
    {
      "id": "6da33429c2e1532b1c793079",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1444.2008297648738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.8972638964879,
        1466.5043956332597
      ],
      "voteCount": 680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.4948283099238
      }
    },
    {
      "id": "18f1fa1b547bc36bf15ffe7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1410.1719545487958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.6147878353954,
        1450.7291212621963
      ],
      "voteCount": 200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 428.1924780652317
      }
    },
    {
      "id": "b1707bf5bd9c44dad3162e43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1419.5149057745823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.823106173759,
        1443.2067053754058
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.11672141370315
      }
    },
    {
      "id": "eb0030c13934952d0157f17d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1417.6347297018206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.6667110740061,
        1427.602748329635
      ],
      "voteCount": 3468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.865537027024878
      }
    },
    {
      "id": "d353fd9ca973196a6396e392",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1428.237202045926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.9859241667896,
        1464.4884799250624
      ],
      "voteCount": 236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 342.09793966577166
      }
    },
    {
      "id": "8186411de495cb5d5a2b848b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1438.9611773228187,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.312048496361,
        1459.6103061492765
      ],
      "voteCount": 778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.9959890744337
      }
    },
    {
      "id": "bdc94ad391b71ead60821a9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1408.2899640574253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.0976279862582,
        1435.4823001285924
      ],
      "voteCount": 457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.48498435646042
      }
    },
    {
      "id": "d87e9e23615c9dc43bae591d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1422.7842282709464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.1443893008882,
        1436.4240672410046
      ],
      "voteCount": 1853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.4308737417374
      }
    },
    {
      "id": "ef86e907927c8bea7279c954",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1401.284440456664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.501252348729,
        1415.067628564599
      ],
      "voteCount": 2654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.454200418682895
      }
    },
    {
      "id": "b89f08f5a792b9a3e7c8dcc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1427.6925769954166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.7029707625425,
        1445.6821832282908
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.24558156668985
      }
    },
    {
      "id": "471fa4c6914f55ea58315787",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1423.8524058971998,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.6803512141032,
        1437.0244605802961
      ],
      "voteCount": 1929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.16592072777508
      }
    },
    {
      "id": "1d396b02acc47350ad2b9b46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1395.7491044797105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.3641011659981,
        1417.1341077934228
      ],
      "voteCount": 740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.04809815060199
      }
    },
    {
      "id": "64a5705546ca703bd03edb74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1376.459415848122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.43075448282,
        1399.488077213424
      ],
      "voteCount": 636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.0515239213026
      }
    },
    {
      "id": "d3d46d918fc0844555d053b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1416.5516676415423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.648708880964,
        1451.4546264021208
      ],
      "voteCount": 271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 317.12341251194414
      }
    },
    {
      "id": "0df20a50707a7992437e9921",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1452.0505550829969,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.8540592723477,
        1476.2470508936456
      ],
      "voteCount": 577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.40835235843028
      }
    },
    {
      "id": "cbbf973ccfe7dd938ed0ed52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1451.966849134585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.8137317838966,
        1490.1199664852732
      ],
      "voteCount": 258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 378.9342620917023
      }
    },
    {
      "id": "732582fe3d387124b83a58e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1429.4891773162476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.5327384792638,
        1445.4456161532314
      ],
      "voteCount": 1315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.27897167264078
      }
    },
    {
      "id": "06a043757b025ca4e86c1c5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1409.4185560443211,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.7569197680543,
        1430.0801923205877
      ],
      "voteCount": 810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.13049326807592
      }
    },
    {
      "id": "deeba631fea24e85e17d4833",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1393.1560706191115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.3474805203243,
        1410.9646607178986
      ],
      "voteCount": 1030,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.55870910242237
      }
    },
    {
      "id": "a364d5f56f2fee970b28c9ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1418.1633104915618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.4736502519563,
        1437.852970731167
      ],
      "voteCount": 846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.92070186009205
      }
    },
    {
      "id": "b7baf11b7fd0d879cdc01e5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1395.3160336631342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.4319042605864,
        1434.200163065682
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 393.5940979632526
      }
    },
    {
      "id": "c5c155a9192dc4505690d476",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1394.6302633979708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.4215781958067,
        1416.838948600135
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.3954147189581
      }
    },
    {
      "id": "c82c41c62dacb7afc0b38f9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1416.0240494129466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.4136493744852,
        1425.6344494514078
      ],
      "voteCount": 3705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.04289443419513
      }
    },
    {
      "id": "240937bcd13324a69bf61b26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-terminus",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1424.8083508755064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.6590886669885,
        1457.9576130840244
      ],
      "voteCount": 261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 286.05632293893035
      }
    },
    {
      "id": "306cff4825d4b11505668da3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1476.4805446181574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.9296133990088,
        1497.031475837306
      ],
      "voteCount": 874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.94280914818331
      }
    },
    {
      "id": "1fcff12b12adf61a592ab558",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1456.9060189526951,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.5344211728927,
        1470.2776167324976
      ],
      "voteCount": 1904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.544720516490585
      }
    },
    {
      "id": "86fdc3cc36aff7b2d31cf053",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1404.3781314280725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.6159889085613,
        1419.1402739475836
      ],
      "voteCount": 1646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.728670522877444
      }
    },
    {
      "id": "76f155d0357f1dab4e2a9995",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1431.4778120589403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.913162646257,
        1440.042461471624
      ],
      "voteCount": 5272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.09514665809295
      }
    },
    {
      "id": "047625cb0d4a8ab2cce19d4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1404.1652309269627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.1325536969869,
        1413.1979081569384
      ],
      "voteCount": 8360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.23913381588182
      }
    },
    {
      "id": "0cc5dfb9badf321f70c7f788",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1431.041022561613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.0713451534134,
        1456.010699969813
      ],
      "voteCount": 529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.30417114217573
      }
    },
    {
      "id": "39ca48c579ae4c39c0b4cdec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1390.584477773467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.7002234680392,
        1436.4687320788946
      ],
      "voteCount": 172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 548.0638714187069
      }
    },
    {
      "id": "f7ce9c5a0d048130c62f5b3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1400.7678643253164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.8567538684456,
        1433.678974782187
      ],
      "voteCount": 314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 281.9609013298309
      }
    },
    {
      "id": "3c9049fa417c286a50872931",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1444.789096450377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.9627926114624,
        1456.6154002892913
      ],
      "voteCount": 2469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.4084242519749
      }
    },
    {
      "id": "ae2b28a44d027f6ddd8a761f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1437.2099015339006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.6228379655452,
        1445.7969651022559
      ],
      "voteCount": 5152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.195223525434667
      }
    },
    {
      "id": "f62a0a1507b6cb7cae678663",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1416.0672097875492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.7205982206729,
        1429.4138213544254
      ],
      "voteCount": 1939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.370935790712664
      }
    },
    {
      "id": "8e59959e421e2d286e3160de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1396.2369457867665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.743759881857,
        1408.730131691676
      ],
      "voteCount": 2231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.63031815252566
      }
    },
    {
      "id": "9059b708eb3ff684a24bc514",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1421.8186986132043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.1731195479729,
        1442.4642776784358
      ],
      "voteCount": 780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.95783004168833
      }
    },
    {
      "id": "6f380f5ff2a7903fb042d13a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1428.324126787294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.7700982753959,
        1441.878155299192
      ],
      "voteCount": 1866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.823417476632095
      }
    },
    {
      "id": "bf34ca7b5f1312f344021e21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1442.1661151052322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.161088060012,
        1466.1711421504526
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.00585723775518
      }
    },
    {
      "id": "688c3b89788494bb2409c5ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1445.7989292678478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.471128326861,
        1468.1267302088347
      ],
      "voteCount": 703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.77639957370542
      }
    },
    {
      "id": "9a6c6de600d93094c42bb7a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1448.4569373886106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4782037932844,
        1458.4356709839371
      ],
      "voteCount": 3577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.921174432504905
      }
    },
    {
      "id": "36e103016975ab69d60cfdba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1409.931975431799,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.554070262016,
        1421.3098806015819
      ],
      "voteCount": 2749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.69988644813341
      }
    },
    {
      "id": "d4788854d9806f4e7877b150",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1418.7768981130978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.7603876812268,
        1429.7934085449685
      ],
      "voteCount": 2861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.593076422354788
      }
    },
    {
      "id": "82a07a25998fc63d3212f1d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1377.5815805829689,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.458282493059,
        1415.7048786728787
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 378.3421676740801
      }
    },
    {
      "id": "b34a2c409258c8749b82732e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1346.9281894331334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.344437893791,
        1379.511940972476
      ],
      "voteCount": 357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 276.37960314924277
      }
    },
    {
      "id": "b83d9e7cd903e3403d29e41f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1445.945396505456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.9590656792889,
        1457.9317273316235
      ],
      "voteCount": 2362,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.40040786077404
      }
    },
    {
      "id": "2df3d767c099ba6d176110e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1413.831102359184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.8489762473232,
        1435.8132284710446
      ],
      "voteCount": 665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.78915744056683
      }
    },
    {
      "id": "bee78b1f69047663d7bc82fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1414.1137711320357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.3892530465973,
        1427.838289217474
      ],
      "voteCount": 1876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.03407936141552
      }
    },
    {
      "id": "af8eeef4b2ccaabdbda9eabb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1417.138923410077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.5331945803287,
        1423.7446522398254
      ],
      "voteCount": 11746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.359136049331305
      }
    },
    {
      "id": "00e407c8355912b955c1a441",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1402.5952308875399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.2643920453552,
        1424.9260697297245
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.81171650449056
      }
    },
    {
      "id": "fc8b858ee0117932ae20be04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1406.5274658992273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.4132584832582,
        1437.6416733151966
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 252.0120475869176
      }
    },
    {
      "id": "a73ca97faea5778c85cabe8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1464.3853343341214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.5177212330527,
        1482.2529474351898
      ],
      "voteCount": 1113,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.10686456136214
      }
    },
    {
      "id": "7af371a840c639b69f064721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1447.5529742169426,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.9504745690065,
        1459.1554738648788
      ],
      "voteCount": 2624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.04345728116763
      }
    },
    {
      "id": "bdde5537faa88aa83116c711",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1389.6262416768968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.3033314098132,
        1402.9491519439805
      ],
      "voteCount": 2003,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.20638832012496
      }
    },
    {
      "id": "7060228b0f208c37b6bc760d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1428.471630597574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.693160474606,
        1436.2501007205417
      ],
      "voteCount": 6784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.7504219823894
      }
    },
    {
      "id": "96473a4b500881ea1a088c44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1404.6277325667272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.3341867215534,
        1412.921278411901
      ],
      "voteCount": 10681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.90541195325737
      }
    },
    {
      "id": "d3a2dafa7153ad97837d1b06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1427.443033104206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.422957050658,
        1449.4631091577544
      ],
      "voteCount": 726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.2238571430089
      }
    },
    {
      "id": "4926af302b0a67527303dc5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1452.681769568463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.877330391156,
        1490.48620874577
      ],
      "voteCount": 248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 372.0398130553074
      }
    },
    {
      "id": "c1a455317072669eefcd9362",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1404.591793899698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.882373978341,
        1435.3012138210545
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.49748309831284
      }
    },
    {
      "id": "c49057974dbb10f4ac748873",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1435.439530719416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.1963974677105,
        1445.6826639711217
      ],
      "voteCount": 3363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.31300365553277
      }
    },
    {
      "id": "16f7f01a338f64cf7727b1d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1433.1096515418064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.3375336967115,
        1440.8817693869014
      ],
      "voteCount": 6810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.7247073618577
      }
    },
    {
      "id": "a18ea4eb6890f8d09ea16829",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1414.4119414554766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.537128136921,
        1426.2867547740323
      ],
      "voteCount": 2527,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.7077191068435
      }
    },
    {
      "id": "0ebf941695e7ff403f510b22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1379.178801656752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.8537374305197,
        1390.5038658829844
      ],
      "voteCount": 2751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.387597190255235
      }
    },
    {
      "id": "97676ae4cc366339d1bf640a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1420.6395324128357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.5239419350357,
        1438.7551228906357
      ],
      "voteCount": 1011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.42968535585146
      }
    },
    {
      "id": "d398821f23f5f8b39b516b45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1434.174453179992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.8250055400392,
        1446.5239008199449
      ],
      "voteCount": 2319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.70076581072916
      }
    },
    {
      "id": "e0808a108c56296f1446b45d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1415.6283595440593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.9986421884612,
        1435.2580768996572
      ],
      "voteCount": 839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.3071545072665
      }
    },
    {
      "id": "c1198042ccbebffef647764e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1434.2924404550688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.981332836703,
        1453.6035480734345
      ],
      "voteCount": 938,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.07741117493518
      }
    },
    {
      "id": "6731fd19f331d241ddbe4e29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1445.260306834978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.4114248551052,
        1454.1091888148512
      ],
      "voteCount": 4787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.383587576652214
      }
    },
    {
      "id": "5767d88fb2609a63ba4d7121",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1398.7141650740828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.5558437633194,
        1408.872486384846
      ],
      "voteCount": 3472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.862579209963112
      }
    },
    {
      "id": "7f23fa8792596b034a01284f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1403.2506756173816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.4320250184185,
        1413.0693262163447
      ],
      "voteCount": 3692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.096168951538765
      }
    },
    {
      "id": "c687c33f657f7c6965e7dc48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1375.4130569630843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.9293258724329,
        1407.8967880537355
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 274.68543457640965
      }
    },
    {
      "id": "0093fe8d3fb9ba7ad08d05d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1337.9568856297842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.2202956829428,
        1365.6934755766256
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.26725725520416
      }
    },
    {
      "id": "21d5f53002969290842cd8b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1421.2018594265794,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.684746960453,
        1431.7189718927057
      ],
      "voteCount": 3221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.7936588124518
      }
    },
    {
      "id": "65e5b7d81edcca5f7ffea18e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1414.8417981281823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.5723487482564,
        1433.111247508108
      ],
      "voteCount": 992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.88698648743022
      }
    },
    {
      "id": "6f4ed040821a779fee41f709",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1406.521885852087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.7608919673291,
        1418.282879736845
      ],
      "voteCount": 2483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.00740854286187
      }
    },
    {
      "id": "3efc4366e59ad87ce8046fa1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1417.7500897657876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.7420308833964,
        1423.758148648179
      ],
      "voteCount": 14969,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.396631128733365
      }
    },
    {
      "id": "5df85cf73975f836f260fccb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1401.4625345809704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.172513373882,
        1421.7525557880585
      ],
      "voteCount": 790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.16891155160195
      }
    },
    {
      "id": "dd63ce5c19647eb97c1d194b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.1",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1405.399664350374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.0419307444195,
        1437.7573979563283
      ],
      "voteCount": 362,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.55867444772593
      }
    },
    {
      "id": "4169bbd175df8fbae36df139",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1465.1322397402962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.9531556237666,
        1498.3113238568258
      ],
      "voteCount": 304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 286.57124134232623
      }
    },
    {
      "id": "e5326e2c0cc00709fc2a2f64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1474.388298772553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.053832936426,
        1487.72276460868
      ],
      "voteCount": 1919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.286576905882974
      }
    },
    {
      "id": "d082f7d5e65467a8ba2cdf9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1394.9184019439879,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6591239966976,
        1412.1776798912779
      ],
      "voteCount": 1203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.54415423044716
      }
    },
    {
      "id": "5d3822bbdd646c22651938fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1441.130021227479,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.0962660379319,
        1450.163776417026
      ],
      "voteCount": 4363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.24420347422114
      }
    },
    {
      "id": "c3bd79a77e23c2650ca0053b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1414.7219790742809,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.5691576575184,
        1423.8748004910433
      ],
      "voteCount": 6462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.807897415391015
      }
    },
    {
      "id": "3fb054b5814719d6959c813b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1447.2050317360877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.8992991272942,
        1476.510764344881
      ],
      "voteCount": 396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.5676610957174
      }
    },
    {
      "id": "aea26b7955402159c8407ad7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1422.0926023681322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9529505858632,
        1470.2322541504013
      ],
      "voteCount": 139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 603.2671914206229
      }
    },
    {
      "id": "13049646b0681c7f46a395f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1431.741136735885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.2501102317983,
        1475.2321632399717
      ],
      "voteCount": 172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 492.38309576292545
      }
    },
    {
      "id": "843a6cb88055b1f420d70293",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1463.4982636587754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.4371442690697,
        1475.5593830484809
      ],
      "voteCount": 2382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.86858267205064
      }
    },
    {
      "id": "a70b78aa0b354b9f11c2ad05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1446.1532373967423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.5567374711907,
        1454.749737322294
      ],
      "voteCount": 4697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.237434115370593
      }
    },
    {
      "id": "912f9cf55df1a362e29dcac8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1404.457174466619,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.75992261833,
        1418.1544263149085
      ],
      "voteCount": 1799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.83944276189395
      }
    },
    {
      "id": "106ae909be0be99ff6150537",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1390.661494831369,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.2960844845682,
        1405.02690517817
      ],
      "voteCount": 1656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.72048069870677
      }
    },
    {
      "id": "aadf936c3f7506881aa2a782",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1424.518643448331,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.6905143120214,
        1449.3467725846408
      ],
      "voteCount": 521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.46924493593542
      }
    },
    {
      "id": "f73a79f16c602846a36a4379",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1452.0577079116886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9794152906925,
        1467.1360005326846
      ],
      "voteCount": 1428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.18452311387915
      }
    },
    {
      "id": "ff200bbe117918c5c9f2383e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1440.5801501418948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.389046201039,
        1469.7712540827506
      ],
      "voteCount": 393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 221.82212254767296
      }
    },
    {
      "id": "7389d55f19872f8723fa3a7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1474.4458063956506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.6035462835712,
        1502.28806650773
      ],
      "voteCount": 438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.79611036637868
      }
    },
    {
      "id": "2a4c5d2d5233d567c652f986",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1458.6069784754845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.2528600864375,
        1468.9610968645316
      ],
      "voteCount": 3225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.908087166486833
      }
    },
    {
      "id": "a812aa958e2d331b8108ea01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1397.2647513118304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.342997787363,
        1410.186504836298
      ],
      "voteCount": 2094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.46570455151182
      }
    },
    {
      "id": "17a5048f89c460fe62d35507",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1416.2426129325802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.7154672057077,
        1427.7697586594527
      ],
      "voteCount": 2539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.589746971319656
      }
    },
    {
      "id": "89b682d066a2cc7079fad328",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1344.7054642470455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.8552529534513,
        1388.5556755406399
      ],
      "voteCount": 195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 500.54969225087893
      }
    },
    {
      "id": "9a762076615462abd056f216",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1430.586774646655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.8857680317644,
        1443.2877812615454
      ],
      "voteCount": 2070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.993309459020516
      }
    },
    {
      "id": "93f4e01fb1138749fe60fd3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1428.8823734786076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.4181312036553,
        1455.34661575356
      ],
      "voteCount": 481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.31514429219527
      }
    },
    {
      "id": "4bfb2e3422fe0e39ac6a639c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1422.3168365593913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.8628102451262,
        1437.7708628736564
      ],
      "voteCount": 1433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.1708940456235
      }
    },
    {
      "id": "fc332ef40bfcb570c01bd188",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1424.7083152624803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.1544448181062,
        1431.2621857068543
      ],
      "voteCount": 9064,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.181485942332607
      }
    },
    {
      "id": "e5ce72ba7242ff1cad67e35f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1405.4865811355623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.9494210387365,
        1430.0237412323881
      ],
      "voteCount": 503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.73010013119708
      }
    },
    {
      "id": "4801db2fe8c146ba05227f8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1383.6481339462978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.5026462048954,
        1418.7936216877001
      ],
      "voteCount": 279,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 321.54589343167015
      }
    },
    {
      "id": "9123d35f63d1dea5af44dc7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1475.6894516378322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.9844992669723,
        1498.3944040086922
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.1976801588793
      }
    },
    {
      "id": "2e1f2b446c055c9866ace170",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1465.592875932478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.8380647627748,
        1477.347687102181
      ],
      "voteCount": 2501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.96956054585789
      }
    },
    {
      "id": "31122c86fe988a71ac9846aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1410.7244783873705,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.0378554855074,
        1425.4111012892333
      ],
      "voteCount": 1634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.14973434039088
      }
    },
    {
      "id": "6f635bdc5eb7db18339696dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1438.1363691725023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.7316396745032,
        1446.5410986705015
      ],
      "voteCount": 5681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.388711484813793
      }
    },
    {
      "id": "cddabb15cc13e6826ef1aa98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1416.4957255371794,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.5600216813523,
        1425.4314293930065
      ],
      "voteCount": 8390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.78554193237869
      }
    },
    {
      "id": "734d198d301bdb999a0b0632",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1423.1812494777334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.7993563312477,
        1446.5631426242192
      ],
      "voteCount": 610,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.31909090590983
      }
    },
    {
      "id": "9645a03ee2ff6cf464239fd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1450.0890304627562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.745569660016,
        1492.4324912654968
      ],
      "voteCount": 198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 466.741609488146
      }
    },
    {
      "id": "986d916286c0d1cd1f35d40a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1440.29651441148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.4514097878573,
        1479.141619035103
      ],
      "voteCount": 210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 392.80445884034
      }
    },
    {
      "id": "1251d531a5ed9eebc17e9166",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1453.5101838504797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.0162893249135,
        1464.004078376046
      ],
      "voteCount": 3210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.666667392209632
      }
    },
    {
      "id": "28776add8a178c8f8c79636d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1447.8555505118266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.8497042620027,
        1455.8613967616502
      ],
      "voteCount": 6471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.684696405059313
      }
    },
    {
      "id": "37a1c6211889bdb5c07375fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1422.5041302231755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.825047599797,
        1435.183212846554
      ],
      "voteCount": 2208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.848460096575266
      }
    },
    {
      "id": "dca9af719af7d5890fa87576",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1407.4557482321932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.8250530986058,
        1420.0864433657805
      ],
      "voteCount": 2161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.52965500976024
      }
    },
    {
      "id": "1dcbc0d8ed3dd400d6c5f803",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1415.853106290217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.089361951702,
        1436.6168506287322
      ],
      "voteCount": 782,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.23160238831295
      }
    },
    {
      "id": "675a94c42839ac542feacd68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1435.0334974613795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.5174771373213,
        1448.5495177854377
      ],
      "voteCount": 1916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.55558081639053
      }
    },
    {
      "id": "b666de87f5a712c3aa1eaf11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1413.124792363394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.4319694416376,
        1435.8176152851504
      ],
      "voteCount": 634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.05433617667768
      }
    },
    {
      "id": "90536a1389e2adb7fbc2ea72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1436.967554439461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.2457052240272,
        1460.6894036548947
      ],
      "voteCount": 594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.48761224989477
      }
    },
    {
      "id": "ac02a3610e4dd0b46d61a767",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1453.4612889898506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.9371264873632,
        1462.9854514923377
      ],
      "voteCount": 4136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.61333951704138
      }
    },
    {
      "id": "629227feb180bfa5531cf17f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1413.0526295093098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.4589141585034,
        1424.6463448601162
      ],
      "voteCount": 2607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.99041429558682
      }
    },
    {
      "id": "70bb935d90a2188353e21289",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1416.5498019790653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.225775423809,
        1426.8738285343218
      ],
      "voteCount": 3313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.746106177022778
      }
    },
    {
      "id": "731645089e057c7acb2e5c28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1346.9238803356593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.2484559911827,
        1400.599304680136
      ],
      "voteCount": 120,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 749.9888227460001
      }
    },
    {
      "id": "0639792953e4e9d599310ced",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1369.9598951423295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.8493444916426,
        1412.070445793017
      ],
      "voteCount": 192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 461.62110772898217
      }
    },
    {
      "id": "c4fe1a45c57121c1e1346892",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1441.9410886330859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.096135863461,
        1452.786041402711
      ],
      "voteCount": 2939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.616754224153098
      }
    },
    {
      "id": "dae37f6f5bb94716a2194fba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1418.3630372569523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.801194546601,
        1438.9248799673037
      ],
      "voteCount": 775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.0595881355388
      }
    },
    {
      "id": "6b94ac86a50a30e8231d8faf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1430.767193255601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.6643479106046,
        1443.8700386005971
      ],
      "voteCount": 1985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.692541075806304
      }
    },
    {
      "id": "00137199a6501202eb38c92f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1423.2863974422846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.8835098494233,
        1429.6892850351458
      ],
      "voteCount": 11941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.672239750681051
      }
    },
    {
      "id": "6fb9bb763e5313533282b312",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1404.8130488076756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.1119682157237,
        1424.5141293996276
      ],
      "voteCount": 845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.03780740787823
      }
    },
    {
      "id": "e29aaba9a5bc46a49e457e11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-exp",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1437.765098036095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.6023997381849,
        1471.9277963340048
      ],
      "voteCount": 301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 303.8142563723071
      }
    },
    {
      "id": "0cde04da2d7b05f656b3b0df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1462.8336643647792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.9588346848473,
        1476.7084940447112
      ],
      "voteCount": 1918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.114008149730765
      }
    },
    {
      "id": "f38173d4e517d37b78604e9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1474.6161780302562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.65858431558,
        1481.5737717449322
      ],
      "voteCount": 8193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.601491401580299
      }
    },
    {
      "id": "322fc37ab17744a6cf34f4d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1391.5418688142609,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.546003503908,
        1399.537734124614
      ],
      "voteCount": 6054,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.643120503307696
      }
    },
    {
      "id": "16a77137ba27e269fba64b74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1444.0614577912056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.9958472955987,
        1449.1270682868126
      ],
      "voteCount": 18078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.679860670370571
      }
    },
    {
      "id": "268265851b107a41fd69a2b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1410.875772323678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.6015434888047,
        1416.150001158551
      ],
      "voteCount": 27832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.241386957671619
      }
    },
    {
      "id": "3cfd194a9792005778a654f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1452.7132882305962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.69597992497,
        1464.7305965362223
      ],
      "voteCount": 2494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.59397292885099
      }
    },
    {
      "id": "5f076056f1652912c39dc45e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1428.8375579491299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3975229008433,
        1450.2775929974166
      ],
      "voteCount": 910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.66159845199189
      }
    },
    {
      "id": "64f125b2424d177eb5970704",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1412.7143387097087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.4873626169988,
        1434.941314802419
      ],
      "voteCount": 707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.6069926259517
      }
    },
    {
      "id": "eb735439bb07e7cab4ac0f33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1461.4152753417327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0656827004982,
        1467.7648679829672
      ],
      "voteCount": 10213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.495316647005927
      }
    },
    {
      "id": "c659cb6426f122e279479126",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1445.2049692003454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.420441860743,
        1449.9894965399478
      ],
      "voteCount": 21680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.959116817830572
      }
    },
    {
      "id": "e14ff40246c81f32c6bfa006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1420.1298462092695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.9923845388068,
        1427.267307879732
      ],
      "voteCount": 7671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.261461719409382
      }
    },
    {
      "id": "802aa37614aa28919320e524",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1389.232571974012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.940907630561,
        1396.5242363174627
      ],
      "voteCount": 7261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.840671312453292
      }
    },
    {
      "id": "1c52a849bae427973e89273f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1431.0274705552677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.0169794305355,
        1442.0379616799999
      ],
      "voteCount": 2898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.558561595071353
      }
    },
    {
      "id": "73fe272c8e9318231f51cc93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1438.5669218035184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.8853743072416,
        1446.2484692997953
      ],
      "voteCount": 6426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.360355191025102
      }
    },
    {
      "id": "74d24b3d7fd140121961358f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1445.9812422954137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.7217472324648,
        1460.2407373583626
      ],
      "voteCount": 1713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.9312453786822
      }
    },
    {
      "id": "81fcb6a26ab53cfae39b7fb3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1431.041913159077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.1530831774555,
        1442.9307431406983
      ],
      "voteCount": 2636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.79442756758776
      }
    },
    {
      "id": "163db8ee24a29059beed7111",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1462.8818604438748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.1972677503472,
        1468.566453137402
      ],
      "voteCount": 13504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.412063124879804
      }
    },
    {
      "id": "132e4ba4c5a1bd921a884b0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1401.4420830303163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.7881632844712,
        1408.0960027761614
      ],
      "voteCount": 9138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.525477702803158
      }
    },
    {
      "id": "425a4ee7ecdc1bdd90133fcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1419.1821649693522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.036982896929,
        1425.3273470417757
      ],
      "voteCount": 10737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.830448396271018
      }
    },
    {
      "id": "12619154dc2bd729e88295c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1392.1581354611517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.1540328699962,
        1426.162238052307
      ],
      "voteCount": 311,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.9999708446417
      }
    },
    {
      "id": "ac9d88b093eee6c3a9bac846",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1365.354251554792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.718708017641,
        1389.989795091943
      ],
      "voteCount": 624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.98946017627748
      }
    },
    {
      "id": "727c3536b243969ae8386ee3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1440.5704830914344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.2314997382857,
        1446.9094664445831
      ],
      "voteCount": 10364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.460273512507912
      }
    },
    {
      "id": "e218ffd0b1db3d64716dc218",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1425.5906685317639,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.6922994667457,
        1437.4890375967823
      ],
      "voteCount": 2456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.85349577216206
      }
    },
    {
      "id": "2d9a825d67fdafef472ea795",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1426.3266818851105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.6270118951888,
        1434.026351875032
      ],
      "voteCount": 6659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.432917732796787
      }
    },
    {
      "id": "bd2396866270edcf155fcd63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1422.2560817266144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.5655508790514,
        1425.9466125741774
      ],
      "voteCount": 40111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.5455327188313115
      }
    },
    {
      "id": "c9a851e30a07c0f12fbb27df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1400.7261116409584,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.6158559098917,
        1409.836367372025
      ],
      "voteCount": 4385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.605531481510667
      }
    },
    {
      "id": "3606e6f744678a4eef521419",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1409.7033295537449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.1054419462969,
        1428.3012171611927
      ],
      "voteCount": 1113,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.0390814020916
      }
    },
    {
      "id": "64db7e1e323e1df5c8365e33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1461.5014981803752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.6840773838298,
        1474.3189189769207
      ],
      "voteCount": 2375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.76663724486599
      }
    },
    {
      "id": "fc12656ebc8a05286030bdaa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1468.653849290358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.1143346253923,
        1475.1933639553238
      ],
      "voteCount": 10179,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.132555117582518
      }
    },
    {
      "id": "cab62eb7f9beae50fb327397",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1399.8396598411105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.930201003833,
        1407.749118678388
      ],
      "voteCount": 6531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.285359812156557
      }
    },
    {
      "id": "a58ed47669b277e8f8bfeac5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1436.3501135335105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.3791600951154,
        1441.3210669719058
      ],
      "voteCount": 20939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.43255055958864
      }
    },
    {
      "id": "7eb992b108ef27e92c72a58b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1414.9059893026576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.778661573754,
        1420.033317031561
      ],
      "voteCount": 32385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.843621360187254
      }
    },
    {
      "id": "4f984f2e51e0ecf3b51f221a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1448.4164573054638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.2441032394738,
        1459.5888113714536
      ],
      "voteCount": 3014,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.49325352738998
      }
    },
    {
      "id": "410987ca8b5c6996204c35dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1443.1241668356856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.9858309287222,
        1463.2625027426488
      ],
      "voteCount": 1053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.57254210743038
      }
    },
    {
      "id": "80cb1317ef9be8308fe17631",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1409.6525295660815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.2968932737415,
        1431.0081658584218
      ],
      "voteCount": 855,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.72135632272762
      }
    },
    {
      "id": "b44ee00a17a365c050aed30e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1455.2788119914762,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.1280260219314,
        1461.4295979610206
      ],
      "voteCount": 12008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.848385680810303
      }
    },
    {
      "id": "629fecc45ae358e8610c64fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1447.1042218705456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.457650743031,
        1451.75079299806
      ],
      "voteCount": 25294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.620422930669165
      }
    },
    {
      "id": "347bb7a1c74530a2e054eaf0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1420.1523558539136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.11366029521,
        1427.191051412617
      ],
      "voteCount": 8543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.89698457815585
      }
    },
    {
      "id": "19ea721fa6da4fa250cc418e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1394.3797966180011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.2665930073802,
        1401.493000228622
      ],
      "voteCount": 8289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.171471560121347
      }
    },
    {
      "id": "215534621945cf2b8e2ecef6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1429.7170583337788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.0346601556046,
        1440.3994565119533
      ],
      "voteCount": 3310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.70580609177082
      }
    },
    {
      "id": "fc5a8ca3011e594662a8508f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1449.6866426025185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.1873460009492,
        1457.1859392040876
      ],
      "voteCount": 7178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.640128176135264
      }
    },
    {
      "id": "a4e6d84fee2754b66f87844a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1439.8834956945675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.7482631593593,
        1453.0187282297757
      ],
      "voteCount": 2201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.913753291988655
      }
    },
    {
      "id": "37b2dbd438022ed2b6cc01cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1441.501302871295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.9900722992481,
        1453.012533443342
      ],
      "voteCount": 2952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.494299032699935
      }
    },
    {
      "id": "8f41a2b5bf96524970b5ac81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1456.1846538460588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.751813236065,
        1461.6174944560526
      ],
      "voteCount": 16420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.683476114489312
      }
    },
    {
      "id": "f1e3b02696a318d283cdad6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1409.282495056709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.768440338626,
        1415.7965497747916
      ],
      "voteCount": 10139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.046040280736317
      }
    },
    {
      "id": "d58701ee5a983a8effa965a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1419.7393359511054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.787794143616,
        1425.6908777585945
      ],
      "voteCount": 12465,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.220676711534324
      }
    },
    {
      "id": "04e449c3bb2e9ae3f0910336",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1372.1887487222289,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.6583651867352,
        1403.7191322577225
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 258.7988397896431
      }
    },
    {
      "id": "8aa7e9b028cf1568bdcebcd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1373.0181929830399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.3721413026083,
        1395.6642446634714
      ],
      "voteCount": 737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.50231790851603
      }
    },
    {
      "id": "dce060246aad923a01a730ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1439.9825586814475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.91455653582,
        1446.0505608270746
      ],
      "voteCount": 12217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.585069568098234
      }
    },
    {
      "id": "b56507cc3730ebd1c613e636",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1429.6958750221181,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.619010623785,
        1440.7727394204514
      ],
      "voteCount": 2954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.94019007521036
      }
    },
    {
      "id": "8e4f04706c90e19613e12c36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1428.575172498386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.2712276564548,
        1435.8791173403174
      ],
      "voteCount": 8034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.887331022940879
      }
    },
    {
      "id": "f8cb49525bc1f173beb1a85f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1424.3521771024466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.7519324483842,
        1427.9524217565092
      ],
      "voteCount": 46204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.3741768880300897
      }
    },
    {
      "id": "a8d24dfe1b30447ab36cf038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1422.5051905108803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.7449481048577,
        1431.265432916903
      ],
      "voteCount": 4812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.977266604776347
      }
    },
    {
      "id": "4bf5f1843ab053dfb0735e66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3.2",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1414.7983168091687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.3953679869342,
        1433.2012656314034
      ],
      "voteCount": 1212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.16143584030131
      }
    },
    {
      "id": "92cfba68b0e76a3ad85496dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1369.4273317479956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.1513624935567,
        1384.7033010024343
      ],
      "voteCount": 1450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.746515205490226
      }
    },
    {
      "id": "db66b0ef1cd2feb3b01fde56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1387.6236901649036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.5332643321974,
        1397.7141159976095
      ],
      "voteCount": 3280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.504694762534164
      }
    },
    {
      "id": "a5dcfc821be78ec0fe4c2c97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1349.057368736028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.046921361376,
        1359.06781611068
      ],
      "voteCount": 3623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.086198321544963
      }
    },
    {
      "id": "e300bb08f8814f3b73231c1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1370.3795471144344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.4610763427763,
        1376.2980178860926
      ],
      "voteCount": 12866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.1184880301916
      }
    },
    {
      "id": "090543f0c90915898927f9e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1327.9129951265913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.5245717232797,
        1335.3014185299028
      ],
      "voteCount": 14106,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.210434872431392
      }
    },
    {
      "id": "61814080e065f078b20f8a7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1347.134581148459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.5210824163769,
        1363.7480798805411
      ],
      "voteCount": 1236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.8498760507402
      }
    },
    {
      "id": "71b29b2c36080746f6670c96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1373.9360800686377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.946787500126,
        1410.9253726371492
      ],
      "voteCount": 242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.1687964344014
      }
    },
    {
      "id": "ea9baa68810f0b570b85ef7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1351.587921152898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.5963010312726,
        1376.5795412745233
      ],
      "voteCount": 493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.58955398375755
      }
    },
    {
      "id": "333d22cdc0e097131c2c9a78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1362.107492394745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.4439502473629,
        1371.771034542127
      ],
      "voteCount": 3637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.30952697739876
      }
    },
    {
      "id": "d671ad97ebf0d2f01ad73d6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1350.3343649907508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.220810782009,
        1358.4479191994928
      ],
      "voteCount": 5408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.136656924073698
      }
    },
    {
      "id": "7a62a9944836d66ebcf79cc6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1350.6114645257142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.2726455783977,
        1362.9502834730306
      ],
      "voteCount": 2241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.63245738688972
      }
    },
    {
      "id": "22906b4afe555c096b5a3fc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1348.692649103407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.418614972385,
        1357.9666832344287
      ],
      "voteCount": 4191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.38933516611655
      }
    },
    {
      "id": "89307f215c9c35e699c12c5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1384.632373613014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.255431223669,
        1401.0093160023587
      ],
      "voteCount": 1312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.81833062457838
      }
    },
    {
      "id": "2a962571679fa51be0c17ae2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1372.7899770471267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.1530153623398,
        1382.4269387319137
      ],
      "voteCount": 3766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.17597971212098
      }
    },
    {
      "id": "15d8ccd89e9e3b1b2c140ccc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1317.79352564914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.1255202855507,
        1329.4615310127297
      ],
      "voteCount": 2326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.44027295863438
      }
    },
    {
      "id": "66f8010e26e0328f77e500e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1393.309340725689,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.1893431020585,
        1411.4293383493196
      ],
      "voteCount": 1060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.4712569380222
      }
    },
    {
      "id": "0d91a7fd792265a0f1eb8a99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1384.3379401513193,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.9291816929567,
        1392.7466986096817
      ],
      "voteCount": 5176,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.40634563884427
      }
    },
    {
      "id": "25f3ca87d7de4b3601aaf432",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1355.8276337000325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.7295985041928,
        1363.9256688958724
      ],
      "voteCount": 5913,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.071164131653983
      }
    },
    {
      "id": "220f7270f783305fbf2715d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1343.4384657554733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.5736009924008,
        1350.3033305185454
      ],
      "voteCount": 8606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.267831158673356
      }
    },
    {
      "id": "843b06273d0a81a4b0640662",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1287.8309010439425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.2401378362817,
        1311.4216642516035
      ],
      "voteCount": 534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.87311583867526
      }
    },
    {
      "id": "584e1d0bff86da9bbd130b4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1282.6865378844982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.3640415599455,
        1318.0090342090512
      ],
      "voteCount": 295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 324.7929510207814
      }
    },
    {
      "id": "444332689c541c09f606fe81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1374.664225856204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.106491473385,
        1385.2219602390228
      ],
      "voteCount": 3123,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.01651703193778
      }
    },
    {
      "id": "c4265fb9a65c445dda4fe932",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1311.0485285529799,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.335363675557,
        1321.7616934304026
      ],
      "voteCount": 2721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.877165693554737
      }
    },
    {
      "id": "f8f0fdb75cfe2ffbef9c53ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1373.721098686135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.9460161656295,
        1383.4961812066408
      ],
      "voteCount": 3747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.873945743723645
      }
    },
    {
      "id": "b18adbd912fd3348a623ab69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1358.4243640918448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.6928335211644,
        1363.155894662525
      ],
      "voteCount": 21770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.8278332753900015
      }
    },
    {
      "id": "7f811f7606a61ffae3d63ad3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1355.715278832135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.3370786754072,
        1367.093478988863
      ],
      "voteCount": 2512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.70163389729354
      }
    },
    {
      "id": "c740948b8ae3437b61318c8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v3",
      "organization": "deepseek",
      "license": "DeepSeek",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1377.0749277696818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.806775359344,
        1426.3430801800198
      ],
      "voteCount": 127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 631.8825621277069
      }
    },
    {
      "id": "9347d906360886f538160176",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1488.3635690948088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.6771509153566,
        1509.0499872742607
      ],
      "voteCount": 883,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.3972365888444
      }
    },
    {
      "id": "e166496021340c2899297eb0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1477.990041873242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.7750020271305,
        1487.2050817193535
      ],
      "voteCount": 4709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.105393635347955
      }
    },
    {
      "id": "aba05cda87dc885723b05454",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1402.8342585307546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.6667513660232,
        1415.001765695486
      ],
      "voteCount": 2546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.539585484099995
      }
    },
    {
      "id": "3218ca13832f2b3540dbe8c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1449.0237009724792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.7474502237558,
        1456.299951721203
      ],
      "voteCount": 7617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.782218534554632
      }
    },
    {
      "id": "dfae11f2142f3b33b171f962",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1433.966900919461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.654621785457,
        1441.2791800534649
      ],
      "voteCount": 12362,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.919041861270474
      }
    },
    {
      "id": "13cbec498b18db4135f317a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1466.9450023176057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.464674860782,
        1482.4253297744294
      ],
      "voteCount": 1553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.38269088803891
      }
    },
    {
      "id": "fc5d5645d3166d4b7c0b974f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1466.035819734203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.542785091745,
        1493.528854376661
      ],
      "voteCount": 536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.76560107308845
      }
    },
    {
      "id": "b4e313794ac0fda302a57d01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1430.621507327864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.3077777496512,
        1466.9352369060769
      ],
      "voteCount": 264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 343.27764982816836
      }
    },
    {
      "id": "9750bc18e6416f74e33cab6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1461.3155597447446,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.582986800399,
        1470.0481326890902
      ],
      "voteCount": 5224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.85126843414572
      }
    },
    {
      "id": "96fbe82f1628d3d2cb0a6e1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1456.900756914298,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.324731234573,
        1463.4767825940232
      ],
      "voteCount": 10742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.257211324886784
      }
    },
    {
      "id": "1789498ea3390ac27ee25742",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1438.027256817549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.1509360334387,
        1448.9035776016594
      ],
      "voteCount": 3325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.794122576979053
      }
    },
    {
      "id": "c84b53f2712924dbda7d1be2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1406.3848349003458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.5835384350091,
        1417.1861313656827
      ],
      "voteCount": 3282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.37075516821925
      }
    },
    {
      "id": "f3657a279da9b067780136d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1465.4133957314768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.3089581226386,
        1482.5178333403148
      ],
      "voteCount": 1239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.15903217251518
      }
    },
    {
      "id": "b4c1e7084b22bb25d489b427",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1461.2840371047073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.5943697346672,
        1472.9737044747471
      ],
      "voteCount": 2783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.571986997764434
      }
    },
    {
      "id": "b7ce31918fc9ab30060eb792",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1449.6432674159767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.104165384143,
        1470.1823694478105
      ],
      "voteCount": 886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.81627864953963
      }
    },
    {
      "id": "294611211d054bb55589fd7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1467.9870566537945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.9643429708394,
        1486.0097703367499
      ],
      "voteCount": 1174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.55595222001841
      }
    },
    {
      "id": "24d8c31a51b255caa5974cb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1470.827964329007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.0003519970257,
        1478.6555766609881
      ],
      "voteCount": 6633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.95006420209692
      }
    },
    {
      "id": "69ff2124edd8a69aa32ab3a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1420.2522851327535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.3482315512156,
        1430.1563387142915
      ],
      "voteCount": 3885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.534642416979136
      }
    },
    {
      "id": "890dcbd5c2b4abcab943f54e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1432.8842322768432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.4389092377328,
        1441.3295553159537
      ],
      "voteCount": 5579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.56676969975747
      }
    },
    {
      "id": "fb2dd397b48b3ab987efb8bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1437.0348144333216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.1515522609668,
        1487.9180766056763
      ],
      "voteCount": 141,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 673.9904005616153
      }
    },
    {
      "id": "faa2abb2a241c82ca85bfb64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1391.5542109708772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.04099196352,
        1426.0674299782343
      ],
      "voteCount": 324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 310.0807120026771
      }
    },
    {
      "id": "2c61e0e7a7c2d94422833e52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1447.8938655345664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.906728274088,
        1455.881002795045
      ],
      "voteCount": 6767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.60680605869354
      }
    },
    {
      "id": "8cc413f20aab074a7bf34c6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1441.1826573298777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.8466653194446,
        1460.5186493403107
      ],
      "voteCount": 948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.32776126960366
      }
    },
    {
      "id": "a6b87017c0b63ff2198951e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1446.5674687694411,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.0731388801569,
        1458.0617986587256
      ],
      "voteCount": 2921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.393084963441275
      }
    },
    {
      "id": "0516dbfef5980830b051f359",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1437.1272586458122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.5785976187644,
        1442.6759196728601
      ],
      "voteCount": 16545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.014569628398686
      }
    },
    {
      "id": "5c16390d8162e27770588b17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1438.5888438628804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.4102226264015,
        1452.767465099359
      ],
      "voteCount": 1884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.33254072243353
      }
    },
    {
      "id": "ae054bbf10d0037d0768edc6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1439.429586663648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.8594211561635,
        1467.9997521711327
      ],
      "voteCount": 453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.4855153276296
      }
    },
    {
      "id": "e7e40a8b7a1213748061b2fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1480.3786744775098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.6151794945297,
        1501.1421694604899
      ],
      "voteCount": 848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.22890678555815
      }
    },
    {
      "id": "2212125dab7776b0355bc9ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1478.6508552841694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.444777457563,
        1487.856933110776
      ],
      "voteCount": 4780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.062417666166912
      }
    },
    {
      "id": "2cb103e17cddb0e0639d81de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1402.1882505518945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.0133661200096,
        1414.3631349837794
      ],
      "voteCount": 2545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.586333434382766
      }
    },
    {
      "id": "5414a4141638a9ab66fb9103",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1443.5311194492706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.2779705619448,
        1450.7842683365961
      ],
      "voteCount": 7702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.69484126663319
      }
    },
    {
      "id": "f71a6798042eb02dede67213",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1427.5712322268296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.276126668901,
        1434.8663377847583
      ],
      "voteCount": 12481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.853738276362842
      }
    },
    {
      "id": "805db6f8685d8964cf0e4f83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1456.1777162301614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.683636362988,
        1471.6717960973347
      ],
      "voteCount": 1549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.49357916765785
      }
    },
    {
      "id": "b9fe1df58636a704b95dcf0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1436.0065976697417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.9734006630752,
        1462.0397946764083
      ],
      "voteCount": 621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.42447258238482
      }
    },
    {
      "id": "508aecc7f5eab8e5fa5211bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1429.0654772469304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.6732068376743,
        1464.4577476561865
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 326.07737403666005
      }
    },
    {
      "id": "2d8495e63d6806162d04e6d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1460.526833309972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.8285667551422,
        1469.2250998648021
      ],
      "voteCount": 5281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.695601226099367
      }
    },
    {
      "id": "c711649e86ef60fb5ab2fc70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1455.5093241327886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.9626859970156,
        1462.0559622685616
      ],
      "voteCount": 10901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.156821635019902
      }
    },
    {
      "id": "28b454c6bd80d56acfda67a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1425.8274982900407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.1109314911123,
        1436.544065088969
      ],
      "voteCount": 3300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.896143448738705
      }
    },
    {
      "id": "2832dd80651f153a94e719af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1400.0387549495563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.1193989520405,
        1410.9581109470723
      ],
      "voteCount": 3248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.038295857338515
      }
    },
    {
      "id": "fa7a2f3aeced841d3e8bcb71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1446.4495166239697,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.3609746244942,
        1463.5380586234448
      ],
      "voteCount": 1247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.01754471366789
      }
    },
    {
      "id": "a70528e7669a941bb370e7c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1458.014989716264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.5294962666715,
        1469.5004831658562
      ],
      "voteCount": 2800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.340224882793926
      }
    },
    {
      "id": "233bfaed12098aa77365e2d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1448.104888009041,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.8104852672063,
        1467.3992907508753
      ],
      "voteCount": 957,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.90953217008351
      }
    },
    {
      "id": "5a1a565ec7c7acb57e386687",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1455.4409434564125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.8892865834382,
        1472.992600329387
      ],
      "voteCount": 1202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.19366427334582
      }
    },
    {
      "id": "2dcb73263c419ac3d210d4f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1468.6943209496023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.8768323594884,
        1476.5118095397163
      ],
      "voteCount": 6709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.908833260776515
      }
    },
    {
      "id": "43bd35e3f525826d782bb07b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1417.3841590047934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.5197766870983,
        1427.2485413224886
      ],
      "voteCount": 3853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.330491110684896
      }
    },
    {
      "id": "71243031e354b95d801534a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1431.7282592387132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.2714433453039,
        1440.1850751321228
      ],
      "voteCount": 5565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.61733742133434
      }
    },
    {
      "id": "3c1efca5781760bd460bef19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1394.4178136430778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.7978517854667,
        1448.0377755006891
      ],
      "voteCount": 135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 748.4397058022253
      }
    },
    {
      "id": "0816f087c4921cc53013bf07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1384.2028887119795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.0961499086166,
        1420.3096275153423
      ],
      "voteCount": 265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 339.3753904092873
      }
    },
    {
      "id": "58d3482f3dc55f713128be78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1444.9683963923599,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9826997939397,
        1452.95409299078
      ],
      "voteCount": 6890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.60081576782229
      }
    },
    {
      "id": "0b08588d3901033cfb3c5331",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1445.7701009795853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.8868252305451,
        1464.6533767286255
      ],
      "voteCount": 992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.82361718766491
      }
    },
    {
      "id": "e9a75d22dda3cfa24d8b0b66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1448.8977712475248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.7191519148553,
        1460.0763905801944
      ],
      "voteCount": 3002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.52970707679079
      }
    },
    {
      "id": "333c54190f99420c45614cf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1432.7101262008289,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.15716526328,
        1438.2630871383778
      ],
      "voteCount": 16725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.026996152564182
      }
    },
    {
      "id": "b21729586535cf92712ed2a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1430.1765980765567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.3719175443373,
        1443.981278608776
      ],
      "voteCount": 1933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.608550681327
      }
    },
    {
      "id": "ad4d1ef6d3017538684674cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-flash",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1433.7439784092703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.0231801854336,
        1461.464776633107
      ],
      "voteCount": 482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.03927935580913
      }
    },
    {
      "id": "c190a9da78e01991bfaebfa4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1514.9139124808685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.580479570225,
        1536.247345391512
      ],
      "voteCount": 842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.47461628410605
      }
    },
    {
      "id": "59ac45a86866bb011ac63381",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1493.560125055447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.0923583614212,
        1503.027891749473
      ],
      "voteCount": 4535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.334522210577482
      }
    },
    {
      "id": "7a74cc681db0171ce6e162e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1437.7232086292672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.90339095751,
        1450.5430263010244
      ],
      "voteCount": 2404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.7826335796567
      }
    },
    {
      "id": "a3a02fd01b326ff6f628d885",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1467.8851181654754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.435784963174,
        1475.334451367777
      ],
      "voteCount": 7304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.445700904034133
      }
    },
    {
      "id": "2b250e06e07548a4a5d99ff8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1460.9904026841893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.6026748624192,
        1468.3781305059595
      ],
      "voteCount": 11920,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.20775932167734
      }
    },
    {
      "id": "29b9c6f30d25cfe8168b4313",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1478.6028651778004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.4532271067105,
        1494.75250324889
      ],
      "voteCount": 1416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.89368883044861
      }
    },
    {
      "id": "fd5f7eb8aca2ef687947bce8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1429.687314047822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.1894935765997,
        1456.185134519044
      ],
      "voteCount": 574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.77808574770776
      }
    },
    {
      "id": "39370bd7c8633dca4caa4e68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1428.1658609304907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.9705019418748,
        1466.3612199191064
      ],
      "voteCount": 244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 379.7738089525125
      }
    },
    {
      "id": "2645f5a0f3a508c72b18555a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1485.6860420989462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.748370170856,
        1494.6237140270366
      ],
      "voteCount": 5036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.79469889507749
      }
    },
    {
      "id": "63927ecf99fd1012abf9fa11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1478.1094497640456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.4389670050805,
        1484.7799325230108
      ],
      "voteCount": 10401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.582927818450662
      }
    },
    {
      "id": "62ff93cdc0b05346aeb305a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1454.3763123253516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.3347153987088,
        1465.4179092519942
      ],
      "voteCount": 3185,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.737126019332543
      }
    },
    {
      "id": "5fbd65a43f20d7964924e450",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1423.934381333956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.9100576811836,
        1434.9587049867284
      ],
      "voteCount": 3203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.637905721222282
      }
    },
    {
      "id": "e20004eee104cff3fa1781e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1483.8690777444203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.6696965053939,
        1501.0684589834468
      ],
      "voteCount": 1247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.0068686957628
      }
    },
    {
      "id": "5b1fb886eb5db76ccc280a9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1474.775592946851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.6543264734846,
        1486.8968594202174
      ],
      "voteCount": 2544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.24721486713946
      }
    },
    {
      "id": "4bb5540f436a87bd15e43077",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1471.1297736405454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.1054982341118,
        1492.154049046979
      ],
      "voteCount": 836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.06570211930465
      }
    },
    {
      "id": "91b8fe2543816e2545a34fd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1490.35276863486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.8350193556812,
        1508.8705179140388
      ],
      "voteCount": 1101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.26479610279056
      }
    },
    {
      "id": "d71692a0cc4b1b9565555d3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1487.786920576453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.7538154928586,
        1495.8200256600471
      ],
      "voteCount": 6344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.798508143947384
      }
    },
    {
      "id": "d72a494d3a941cdb16e1da16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1439.4466768099855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.2040697389577,
        1449.6892838810134
      ],
      "voteCount": 3730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.3101976380192
      }
    },
    {
      "id": "1a593628f6421024a0036ff1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1448.8850366697695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.2044262977236,
        1457.5656470418155
      ],
      "voteCount": 5307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.61572411640649
      }
    },
    {
      "id": "22db3a1b0c912a35eeceb2b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1426.4518894409305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.1613980429481,
        1461.7423808389128
      ],
      "voteCount": 276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 324.20464236188985
      }
    },
    {
      "id": "f48d0b6f7a215b41ee5154ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1473.6778628774598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.4480470243027,
        1481.9076787306167
      ],
      "voteCount": 6400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.63128856464853
      }
    },
    {
      "id": "3b6ebeef724bf3b8ccc71ab4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1478.5457737114782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.4870632951277,
        1498.6044841278285
      ],
      "voteCount": 886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.73934053373577
      }
    },
    {
      "id": "c41a554ea9ad0f4996ca2ebc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1461.3792089623196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.5939728619828,
        1473.1644450626563
      ],
      "voteCount": 2787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.15600125464376
      }
    },
    {
      "id": "7ffe819fc9b5d93d5fc2ecb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1457.7941844387415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.1179793927079,
        1463.4703894847753
      ],
      "voteCount": 15852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.387257348966383
      }
    },
    {
      "id": "6800e2b08231482534857b01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1453.8735012713096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.2550585521535,
        1468.4919439904654
      ],
      "voteCount": 1784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.62961299546827
      }
    },
    {
      "id": "19f5832ada13e4a7afae3b3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro-thinking",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1438.200602571086,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.450161680688,
        1465.9510434614838
      ],
      "voteCount": 480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.46732388825023
      }
    },
    {
      "id": "811453ed651e6dde04ce9d13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1516.1367469476859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.993682694315,
        1536.2798112010564
      ],
      "voteCount": 936,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.62212337918567
      }
    },
    {
      "id": "765cc62eeb1efc282cf41665",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1500.427943255175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.4064245891975,
        1509.4494619211523
      ],
      "voteCount": 4940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.186690483869526
      }
    },
    {
      "id": "31d8ce53c5437d7f620c2d08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1439.4222709024816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.124972536388,
        1451.7195692685755
      ],
      "voteCount": 2580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.36617679983542
      }
    },
    {
      "id": "659f19194cb9bf4d04ffdfef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1461.2763079840156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.9628105076306,
        1468.5898054604008
      ],
      "voteCount": 7722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.923680516619028
      }
    },
    {
      "id": "9fcd7e72215c6729252838af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1456.9092079084282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.6123460466924,
        1464.206069770164
      ],
      "voteCount": 12621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.86040968145341
      }
    },
    {
      "id": "2ab5d9a7b98347d6883c195d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1472.7233164513682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.1569908050003,
        1488.2896420977359
      ],
      "voteCount": 1551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.077727873439216
      }
    },
    {
      "id": "578d4cdb83afd3012e90a9df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1465.2883647206024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4173052480814,
        1492.1594241931232
      ],
      "voteCount": 600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.96344588832116
      }
    },
    {
      "id": "0a68d7229eb26bbd88523204",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1472.1057767912953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.0873301530503,
        1507.1242234295403
      ],
      "voteCount": 286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 319.22549796694983
      }
    },
    {
      "id": "2382a61229e922b7c2c2290d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1474.6766385350415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.007655090643,
        1483.3456219794402
      ],
      "voteCount": 5357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.56321217200422
      }
    },
    {
      "id": "e99ce13c32b19b4bd1387a87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1475.024263577547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.48769578198,
        1481.5608313731138
      ],
      "voteCount": 10940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.122524160840317
      }
    },
    {
      "id": "e0a5874893a0c53bb31d142c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1455.7224093231928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.9708679096345,
        1466.473950736751
      ],
      "voteCount": 3269,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.09160013501591
      }
    },
    {
      "id": "86b70c431e1b96c49a47e73d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1433.95032833991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.0734363781835,
        1444.8272203016363
      ],
      "voteCount": 3321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.797357011806163
      }
    },
    {
      "id": "125e207e9091efa049e2f18f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1467.9808591175783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.4178702774304,
        1485.5438479577265
      ],
      "voteCount": 1238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.2972494036599
      }
    },
    {
      "id": "e59338521143b913c781ee67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1476.1547952011763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.5055479219895,
        1487.8040424803633
      ],
      "voteCount": 2801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.326413351248526
      }
    },
    {
      "id": "ddb90da380681e37695fbb2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1463.241206629418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.883840713075,
        1482.598572545761
      ],
      "voteCount": 973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.54305140553106
      }
    },
    {
      "id": "be73b6f569f2c2e0b69a6998",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1480.052674390989,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.0724021688563,
        1498.032946613122
      ],
      "voteCount": 1178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.15818163673144
      }
    },
    {
      "id": "4c093d310bdf97fb5bd0734c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1488.9929016186134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.2868411927548,
        1496.698962044472
      ],
      "voteCount": 6927,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.458545843855745
      }
    },
    {
      "id": "c3f7a59c3698331a9a485ad7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1449.3224301560138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.3968791842644,
        1459.247981127763
      ],
      "voteCount": 3892,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.64561191234974
      }
    },
    {
      "id": "1866b0bcb6c8b240f4ed3d20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1447.1415522273255,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.679790361154,
        1455.6033140934974
      ],
      "voteCount": 5516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.639120506531818
      }
    },
    {
      "id": "097da19730bc6e534fa8cc9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1448.7162723554504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.3584128732236,
        1500.0741318376772
      ],
      "voteCount": 142,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 686.6218938459292
      }
    },
    {
      "id": "a4de85c78d8d9740311e125a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1416.8324455628654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.856909530659,
        1448.8079815950714
      ],
      "voteCount": 343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 266.1579759853219
      }
    },
    {
      "id": "68f34b01dc64cf1e023e5708",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1468.6311454599665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.5910139992952,
        1476.6712769206376
      ],
      "voteCount": 6777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.827907553411013
      }
    },
    {
      "id": "edec9fb527fd4d8444bb2509",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1436.534151477746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.0965568753197,
        1454.9717460801726
      ],
      "voteCount": 1045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.49369747037841
      }
    },
    {
      "id": "89655707f6be451c0067a33b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1471.9287676491813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.6697520442347,
        1483.187783254128
      ],
      "voteCount": 3100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.99929487973184
      }
    },
    {
      "id": "eb16f2d87fddddf348c3db62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1454.1640520568938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.6173352839155,
        1459.710768829872
      ],
      "voteCount": 16920,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.008953992660318
      }
    },
    {
      "id": "637a731ebd36170e8348eecb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1453.3525351560843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.3069263007517,
        1467.3981440114171
      ],
      "voteCount": 1885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.35526301993631
      }
    },
    {
      "id": "0307d1268f99f4eeff82857c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "deepseek-v4-pro",
      "organization": "deepseek",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1445.8377626332742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.104362733936,
        1472.5711625326126
      ],
      "voteCount": 504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.04251757898754
      }
    },
    {
      "id": "ca74da528dbc1f3b7f6d369c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1513.0719269120711,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.7554779699278,
        1527.3883758542147
      ],
      "voteCount": 1978,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.354915379768784
      }
    },
    {
      "id": "215d97c4b5631a1229cface6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1510.8654658903843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.010542417769,
        1517.7203893629994
      ],
      "voteCount": 10045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.232325793074518
      }
    },
    {
      "id": "894fbbcd627773e70e67509e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1403.6674515666466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.2343972086169,
        1412.100505924676
      ],
      "voteCount": 5880,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.512864285405097
      }
    },
    {
      "id": "10b10e86ca336c09af40ee9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1460.5611840792096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0503689825312,
        1466.0719991758883
      ],
      "voteCount": 17499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.9056120206679745
      }
    },
    {
      "id": "744dee304f0aad6413454a7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1460.2993784624744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.5460699233647,
        1466.052687001584
      ],
      "voteCount": 27820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.616663796544614
      }
    },
    {
      "id": "a02ccf8400bb9532496da79e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1479.0172854338002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.8636435605545,
        1490.170927307046
      ],
      "voteCount": 3198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.38450100426782
      }
    },
    {
      "id": "ea2698dfc7ab93d8d421ba58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1493.5439243922242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.26539413167,
        1514.8224546527783
      ],
      "voteCount": 1048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.86560033136176
      }
    },
    {
      "id": "7eefec53f68946c2fcbd9348",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1435.9600882671002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.209294938079,
        1460.7108815961212
      ],
      "voteCount": 635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.47112776942996
      }
    },
    {
      "id": "4320c0cd6c9f68e1654bce97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1477.1049452595907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.5838213023376,
        1483.626069216844
      ],
      "voteCount": 11198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.070028249886947
      }
    },
    {
      "id": "341fd7c2a98e488919fbaea2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1480.9150881430285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.7669455195878,
        1486.0632307664694
      ],
      "voteCount": 22986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.899298862326207
      }
    },
    {
      "id": "1cde9accb4d5c4edff0462d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1460.089035639514,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.2976358415424,
        1467.8804354374854
      ],
      "voteCount": 7114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.802827427123633
      }
    },
    {
      "id": "98fb77449549baa81c6b89ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1416.3691026953702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.6255260682092,
        1424.1126793225314
      ],
      "voteCount": 7225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.609429068377226
      }
    },
    {
      "id": "4b71e176ab39bec0b8ecd5aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1468.500529705957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.1855324113892,
        1480.815527000525
      ],
      "voteCount": 2697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.47957415245987
      }
    },
    {
      "id": "a3464edef49b9d7eae8a5b8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1471.0798162901165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.812022294479,
        1479.3476102857537
      ],
      "voteCount": 5960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.794390294139763
      }
    },
    {
      "id": "9c18caf421eb179d507ad99a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1449.2883661336436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.4441888813958,
        1463.1325433858917
      ],
      "voteCount": 2002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.89282789110503
      }
    },
    {
      "id": "cb83dd462c243c1167922c14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1493.1085184160283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.7041086324418,
        1505.5129281996149
      ],
      "voteCount": 2711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.0549346644652
      }
    },
    {
      "id": "c0acf5a67a9e931103c25b50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1499.943659802355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.9491572354948,
        1505.938162369215
      ],
      "voteCount": 14372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.354274691300509
      }
    },
    {
      "id": "c8fe815cc5a8a91627e83656",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1409.8316242466133,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.722057260597,
        1416.9411912326293
      ],
      "voteCount": 8488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.158007175908942
      }
    },
    {
      "id": "3a288534e008441b221cb30e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1433.4858253999607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.1689545280758,
        1439.802696271846
      ],
      "voteCount": 11609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.387422975123568
      }
    },
    {
      "id": "312877a0a9cc2bdb1feb04b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1387.3493694887045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.5716940690302,
        1423.127044908379
      ],
      "voteCount": 321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 333.21769624079394
      }
    },
    {
      "id": "21bb6e96cfedddf188509d43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1434.8983397881843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.8841543929018,
        1459.9125251834669
      ],
      "voteCount": 637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.88329517391696
      }
    },
    {
      "id": "ac5b323dd8fbd21293da4e02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1451.657061852202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.373256803446,
        1457.940866900958
      ],
      "voteCount": 13121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.278961127490765
      }
    },
    {
      "id": "d5457b0156844b86c651556f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1449.9824978944246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.2948360138669,
        1462.6701597749825
      ],
      "voteCount": 2260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.90511248699887
      }
    },
    {
      "id": "9d3a570c1f6a83cdff79381e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1446.4585142236879,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.447289113427,
        1454.4697393339488
      ],
      "voteCount": 6617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.707123716005018
      }
    },
    {
      "id": "ad2ce392a512b0c43414cfb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1455.9259443333185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.7518060309455,
        1460.1000826356915
      ],
      "voteCount": 37742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.535628619386946
      }
    },
    {
      "id": "e85b8a9c5c6210a696c93fc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1448.9258255083546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.0883354977434,
        1458.7633155189656
      ],
      "voteCount": 4201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.192567257921443
      }
    },
    {
      "id": "c5f6f49c0802d5fc3fd7d5fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dola-seed-2.0-pro",
      "organization": "bytedance",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1471.8975081920585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.235930405678,
        1490.5590859784393
      ],
      "voteCount": 1240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.6568316185183
      }
    },
    {
      "id": "e0c9c72958fe1aa14b8a6050",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 994.9388068419062,
      "unit": "Arena rating",
      "confidenceInterval": [
        945.5983426659476,
        1044.2792710178649
      ],
      "voteCount": 177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 633.7387744427684
      }
    },
    {
      "id": "66f74db1ee200e1d0e6997b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 960.885787344241,
      "unit": "Arena rating",
      "confidenceInterval": [
        926.9274465354724,
        994.8441281530096
      ],
      "voteCount": 396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.19036108686134
      }
    },
    {
      "id": "babcf35494d87cf3f57b360f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 968.0202987634598,
      "unit": "Arena rating",
      "confidenceInterval": [
        940.2338152850944,
        995.8067822418252
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.9884005352858
      }
    },
    {
      "id": "e94f7e37ec6a29afc389ddd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 993.226397165346,
      "unit": "Arena rating",
      "confidenceInterval": [
        978.2788056289269,
        1008.1739887017652
      ],
      "voteCount": 2765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.162927983504126
      }
    },
    {
      "id": "12983ccd514534cb7aebf786",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 748.5736242882512,
      "unit": "Arena rating",
      "confidenceInterval": [
        726.6737714441717,
        770.4734771323306
      ],
      "voteCount": 2379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.849328595867
      }
    },
    {
      "id": "27ac0208fd19a5542009904e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 971.6485522712615,
      "unit": "Arena rating",
      "confidenceInterval": [
        944.8054601097936,
        998.4916444327293
      ],
      "voteCount": 523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.57238601840967
      }
    },
    {
      "id": "aca3da4db99df420283134ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 970.7371547504491,
      "unit": "Arena rating",
      "confidenceInterval": [
        946.3869917400027,
        995.0873177608955
      ],
      "voteCount": 615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.3503305153678
      }
    },
    {
      "id": "b01cc3533ea419567fd2a104",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 901.0166593833353,
      "unit": "Arena rating",
      "confidenceInterval": [
        857.2515879103019,
        944.7817308563685
      ],
      "voteCount": 233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 498.60783895989226
      }
    },
    {
      "id": "2cc49a42bf59839dd9851d40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 935.4847487215432,
      "unit": "Arena rating",
      "confidenceInterval": [
        907.6720137407626,
        963.2974837023237
      ],
      "voteCount": 558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.36835072759166
      }
    },
    {
      "id": "a6765773d795950360546962",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 984.1977455639008,
      "unit": "Arena rating",
      "confidenceInterval": [
        954.9854090920257,
        1013.4100820357758
      ],
      "voteCount": 589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 222.14493034493648
      }
    },
    {
      "id": "a5a400be605d6c8f99918e1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 933.9603392056015,
      "unit": "Arena rating",
      "confidenceInterval": [
        903.3287200683026,
        964.5919583429004
      ],
      "voteCount": 343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 244.25514752830117
      }
    },
    {
      "id": "fd4a71ee88650ab1bea37be0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 962.3503785508312,
      "unit": "Arena rating",
      "confidenceInterval": [
        938.5865797000108,
        986.1141774016515
      ],
      "voteCount": 824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.00616671460523
      }
    },
    {
      "id": "eb739d2923d516b49c949111",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 971.9147516095397,
      "unit": "Arena rating",
      "confidenceInterval": [
        948.6654155722158,
        995.1640876468637
      ],
      "voteCount": 732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.70998842016448
      }
    },
    {
      "id": "f8c8b9c9fc766f85e05fc27c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 934.7597050060008,
      "unit": "Arena rating",
      "confidenceInterval": [
        913.4697729156054,
        956.0496370963963
      ],
      "voteCount": 899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.99194773920546
      }
    },
    {
      "id": "8767f6cdfd242d6f92b1e4c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 949.3348989963126,
      "unit": "Arena rating",
      "confidenceInterval": [
        920.6516006854085,
        978.0181973072167
      ],
      "voteCount": 370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 214.17165727775512
      }
    },
    {
      "id": "b12ae0e86f5af3f66c4f34bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 864.9060647091575,
      "unit": "Arena rating",
      "confidenceInterval": [
        829.186452065755,
        900.6256773525599
      ],
      "voteCount": 356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 332.1370309949524
      }
    },
    {
      "id": "e320efd873f5f994742d8d21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolly-v2-12b",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 979.7076024424512,
      "unit": "Arena rating",
      "confidenceInterval": [
        966.1631336582337,
        993.2520712266687
      ],
      "voteCount": 3412,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.75598105031684
      }
    },
    {
      "id": "c27091704b2701bf7df2ace4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1134.052764539484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.5550990188378,
        1167.55043006013
      ],
      "voteCount": 291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.1009042940437
      }
    },
    {
      "id": "a1145b731fe43dc2b9a479ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1181.7084523073217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.951189991813,
        1198.4657146228303
      ],
      "voteCount": 1302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.09875060954796
      }
    },
    {
      "id": "3d990b1bb8298dd96060bcbc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1006.0678276838712,
      "unit": "Arena rating",
      "confidenceInterval": [
        983.7090637130239,
        1028.4265916547185
      ],
      "voteCount": 1098,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.13658342788875
      }
    },
    {
      "id": "c09bd6d0ad7909c2999aabf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1166.0346671733355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.7631129067722,
        1197.3062214398992
      ],
      "voteCount": 286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.56737970965034
      }
    },
    {
      "id": "261d833982cdd1cf5777e429",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1154.044185276234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.56728942033,
        1181.5210811321379
      ],
      "voteCount": 359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.5346606890786
      }
    },
    {
      "id": "87f0ab12d23c6f969abd2389",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1118.197607322707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.0088020796682,
        1151.3864125657456
      ],
      "voteCount": 282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 286.7391907278923
      }
    },
    {
      "id": "962cda5f14dbe5aab3ff154d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1171.702184239177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.2444548667122,
        1205.1599136116422
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 291.40483004288404
      }
    },
    {
      "id": "762eac3fadb68b0024c95758",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1110.0631822565028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1075.8572738679518,
        1144.2690906450541
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.5832906974997
      }
    },
    {
      "id": "813c4fc3a60900619e740251",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1153.1800117505397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.0182195813572,
        1181.3418039197222
      ],
      "voteCount": 366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.45452032645449
      }
    },
    {
      "id": "dc98d83c0817ccf1085d37ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1130.691319060526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.012868529464,
        1159.369769591588
      ],
      "voteCount": 382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 214.09926885900023
      }
    },
    {
      "id": "517cd4c46b1dfd920f221be1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1126.6230319655224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.1863187802483,
        1151.0597451507967
      ],
      "voteCount": 497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.44952560273953
      }
    },
    {
      "id": "d1fb6284d4f380a95e09feac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1124.380136816347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.9063237287514,
        1156.8539499039425
      ],
      "voteCount": 219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 274.51772508068524
      }
    },
    {
      "id": "6c1a83e0624ae98b478dc0b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1083.4945472717507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1042.6378059562207,
        1124.3512885872806
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 434.5415085362012
      }
    },
    {
      "id": "7d680b066fe961bfb97fbe30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "dolphin-2.2.1-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1151.108982928693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.7571659853047,
        1166.4607998720812
      ],
      "voteCount": 1679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.35124557204489
      }
    },
    {
      "id": "9c40b02b683bb03e2f328dd1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1496.34992618924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.986585374967,
        1511.713267003513
      ],
      "voteCount": 1635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.44338700287205
      }
    },
    {
      "id": "0fabbf7654bc28f253e44a3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1492.19525442203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.253354787325,
        1499.1371540567352
      ],
      "voteCount": 8166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.54470574530645
      }
    },
    {
      "id": "83f76c48dea852030e92bbdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1423.7540982776989,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.2364917073683,
        1432.2717048480292
      ],
      "voteCount": 5357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.885955849926027
      }
    },
    {
      "id": "587624a2c54cdff22a70f68c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1452.5935951108856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.1934475784115,
        1457.9937426433598
      ],
      "voteCount": 15348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.59128100381883
      }
    },
    {
      "id": "6da77c3a706a7a38de72592e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1449.305681944006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.6762008199585,
        1454.9351630680535
      ],
      "voteCount": 23971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.24974552773675
      }
    },
    {
      "id": "586a7f3d1df4557c940f2054",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1447.2732518455377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.4151108034519,
        1459.1313928876239
      ],
      "voteCount": 2568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.60471595231004
      }
    },
    {
      "id": "a28b64f209c42f2c310cd0a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1474.0726845585598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.347403534045,
        1495.7979655830745
      ],
      "voteCount": 906,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.86682159691985
      }
    },
    {
      "id": "c8e1cc4192ddd3fc44f990b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1427.4701780759558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.1700340693908,
        1451.7703220825208
      ],
      "voteCount": 630,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.71686286437938
      }
    },
    {
      "id": "4e092aa07095f68f8ef31c24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1468.2753061220785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.6670241178788,
        1474.8835881262783
      ],
      "voteCount": 9277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.367918565671198
      }
    },
    {
      "id": "c03ee2d11672c260351265e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1466.185021091137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.2085095542536,
        1471.1615326280203
      ],
      "voteCount": 19949,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.446943266271245
      }
    },
    {
      "id": "c7248d1e417800ea6976d4aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1440.3725518883987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.7061958541224,
        1448.038907922675
      ],
      "voteCount": 6500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.299660256065314
      }
    },
    {
      "id": "3b0c2c78a0b33ef0a5a2ce6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1414.726899428097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.8957664441546,
        1422.55803241204
      ],
      "voteCount": 6348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.964415258553458
      }
    },
    {
      "id": "3216ff254b1d3a4c1bac5a88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1442.7878884425463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.4744772647343,
        1455.1012996203585
      ],
      "voteCount": 2468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.469405221027166
      }
    },
    {
      "id": "b9da69e1edbcb0384d3c2ff7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1457.4068006314983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.252748594072,
        1465.5608526689248
      ],
      "voteCount": 5635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.30815498291418
      }
    },
    {
      "id": "1bb874c36fffe95975348c9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1434.294685094199,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.5481700354542,
        1449.041200152944
      ],
      "voteCount": 1607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.60862618292897
      }
    },
    {
      "id": "68b7a963d91588b38c67f91d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1472.7229102125011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.070571739135,
        1485.3752486858675
      ],
      "voteCount": 2318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.672103311965316
      }
    },
    {
      "id": "9a798692b41913fe4c34078c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1486.023952351119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.1995671819473,
        1491.848337520291
      ],
      "voteCount": 12551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.8308801896094
      }
    },
    {
      "id": "201f37d00965834e7e985fc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1421.0666496270146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.9488603580555,
        1428.184438895974
      ],
      "voteCount": 7706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.188459499913886
      }
    },
    {
      "id": "94f1b194d195f3e47d327d4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1427.6582821753443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.3029176514178,
        1434.0136466992708
      ],
      "voteCount": 10009,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.514406145497867
      }
    },
    {
      "id": "feb5d6a40ad6019f9b5f0933",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1379.1453063368529,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.8549335467583,
        1413.4356791269474
      ],
      "voteCount": 330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 306.0893584878239
      }
    },
    {
      "id": "248bd2e0c1d869428ceb44a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1401.662415455075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.4436801157485,
        1426.8811507944017
      ],
      "voteCount": 583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 165.55809701484273
      }
    },
    {
      "id": "b401c4ff13afd26ab899c357",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1441.2989725439531,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.8773467760648,
        1447.7205983118415
      ],
      "voteCount": 10316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.734796187495371
      }
    },
    {
      "id": "3ba8f307fe4b3c17a7789d12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1438.670423434038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.8043748326515,
        1451.5364720354244
      ],
      "voteCount": 2094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.091756111374586
      }
    },
    {
      "id": "730d06fd06cd430915bd43d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1441.2641527056373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.9804071448145,
        1449.5478982664602
      ],
      "voteCount": 5469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.86312016330602
      }
    },
    {
      "id": "60602e091650703187696b1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1448.0495035277067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.0059520041048,
        1452.0930550513085
      ],
      "voteCount": 34159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.256275984514905
      }
    },
    {
      "id": "1a8fd44374b260a53d296065",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1448.156381310741,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4052769048023,
        1457.9074857166795
      ],
      "voteCount": 3768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.752064664416686
      }
    },
    {
      "id": "e9e6dbd803bda88ca0c9976b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-0110",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1441.5990815185883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.857471044689,
        1460.3406919924876
      ],
      "voteCount": 1111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.43608705713113
      }
    },
    {
      "id": "7011f5d3d13a1131e2db8d03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1491.6158321007772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.3525101065666,
        1525.8791540949878
      ],
      "voteCount": 280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 305.60661688072787
      }
    },
    {
      "id": "9c601a9a2d40db65d66960d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1433.2954138767236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.5670758008491,
        1452.0237519525983
      ],
      "voteCount": 916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.30662684570348
      }
    },
    {
      "id": "a9e91d7643eda6b1e973360a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1407.126815163532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.94537511903,
        1429.308255208034
      ],
      "voteCount": 717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.08058225102602
      }
    },
    {
      "id": "18f42e4129097ca52e2dcf7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1423.3143531614635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.6441799451732,
        1434.9845263777538
      ],
      "voteCount": 2377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.45344340658865
      }
    },
    {
      "id": "ec0d0304ded176f2952efddc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1408.0725191480503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.4696968894648,
        1420.6753414066359
      ],
      "voteCount": 3258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.3465655354337
      }
    },
    {
      "id": "d450e62fb90bce0b6ad55633",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1435.9591463312404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.576040372559,
        1470.3422522899218
      ],
      "voteCount": 276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 307.74714256921396
      }
    },
    {
      "id": "539398bd5136302f70be1f61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1426.7172147558877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.5183140906713,
        1441.916115421104
      ],
      "voteCount": 1368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.135118509320336
      }
    },
    {
      "id": "e40e9b61bb114abd9405a05c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1427.8781984533348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.5093666172934,
        1439.247030289376
      ],
      "voteCount": 2532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.64615979218812
      }
    },
    {
      "id": "beb3970608155c83f866533e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1410.7458543591342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.9767609219862,
        1429.514947796282
      ],
      "voteCount": 921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.70445002680871
      }
    },
    {
      "id": "3e6f78680413b1e833e6652b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1391.7385535353176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.7387327096983,
        1410.7383743609366
      ],
      "voteCount": 910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.97294315923502
      }
    },
    {
      "id": "5c415efcb59d52f33445807d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1450.245669387883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.8946017702472,
        1480.596737005519
      ],
      "voteCount": 322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 239.80142662673308
      }
    },
    {
      "id": "66ac73c78646d46aeca43bea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1438.1045926681518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.7868098568433,
        1458.42237547946
      ],
      "voteCount": 776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.46237761125008
      }
    },
    {
      "id": "a1335ad75d9e486471e57224",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1422.7401562721777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.5164183519382,
        1456.9638941924172
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.9008962229617
      }
    },
    {
      "id": "c1c08474f30889104d804670",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1443.450097363615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.6269639671536,
        1480.2732307600766
      ],
      "voteCount": 245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 352.9761000766347
      }
    },
    {
      "id": "b640d51e4707b7c439c4849e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1440.0992221239233,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.0361740931585,
        1454.162270154688
      ],
      "voteCount": 1632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.48286865661681
      }
    },
    {
      "id": "6752e0afdd6b22df2291698b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1403.8705618902056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.5637471839068,
        1421.1773765965045
      ],
      "voteCount": 1107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.97189798432872
      }
    },
    {
      "id": "735bf977a738f1bd0ebc1776",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1400.8391376218458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.2573436513019,
        1416.4209315923897
      ],
      "voteCount": 1311,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.20315137378175
      }
    },
    {
      "id": "f8f87b2631a50876d2ed585f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1420.440617337357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.7305031844733,
        1437.1507314902408
      ],
      "voteCount": 1152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.68798860948064
      }
    },
    {
      "id": "8205bd26d2b5c071f3ee4081",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1399.9095288252436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.717014854027,
        1434.10204279646
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.34479874512476
      }
    },
    {
      "id": "7a3dca855b282351af586a2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1420.2125747403873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.6281860860759,
        1441.7969633946987
      ],
      "voteCount": 703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.27836203023114
      }
    },
    {
      "id": "47939953325111ce5c270b72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1419.5677210690806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.7521839673634,
        1428.3832581707977
      ],
      "voteCount": 4708,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.230255748963017
      }
    },
    {
      "id": "991f1b6727a7852a88f3fef8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1022",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1391.7865037073568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.162452681992,
        1425.4105547327217
      ],
      "voteCount": 259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 294.30923514417617
      }
    },
    {
      "id": "13725502d21673ae15264ad8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1479.915075307465,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.4261679947936,
        1505.4039826201365
      ],
      "voteCount": 534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.12439422598285
      }
    },
    {
      "id": "a8ac608a98c9e69c7b27ab05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1471.63538117694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.4711037874897,
        1484.7996585663902
      ],
      "voteCount": 1960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.112601039174216
      }
    },
    {
      "id": "b8afb54467c87fb6b8951c95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1420.915901763954,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.7208593620164,
        1436.1109441658914
      ],
      "voteCount": 1550,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.10459160797627
      }
    },
    {
      "id": "58524700519f746d753a12de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1451.3078535702493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.393719805545,
        1460.2219873349538
      ],
      "voteCount": 4590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.685313700872598
      }
    },
    {
      "id": "0cb1142f5fc642d45ec1f2a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1450.6686100828795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.4480700443823,
        1459.8891501213766
      ],
      "voteCount": 6909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.131789658535787
      }
    },
    {
      "id": "e20650370141f61a69cc0ef8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1449.4764587843829,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.0172435166896,
        1471.9356740520764
      ],
      "voteCount": 672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.30854031892153
      }
    },
    {
      "id": "9275a226ed3bfa48a4da1eb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1480.437705597399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.336884821042,
        1520.5385263737558
      ],
      "voteCount": 228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 418.61071587562225
      }
    },
    {
      "id": "bc39d8ff8dac320a9f11d500",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1459.2183888245258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.2955153213588,
        1501.1412623276926
      ],
      "voteCount": 215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 457.5155962351211
      }
    },
    {
      "id": "ca53da28109e25d97991fbf2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1460.4748273507582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.8553219834475,
        1472.094332718069
      ],
      "voteCount": 2526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.14625856553277
      }
    },
    {
      "id": "5ce0a06eb7d3512c8de46554",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1463.5287447850083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0680322421988,
        1471.9894573278177
      ],
      "voteCount": 5210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.63449800540064
      }
    },
    {
      "id": "852d987f85c802c242afe6cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1440.1486405484043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.556628948363,
        1453.7406521484459
      ],
      "voteCount": 1891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.09182864083857
      }
    },
    {
      "id": "ec7269deb466f4fd52cec73c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1411.3912949376665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.0591072400698,
        1424.7234826352635
      ],
      "voteCount": 1898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.270762515121305
      }
    },
    {
      "id": "8fe8b53410ecc99e0368be0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1457.6309220745973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.0030311546727,
        1478.258812994522
      ],
      "voteCount": 763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.76778475720438
      }
    },
    {
      "id": "8e54e3fa133066520aff3b2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1480.560471893114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.9189717795957,
        1495.2019720066323
      ],
      "voteCount": 1615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.80523847328944
      }
    },
    {
      "id": "5c86d5d7cff25033e4afd853",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1416.4347818929207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.7603097133751,
        1443.109254072466
      ],
      "voteCount": 477,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.22324441545695
      }
    },
    {
      "id": "6a1aa4376c6e5840edd1c341",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1492.984098539638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.0596350100384,
        1515.9085620692374
      ],
      "voteCount": 679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.80506616103196
      }
    },
    {
      "id": "3f094886f5539b1bcaf520f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1477.4093773001055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.1898115621384,
        1487.6289430380725
      ],
      "voteCount": 3350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.187464124308757
      }
    },
    {
      "id": "952a2b6220897a6e9866036d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1414.8963249688422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.2702219832593,
        1427.5224279544252
      ],
      "voteCount": 2156,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.49946258534745
      }
    },
    {
      "id": "757593ea65e600e4803ec9af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1419.9591970734775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.6073342009538,
        1431.3110599460015
      ],
      "voteCount": 2627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.54579515010943
      }
    },
    {
      "id": "dc68dd20bbf6daf3dc07d85f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1372.9850509162175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.513373947278,
        1419.456727885157
      ],
      "voteCount": 150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 562.1866226110528
      }
    },
    {
      "id": "9315654b86781ddaf50f2582",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1434.929282172708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.1487881789678,
        1446.7097761664484
      ],
      "voteCount": 2456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.12691043020817
      }
    },
    {
      "id": "5c950028e4e5b136aed0d73b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1407.3365982008154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.3033697520439,
        1430.369826649587
      ],
      "voteCount": 618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.10628657928308
      }
    },
    {
      "id": "956b33b8b414949ddb0474a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1428.1278058986459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.9905723503468,
        1443.265039446945
      ],
      "voteCount": 1544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.648131137417145
      }
    },
    {
      "id": "810f2c706c99beccd7d96329",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1449.165768028484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.6224308809026,
        1455.7091051760656
      ],
      "voteCount": 9752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.145573342156405
      }
    },
    {
      "id": "3a08b47d2fb36b78d4f9b73b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1446.4963023820821,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.0007733566883,
        1464.991831407476
      ],
      "voteCount": 956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.05069919957505
      }
    },
    {
      "id": "6124b7f7210a9de3df27c6a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.0-preview-1203",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1473.2470396790616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.7499430765602,
        1511.744136281563
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 385.7978221290782
      }
    },
    {
      "id": "9dacb75d3de020288f4356c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1510.5011260483204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.104184633954,
        1533.8980674626869
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.50233911094693
      }
    },
    {
      "id": "b4f088127ac38b9c88ff3a5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1515.1719803229423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1505.189810823867,
        1525.1541498220176
      ],
      "voteCount": 3943,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.939027999333423
      }
    },
    {
      "id": "f35ac4914b1eb9a15f534b8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1441.5255480192418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.2165630008428,
        1454.8345330376405
      ],
      "voteCount": 2181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.10984797383824
      }
    },
    {
      "id": "11437cc37f823e8e87db930c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1478.197300356025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.564785290999,
        1485.8298154210509
      ],
      "voteCount": 6874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.164886293723448
      }
    },
    {
      "id": "75cef06cbd53a712b779739f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1477.7876339662728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.0508618070398,
        1485.5244061255057
      ],
      "voteCount": 10968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.582008356155157
      }
    },
    {
      "id": "23ee95c975668313d6bcfe86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1475.154970506753,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.7691891909603,
        1492.5407518225456
      ],
      "voteCount": 1234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.68505327513759
      }
    },
    {
      "id": "b979c407322711d7f72f0042",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1507.2384642116876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.3141713887924,
        1535.162757034583
      ],
      "voteCount": 528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.98698126299305
      }
    },
    {
      "id": "df151fe3eedab662d5988e2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1472.515425421601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.148662407339,
        1506.8821884358629
      ],
      "voteCount": 282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 307.4546559541218
      }
    },
    {
      "id": "e890f34777ece13f0dc37a6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1489.0474722091385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.8391476527083,
        1498.2557967655687
      ],
      "voteCount": 4639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.073187581699216
      }
    },
    {
      "id": "bb15961d3d9f215a00b31acd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1488.1821112727066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.2049228340165,
        1495.1592997113964
      ],
      "voteCount": 9286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.672570703281254
      }
    },
    {
      "id": "05a85d46f6a910fb97bbe13c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1471.3954733397163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.7182619823225,
        1483.07268469711
      ],
      "voteCount": 2849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.496219392143644
      }
    },
    {
      "id": "5ae21de61e8470c56ce04527",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1433.4949397402202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.6205125021304,
        1445.3693669783102
      ],
      "voteCount": 2753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.705332222515246
      }
    },
    {
      "id": "9e2fe2b976f954fb64f2da25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1468.298298240719,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.0124209049554,
        1486.584175576483
      ],
      "voteCount": 1142,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.04331493476202
      }
    },
    {
      "id": "5aaa8c3e950858eb5c4c7291",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1490.009907081129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.445311805904,
        1502.5745023563543
      ],
      "voteCount": 2414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.09612045813431
      }
    },
    {
      "id": "6d0fd58d47a1d42440f904f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1493.0732884379524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.1186384704827,
        1515.0279384054222
      ],
      "voteCount": 759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.47489838952005
      }
    },
    {
      "id": "182ad20a1e1ffb261402c385",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1489.8411107437867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.9417231639866,
        1508.740498323587
      ],
      "voteCount": 1088,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.98208507854477
      }
    },
    {
      "id": "3df6ac6f48c975890cae6eca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1508.3322085647494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1499.8812033055326,
        1516.783213823966
      ],
      "voteCount": 5671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.59176245924271
      }
    },
    {
      "id": "d49daf520c4ece3e9d386270",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1444.9658194733088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.1396266450222,
        1455.7920123015954
      ],
      "voteCount": 3317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.51092218504255
      }
    },
    {
      "id": "f0bc000636332983b924b5e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1457.9894984488387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.5660834903197,
        1467.4129134073578
      ],
      "voteCount": 4430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.116413223556417
      }
    },
    {
      "id": "7e2575d86d540742ab4a8e07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1420.5864059788128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.5665794615043,
        1460.6062324961213
      ],
      "voteCount": 237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 416.92143251611583
      }
    },
    {
      "id": "ada68808f34b7f17c1cdc54a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1468.2585760013017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.4340032629684,
        1477.0831487396351
      ],
      "voteCount": 5528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.2717477002827
      }
    },
    {
      "id": "32bc170e06bdce5799283365",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1479.861767266812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.8756814748547,
        1499.8478530587693
      ],
      "voteCount": 836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.9822744244075
      }
    },
    {
      "id": "a1ca402c8cdece2d6cbe6269",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1474.851162201474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.4493181750443,
        1487.2530062279036
      ],
      "voteCount": 2490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.03836626526585
      }
    },
    {
      "id": "8cbbc98f60a3d6384c3c93a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1470.4548279693813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.6032561813495,
        1476.3063997574134
      ],
      "voteCount": 14675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.913512805612967
      }
    },
    {
      "id": "d6cbacc7c2a1686d62dc92cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1470.0491855122398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.9733848403985,
        1485.1249861840813
      ],
      "voteCount": 1637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.16496219423903
      }
    },
    {
      "id": "421b3667698b933c69099fde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ernie-5.1",
      "organization": "baidu",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1455.0687175672563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.6424549853148,
        1483.4949801491978
      ],
      "voteCount": 475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.35040126539158
      }
    },
    {
      "id": "193f664517ba4c7b9db9fb13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1152.625304394029,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.697809330632,
        1189.5527994574259
      ],
      "voteCount": 270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 354.979697897896
      }
    },
    {
      "id": "f2cb03900f0e87d03df2176e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1170.0202484336176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.3468583902775,
        1188.6936384769576
      ],
      "voteCount": 1047,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.77163441978699
      }
    },
    {
      "id": "46662988c9914cfda0d0581d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 999.4177624143006,
      "unit": "Arena rating",
      "confidenceInterval": [
        975.4851125350324,
        1023.3504122935685
      ],
      "voteCount": 944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.10266046796576
      }
    },
    {
      "id": "098261feb72f433b3cce0399",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1125.4514180879567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1090.54937495113,
        1160.3534612247831
      ],
      "voteCount": 231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 317.1067742709246
      }
    },
    {
      "id": "a913583e9e7b97f247f303c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1139.419509913452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.2117714947508,
        1176.6272483321532
      ],
      "voteCount": 229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 360.3880356016241
      }
    },
    {
      "id": "d80297d990fde9ef9e49d9fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1161.8074148515902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.5254125649794,
        1203.089417138201
      ],
      "voteCount": 206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 443.6345129124164
      }
    },
    {
      "id": "45580ef5b81af5c42ffa3d73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1148.538055105971,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.9291106573287,
        1181.146999554613
      ],
      "voteCount": 309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 276.8071474113803
      }
    },
    {
      "id": "57692f1f6339710c29220926",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1168.801736921077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.850675937531,
        1200.7527979046233
      ],
      "voteCount": 342,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 265.75068108886336
      }
    },
    {
      "id": "0cd3b0391ea1d0eb42015d11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1131.3440216693557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.5810924399261,
        1160.106950898785
      ],
      "voteCount": 389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 215.36247984761158
      }
    },
    {
      "id": "f10efbacff7d38dcebe442de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1095.6790836248992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1055.848402012417,
        1135.5097652373813
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 412.9897707528349
      }
    },
    {
      "id": "c61c847b57b00f88af256196",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "falcon-180b-chat",
      "license": "Falcon-180B TII License",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1146.3208266425909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.2393357686683,
        1163.4023175165134
      ],
      "voteCount": 1295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.95482448076277
      }
    },
    {
      "id": "649e5f5621d220a7b4e854d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 957.2626245258598,
      "unit": "Arena rating",
      "confidenceInterval": [
        916.0729882074003,
        998.4522608443192
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 441.6515233502865
      }
    },
    {
      "id": "3949f2160022016c48da905d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 906.2573926961478,
      "unit": "Arena rating",
      "confidenceInterval": [
        875.779201483568,
        936.7355839087277
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 241.8144207576659
      }
    },
    {
      "id": "3c51bebc66f769fdd99662cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 990.5621880277488,
      "unit": "Arena rating",
      "confidenceInterval": [
        966.3048438108871,
        1014.8195322446104
      ],
      "voteCount": 744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.17585738143913
      }
    },
    {
      "id": "74f6f2ecd7ab085bfd57d118",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1022.4590252960318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1009.0264941456205,
        1035.8915564464432
      ],
      "voteCount": 3442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.9698886617682
      }
    },
    {
      "id": "f50681dac2b274f9149c88c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 767.3498037492875,
      "unit": "Arena rating",
      "confidenceInterval": [
        748.1151617959255,
        786.5844457026495
      ],
      "voteCount": 2836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.31014370920252
      }
    },
    {
      "id": "bb13052dff6b0f1862dbe081",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 945.2390764493709,
      "unit": "Arena rating",
      "confidenceInterval": [
        922.1207803942051,
        968.3573725045369
      ],
      "voteCount": 690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.1282940780622
      }
    },
    {
      "id": "e9b62604be671f6663fe5e88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 936.5929439540168,
      "unit": "Arena rating",
      "confidenceInterval": [
        915.1673057427191,
        958.0185821653146
      ],
      "voteCount": 797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.5009485168642
      }
    },
    {
      "id": "a6c34d83984a785d932d0455",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1002.4723408806942,
      "unit": "Arena rating",
      "confidenceInterval": [
        964.2335450272592,
        1040.711136734129
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 380.6380795867711
      }
    },
    {
      "id": "9f7737c7bc33064ee6cd417e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 957.2520420446342,
      "unit": "Arena rating",
      "confidenceInterval": [
        932.4590058153226,
        982.0450782739458
      ],
      "voteCount": 719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.01594033927117
      }
    },
    {
      "id": "f66533791c40cd8e0d55e7dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1032.0864227776358,
      "unit": "Arena rating",
      "confidenceInterval": [
        985.8372864775272,
        1078.3355590777444
      ],
      "voteCount": 184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 556.8151861952081
      }
    },
    {
      "id": "a70a3d7ac7d339eac7814f97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 994.6501361788321,
      "unit": "Arena rating",
      "confidenceInterval": [
        969.3473232166641,
        1019.9529491410001
      ],
      "voteCount": 685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.66385706114897
      }
    },
    {
      "id": "648c3483d81914b3f988bc2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 921.1137248772657,
      "unit": "Arena rating",
      "confidenceInterval": [
        892.6037513055148,
        949.6236984490166
      ],
      "voteCount": 400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.59112488288022
      }
    },
    {
      "id": "fa06bcf705012daefbcdde8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 967.1265318352226,
      "unit": "Arena rating",
      "confidenceInterval": [
        946.4368451631234,
        987.8162185073219
      ],
      "voteCount": 955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.43244131204634
      }
    },
    {
      "id": "c13996ae7b8f71dc50fa3577",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 995.2906163906277,
      "unit": "Arena rating",
      "confidenceInterval": [
        974.1492291464131,
        1016.4320036348423
      ],
      "voteCount": 940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.35117685032961
      }
    },
    {
      "id": "70f48efd7f7d9f4c03462554",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 954.7344538956423,
      "unit": "Arena rating",
      "confidenceInterval": [
        936.0279400081763,
        973.4409677831082
      ],
      "voteCount": 1134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.09395106277023
      }
    },
    {
      "id": "1d02ed6f1bfce1b8fd2e0405",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 918.9954959388767,
      "unit": "Arena rating",
      "confidenceInterval": [
        893.0524222630938,
        944.9385696146596
      ],
      "voteCount": 462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.20507264620053
      }
    },
    {
      "id": "59b73e92bc5f0f5d35d98778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 938.2832822090596,
      "unit": "Arena rating",
      "confidenceInterval": [
        907.3570067953899,
        969.2095576227293
      ],
      "voteCount": 387,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.97690060083283
      }
    },
    {
      "id": "548fd6fac3b51104db650bd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "fastchat-t5-3b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 990.709960021027,
      "unit": "Arena rating",
      "confidenceInterval": [
        978.3256769653229,
        1003.0942430767311
      ],
      "voteCount": 4203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.925058151758584
      }
    },
    {
      "id": "38072a8bd8bb2fb849fb3379",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1294.7970117761715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.6918441161797,
        1304.902179436163
      ],
      "voteCount": 7043,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.582196556798916
      }
    },
    {
      "id": "2440a66d08edc7c41e930c82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1309.7291143603059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.062029332084,
        1317.3961993885277
      ],
      "voteCount": 10680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.302570084393688
      }
    },
    {
      "id": "a3089bbe30576e43044df617",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1263.1520578080824,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.6991131688528,
        1271.605002447312
      ],
      "voteCount": 9031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.600296504277193
      }
    },
    {
      "id": "e5c7881422ad251eb05f34f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1289.9558884113603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.6031901894085,
        1295.3085866333122
      ],
      "voteCount": 33810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.458462941458529
      }
    },
    {
      "id": "ce2b5c16b6cf0546bde04fa0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1208.5850165188106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.7759385393977,
        1215.3940944982237
      ],
      "voteCount": 40479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.069254180199524
      }
    },
    {
      "id": "57dadd179ddde24c51f76c64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1264.3044282167393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.9110731366068,
        1276.697783296872
      ],
      "voteCount": 3194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.98357324952334
      }
    },
    {
      "id": "2957de47694d373395328ed7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1298.4243392264425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.431531559575,
        1322.41714689331
      ],
      "voteCount": 919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.85317990087893
      }
    },
    {
      "id": "a414cec4e5bbaa288e1c1e24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1265.4101906773756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.2708550356824,
        1280.5495263190687
      ],
      "voteCount": 2169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.66469884751363
      }
    },
    {
      "id": "8be3f60e20c6d87e2a368e3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1293.132860249168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.7339769114587,
        1300.5317435868774
      ],
      "voteCount": 10974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.250699330714308
      }
    },
    {
      "id": "a809112e221645e148e92f02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1287.7848713839603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.5035261681849,
        1294.0662165997355
      ],
      "voteCount": 18228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.27091518128411
      }
    },
    {
      "id": "90788017e0b95d09ec3ce800",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1284.9426573190603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.6185484690911,
        1294.2667661690293
      ],
      "voteCount": 7261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.631768269316964
      }
    },
    {
      "id": "679399bf50efdf7694d77010",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1255.405282387118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.4321502793473,
        1263.3784144948881
      ],
      "voteCount": 9767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.548618265930703
      }
    },
    {
      "id": "ce4648eeb409be0b86db6af2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1306.6993569677759,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.4863925130576,
        1318.9123214224944
      ],
      "voteCount": 3784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.828087904705455
      }
    },
    {
      "id": "20eb18ea120c0df601e606e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1294.0899905213391,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.0260686680695,
        1302.1539123746086
      ],
      "voteCount": 10875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.927640953831318
      }
    },
    {
      "id": "c1aa8118babe645a11b956d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1271.9736270872038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.663592870103,
        1280.2836613043046
      ],
      "voteCount": 7315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.976678109205757
      }
    },
    {
      "id": "cc5fc35c1ed3d9371f6c1f8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1270.0110676716172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.2103266477247,
        1282.8118086955096
      ],
      "voteCount": 3461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.655402129536796
      }
    },
    {
      "id": "c17813e7d2df78fb4b2e43f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1306.2475807899891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.590512495516,
        1312.904649084462
      ],
      "voteCount": 17507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.53638769691981
      }
    },
    {
      "id": "bc6c9c84fbfdbd90d4060061",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1290.7556629930882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.8567156318027,
        1297.6546103543737
      ],
      "voteCount": 16463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.389947911816838
      }
    },
    {
      "id": "64b2d8cd354bb4ef820900c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1263.7238073130925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.756830411503,
        1269.6907842146816
      ],
      "voteCount": 23685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.268565668931753
      }
    },
    {
      "id": "3744df9e5dfa68be57a79f13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1222.9896194045773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.598494371839,
        1240.3807444373151
      ],
      "voteCount": 1522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.73343019454184
      }
    },
    {
      "id": "2e6f1f384d0f905e2699e236",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1246.7417463956494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.8468336374415,
        1265.6366591538572
      ],
      "voteCount": 2083,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.9380594208153
      }
    },
    {
      "id": "a11f0462f73953e6225763c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1299.5186454031186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.7525484609346,
        1308.2847423453027
      ],
      "voteCount": 7837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.00397744362227
      }
    },
    {
      "id": "afca333df75f87061d65e973",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1256.690683558294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.7041459805187,
        1264.6772211360696
      ],
      "voteCount": 8392,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.604312439224667
      }
    },
    {
      "id": "a1039427393feb5a38028b76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1269.7568182854247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.8190606823516,
        1277.694575888498
      ],
      "voteCount": 11065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.40210105226722
      }
    },
    {
      "id": "cd1e013710c8ddf516d1a608",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1285.756856437718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.2630523018443,
        1290.2506605735916
      ],
      "voteCount": 62833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.256928826831858
      }
    },
    {
      "id": "e4e7c75616c17cb485cb975c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1284.8760999875658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.7618667803927,
        1293.990333194739
      ],
      "voteCount": 7468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.624401257990726
      }
    },
    {
      "id": "da1fb71e58cb5350a7a9e3fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1275.6431688499208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.3108339039209,
        1297.9755037959205
      ],
      "voteCount": 1077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.82911113184934
      }
    },
    {
      "id": "65c6fa8281cfdf859bede3fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1322.5743694184494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.20491974268,
        1333.9438190942185
      ],
      "voteCount": 2980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.64981689599164
      }
    },
    {
      "id": "e27a16ebf4b2071a4343d512",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1316.266034003804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.2200619038435,
        1324.3120061037644
      ],
      "voteCount": 5892,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.852365222451024
      }
    },
    {
      "id": "4c304dc1edb42a0acf4fa827",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1298.3592141741756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.4263002841244,
        1307.2921280642267
      ],
      "voteCount": 5017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.772564354249177
      }
    },
    {
      "id": "1eafefd84bb2a0f1369b8a9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1314.0917008000076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.680220855781,
        1319.5031807442342
      ],
      "voteCount": 18364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.623175609487518
      }
    },
    {
      "id": "672844231a05f2101661f8d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1246.816596505088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.257759417343,
        1253.375433592833
      ],
      "voteCount": 22474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.198439434476546
      }
    },
    {
      "id": "17381caf2ff5dfdae4cce02e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1281.0401029538612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.974114851973,
        1294.1060910557494
      ],
      "voteCount": 2116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.44146170694497
      }
    },
    {
      "id": "15b3d249c820021500aacdb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1286.676221950077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.9053132720542,
        1321.4471306280993
      ],
      "voteCount": 295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 314.7283744868886
      }
    },
    {
      "id": "3898a898552e1315ed4b3037",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1278.346761451096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.805600524971,
        1299.8879223772212
      ],
      "voteCount": 739,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.79307255501854
      }
    },
    {
      "id": "c5fb87b04d44c1b0e5d9883f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1313.1666686874732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.9685632586452,
        1321.364774116301
      ],
      "voteCount": 5484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.49567957363533
      }
    },
    {
      "id": "938eeaf924bbcc861b57ccce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1302.7735437040344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.0440513938236,
        1309.503036014245
      ],
      "voteCount": 9262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.788767982941309
      }
    },
    {
      "id": "c3b40c5d56d45af82ff47b76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1298.2248526907479,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.5336066428558,
        1307.9160987386397
      ],
      "voteCount": 4259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.449110180441764
      }
    },
    {
      "id": "4c3b06437e0f86173e9be3a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1273.3309143300812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.1043552809372,
        1281.5574733792255
      ],
      "voteCount": 5693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.617336784786076
      }
    },
    {
      "id": "ab24fe9cff4ae5cff1ceab65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1327.459406575409,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.0341277732105,
        1340.884685377608
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.919183396114676
      }
    },
    {
      "id": "c5766ec01b6ec2193e5e66ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1327.2218560061851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.8894982902466,
        1335.5542137221237
      ],
      "voteCount": 6083,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.07339043499465
      }
    },
    {
      "id": "5374b564690ca498099eaec9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1301.9950655580647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.899640826579,
        1311.0904902895509
      ],
      "voteCount": 4114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.53524348626987
      }
    },
    {
      "id": "970e48bf38f70c21584a0b7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1325.4503985964166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.422255087451,
        1340.478542105382
      ],
      "voteCount": 1696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.791492468803945
      }
    },
    {
      "id": "f244578c82117d1148af130a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1321.8152992875027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.9273330692995,
        1328.703265505706
      ],
      "voteCount": 9225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.350536824064417
      }
    },
    {
      "id": "0a5c303d9da0c04043514bc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1308.884833053191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.9172751373324,
        1315.8523909690493
      ],
      "voteCount": 9441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.637611276559083
      }
    },
    {
      "id": "d6d1b976760584fa56ff261f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1289.3229161842946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.438629311142,
        1295.2072030574475
      ],
      "voteCount": 14561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.013459110646451
      }
    },
    {
      "id": "eea0903da30e99455de7cc8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1257.9071132218965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.3183912842776,
        1279.495835159515
      ],
      "voteCount": 753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.32706262242459
      }
    },
    {
      "id": "143d7321ca39764ce7e5ecf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1233.462290972202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.0040316459101,
        1261.9205502984942
      ],
      "voteCount": 502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.82421071902667
      }
    },
    {
      "id": "8c256e7596e07590ecbbb2df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1322.0373365318724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.5762689318792,
        1330.4984041318653
      ],
      "voteCount": 5463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.636062046531944
      }
    },
    {
      "id": "9986e013c8925407b4ca4287",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1288.2076562871248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.6498214698177,
        1296.765491104432
      ],
      "voteCount": 4789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.06477205112458
      }
    },
    {
      "id": "7cf994155fd0944d81e66d2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1276.7884054145034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.4938048935783,
        1285.0830059354282
      ],
      "voteCount": 6324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.909966242797932
      }
    },
    {
      "id": "00978d982bf96e168d536f1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1309.2498963852527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.0427974713782,
        1313.4569952991274
      ],
      "voteCount": 34902,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.607541587007221
      }
    },
    {
      "id": "9f3d3aa28ffee214ae1d8f5f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1307.1841086066859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.3237089927957,
        1316.0445082205763
      ],
      "voteCount": 5101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.436684338488543
      }
    },
    {
      "id": "0d6d5c333a1ec7a99de8a29b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1268.7317026484884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.8380764663093,
        1302.6253288306675
      ],
      "voteCount": 283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 299.0473019231051
      }
    },
    {
      "id": "20af98c95054e27179d787d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1271.0206028137654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.4303441754919,
        1282.6108614520392
      ],
      "voteCount": 2914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.96955234256627
      }
    },
    {
      "id": "f3e33edf02e01851156804d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1272.2453925587165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.11407851287,
        1280.3767066045625
      ],
      "voteCount": 6069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.211760218798812
      }
    },
    {
      "id": "5c3073a9813cd314a1eb2385",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1237.7747818316957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.9198572043701,
        1246.6297064590212
      ],
      "voteCount": 5031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.411435815273656
      }
    },
    {
      "id": "feb47fb311f6b2b534c1fe0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1266.4562772803577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.9230956516137,
        1271.9894589091016
      ],
      "voteCount": 18467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.96991465110551
      }
    },
    {
      "id": "ef3d7f114a32d189aa13baf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1164.1919498172338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.3452494174107,
        1171.0386502170563
      ],
      "voteCount": 22722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.202995932796108
      }
    },
    {
      "id": "984b1f1e6aeee8d0f8f602ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1238.7050458655117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.6488613238562,
        1251.7612304071674
      ],
      "voteCount": 2111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.37479685255747
      }
    },
    {
      "id": "0e3c0cde32ac82e7c21bd939",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1276.6379389782805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.365869819798,
        1309.9100081367633
      ],
      "voteCount": 331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 288.1797352930674
      }
    },
    {
      "id": "70b648c6da5be8958d80e414",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1228.839625200104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.8749806573724,
        1249.8042697428355
      ],
      "voteCount": 798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.41390922515883
      }
    },
    {
      "id": "5b32db285e03c826b388a95b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1266.3478894600203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.099200138323,
        1274.5965787817174
      ],
      "voteCount": 5581,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.712249096447756
      }
    },
    {
      "id": "0825ea15eba5d6c42671a4f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1258.6261319731327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.9014172721618,
        1265.3508466741034
      ],
      "voteCount": 9654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.772035031545881
      }
    },
    {
      "id": "7d990c1e0832672a53ee8c5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1255.1896541261992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.4681455177172,
        1264.9111627346815
      ],
      "voteCount": 4291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.602041577453626
      }
    },
    {
      "id": "72e60be769de2830ab20b6b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1217.05007456328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.5941260751204,
        1225.5060230514396
      ],
      "voteCount": 5700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.613518502195078
      }
    },
    {
      "id": "9c4afcc8be7e10abe0ece31b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1294.19730858832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.7261471942252,
        1307.6684699824152
      ],
      "voteCount": 2128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.240435932348966
      }
    },
    {
      "id": "55809438d16169de64ce5729",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1276.3341148489308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.9937785426998,
        1284.6744511551615
      ],
      "voteCount": 6236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.108019101051333
      }
    },
    {
      "id": "709facb2c6f7aa1257455a76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1252.6829029735911,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.7816726059407,
        1261.5841333412413
      ],
      "voteCount": 4171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.625472185502822
      }
    },
    {
      "id": "881a902ebf6d700b736e0328",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1266.3006701861607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.406447554406,
        1281.1948928179154
      ],
      "voteCount": 1813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.74833940929559
      }
    },
    {
      "id": "0daa674e0dec39dcdf1117ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1274.374857400761,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.4080584954306,
        1281.3416563060914
      ],
      "voteCount": 9602,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.634858071585965
      }
    },
    {
      "id": "a29e0d7cb38a7ccc36d4aec5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1253.951968474826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.8971209927677,
        1261.006815956884
      ],
      "voteCount": 9499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.956242750016376
      }
    },
    {
      "id": "f120e9b502342a7ab7c94011",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1237.2640005404046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.32606500381,
        1243.2019360769993
      ],
      "voteCount": 14894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.178564728277527
      }
    },
    {
      "id": "b808da488bfdb67593c70d24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1170.9479083256533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.5249876545943,
        1193.3708289967124
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.88448813041234
      }
    },
    {
      "id": "66251ba07c1f3a18276d92fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1164.7118993159363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.0841804699562,
        1193.3396181619164
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 213.34246300117636
      }
    },
    {
      "id": "0ace7b457b33deae36e60734",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1265.5860252237674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.0984100247194,
        1274.0736404228153
      ],
      "voteCount": 5573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.753191204088527
      }
    },
    {
      "id": "0eedb8ba98c898d8768e9580",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1228.6888397146463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.2438942929925,
        1237.1337851363
      ],
      "voteCount": 5036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.565109377333666
      }
    },
    {
      "id": "aad375ea364d9cbd1454c2f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1221.2185878298033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.8316795491821,
        1229.6054961104246
      ],
      "voteCount": 6665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.31081206145614
      }
    },
    {
      "id": "791094ee74af3ca4db9c5f02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1258.4635624553034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.1780912859042,
        1262.7490336247029
      ],
      "voteCount": 35558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.7808043769253485
      }
    },
    {
      "id": "c37bb5bf7e75c8e94a5b9532",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1263.4708827998015,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.7077921781563,
        1272.233973421447
      ],
      "voteCount": 5317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.990259124863694
      }
    },
    {
      "id": "e606b2c8a76fa992ab43e2dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-flash-8b-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1246.2132525437446,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.4358297644503,
        1277.9906753230389
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 262.8700828586646
      }
    },
    {
      "id": "60a99b2c56a8a1221bcf689b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1340.269457091461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.5186974211056,
        1350.020216761816
      ],
      "voteCount": 8912,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.750314551554908
      }
    },
    {
      "id": "018d645e8d1536d4a284f675",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1347.0190546565996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.4852048217208,
        1354.552904491478
      ],
      "voteCount": 12747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.77534863285255
      }
    },
    {
      "id": "04e18336623c232aac0e350a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1322.4342272713366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.3395985302877,
        1330.528856012385
      ],
      "voteCount": 11797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.05680511331642
      }
    },
    {
      "id": "eec90d9cfa70e700ecbe1372",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1329.1234077562854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.023664278596,
        1334.223151233975
      ],
      "voteCount": 42538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.7701841285222395
      }
    },
    {
      "id": "4c84a7ab60adfcadbc73002e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1266.8598661682745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.572155212148,
        1273.1475771244009
      ],
      "voteCount": 52502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.291743557112813
      }
    },
    {
      "id": "733b52909db507cb101db623",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1315.5394122822968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.495124378396,
        1327.5837001861973
      ],
      "voteCount": 3896,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.76296398924706
      }
    },
    {
      "id": "835bb3352ec05f86f7a8528a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1333.3514404142206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.7367477299094,
        1355.9661330985318
      ],
      "voteCount": 1076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.1328406934298
      }
    },
    {
      "id": "f30a891ec6e1cb4cd52729ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1300.543221324499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.9180189117737,
        1315.1684237372242
      ],
      "voteCount": 2677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.68107211273859
      }
    },
    {
      "id": "8255e679ce1a66bb57a1d589",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1331.2097831110104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.983433164073,
        1338.4361330579482
      ],
      "voteCount": 13552,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.59382880125952
      }
    },
    {
      "id": "a794677d8c61a7aba23f0bc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1326.800143595146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.6383363326493,
        1332.961950857643
      ],
      "voteCount": 22512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.883710983864546
      }
    },
    {
      "id": "4d7872ab0017626fa966a88a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1312.2300890565018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.36451270511,
        1321.0956654078936
      ],
      "voteCount": 9291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.460571806456603
      }
    },
    {
      "id": "0d559b7ae50e142b22180c19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1308.57243100585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.8535802872402,
        1316.2912817244599
      ],
      "voteCount": 12133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.509903710335452
      }
    },
    {
      "id": "ad7f609a3800d463cfcbbbc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1332.777975087476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.1166810508776,
        1344.4392691240741
      ],
      "voteCount": 4795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.399514860198536
      }
    },
    {
      "id": "dd12d2d67430f0b26bd61829",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1332.7086888234521,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.8887188497783,
        1340.5286587971261
      ],
      "voteCount": 13570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.918934249596328
      }
    },
    {
      "id": "8fce8e3d249b25332fffbd52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1310.6633317536566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.594618076937,
        1318.7320454303763
      ],
      "voteCount": 9328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.947764751808094
      }
    },
    {
      "id": "4136c5c82e3d3dbe8fab39c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1298.4877178987058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.23594654924,
        1310.7394892481716
      ],
      "voteCount": 4418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.07523370834108
      }
    },
    {
      "id": "61c7314e4d4119d1bcab3720",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1342.6482062544148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.1952003977299,
        1349.1012121110998
      ],
      "voteCount": 21409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.839966411220521
      }
    },
    {
      "id": "c70c246fb2b6414c054a46e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1332.9582731217852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.2253081036247,
        1339.6912381399459
      ],
      "voteCount": 20950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.800938146613422
      }
    },
    {
      "id": "69cad9d69223ba37e615340c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1309.896876626441,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.1033748551808,
        1315.6903783977014
      ],
      "voteCount": 29835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.737478218634491
      }
    },
    {
      "id": "64782b1efc12f647fba06ba7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1285.5276056698178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.1597414532234,
        1301.8954698864122
      ],
      "voteCount": 1935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.74094777995408
      }
    },
    {
      "id": "e73ac098cbdb30fff6c4135e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1273.3810129235035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.028407780857,
        1291.73361806615
      ],
      "voteCount": 2488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.67974127626681
      }
    },
    {
      "id": "66b7b917b944fc722b3530cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1349.6398493079028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.2555709261699,
        1358.0241276896356
      ],
      "voteCount": 9750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.2993303491124
      }
    },
    {
      "id": "0875e2a1efdf0355c7befc9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1297.0379417988163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.1663867059883,
        1304.9094968916443
      ],
      "voteCount": 10492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.12964825905091
      }
    },
    {
      "id": "ff731f65077b5c3afe91b0a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1316.105602027219,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.3511001639677,
        1323.8601038904708
      ],
      "voteCount": 13712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.653506116800047
      }
    },
    {
      "id": "f74ca0d8df70c8e0b90b5acd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1323.1750488696066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.1976343728466,
        1327.1524633663662
      ],
      "voteCount": 79138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.118181872421102
      }
    },
    {
      "id": "cbde87fd0b4c133906a0e2d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1325.5595732170764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.8047015413295,
        1334.3144448928233
      ],
      "voteCount": 9385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.952778784427064
      }
    },
    {
      "id": "6e9252b39f0c07306ada8605",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1294.6730806146097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.803008778568,
        1316.5431524506512
      ],
      "voteCount": 1300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.5100011321204
      }
    },
    {
      "id": "19715297ce3058f826aa2bd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1372.384932991162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.5211343839328,
        1382.248731598391
      ],
      "voteCount": 4444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.32749340949415
      }
    },
    {
      "id": "43fd2f22ee06e181c993a6ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1356.4903690629708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.6416961082368,
        1363.339042017705
      ],
      "voteCount": 9175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.210028385109995
      }
    },
    {
      "id": "cd26788a6cca99ff6bc2786f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1358.4786862173673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.1179201256343,
        1365.8394523091006
      ],
      "voteCount": 8062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.104245284456637
      }
    },
    {
      "id": "14b241af9978682167a591e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1355.829673614917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.4326392548805,
        1360.2267079749536
      ],
      "voteCount": 30133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.032960670875335
      }
    },
    {
      "id": "d425321398ff425a0daf13b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1312.5728720777365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.3034163851585,
        1317.8423277703146
      ],
      "voteCount": 35980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.228286073629168
      }
    },
    {
      "id": "cdaea1c548bee18eadf0ec9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1335.3999202639736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.4441119320409,
        1346.3557285959064
      ],
      "voteCount": 3319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.245873458136106
      }
    },
    {
      "id": "34968bd08a014d84f98f597d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1344.713130127175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.5342428892923,
        1372.8920173650577
      ],
      "voteCount": 459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.70524481161442
      }
    },
    {
      "id": "ff1896684224bb0314507b83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1313.6225496427128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.008606619096,
        1330.2364926663295
      ],
      "voteCount": 1281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.85371903638043
      }
    },
    {
      "id": "293c553b0647e7c02c46589b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1354.169983204152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.4472605215965,
        1360.8927058867075
      ],
      "voteCount": 9056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.765061758069018
      }
    },
    {
      "id": "e5d570c13950a5a98ce1a910",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1350.69379311799,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.11295068858,
        1356.2746355474003
      ],
      "voteCount": 14853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.107805829941835
      }
    },
    {
      "id": "ca1eff385d84dbc25c95748d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1331.5710265819325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.3810095764195,
        1339.7610435874456
      ],
      "voteCount": 6378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.461173393099795
      }
    },
    {
      "id": "e7d88454990c1f58ddbab7e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1336.493870087779,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.739489411554,
        1343.2482507640043
      ],
      "voteCount": 9269,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.876128431625347
      }
    },
    {
      "id": "0f290bf8d5ac8680a0b81b65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1367.2429779336999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.1477921368903,
        1378.3381637305095
      ],
      "voteCount": 3342,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.045937132675476
      }
    },
    {
      "id": "4041bdf497f846910952e291",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1359.7392928771942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.8243690042377,
        1366.654216750151
      ],
      "voteCount": 9790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.447399386711243
      }
    },
    {
      "id": "af31ee36c92515251ced1d06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1353.058083555533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.44176763746,
        1360.6743994736057
      ],
      "voteCount": 6506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.100583104365992
      }
    },
    {
      "id": "47a1e33da65bd7a2d8a348cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1354.6731086013413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.2503204048967,
        1367.0958967977858
      ],
      "voteCount": 2686,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.17371362732452
      }
    },
    {
      "id": "f2285a724a7cf4e1a0620078",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1355.8380428023315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.0179422733804,
        1361.6581433312822
      ],
      "voteCount": 14433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.81789230294889
      }
    },
    {
      "id": "8544110263e17670ae61229e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1353.5767064590946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.714917790574,
        1359.4384951276152
      ],
      "voteCount": 14953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.944666075631325
      }
    },
    {
      "id": "214786b9a6900244f7a92c1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1338.3770617021446,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.417572812859,
        1343.3365505914303
      ],
      "voteCount": 22789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.402913890536645
      }
    },
    {
      "id": "98920ca7d2989276212ec903",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1316.8774114131393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.564715836389,
        1334.1901069898895
      ],
      "voteCount": 1210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.0248968226782
      }
    },
    {
      "id": "3f04c7f2ae34d986b6bec780",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1325.9365368187568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.4865837186353,
        1349.3864899188784
      ],
      "voteCount": 773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.14882081660326
      }
    },
    {
      "id": "04f69c62a7176f82b47c9b77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1356.4485495392973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.2757630177148,
        1363.62133606088
      ],
      "voteCount": 8372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.393054275900784
      }
    },
    {
      "id": "d77f9605866e40887a0a8b21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1338.3867681424051,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.0969422268417,
        1345.6765940579685
      ],
      "voteCount": 7610,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.833692969176894
      }
    },
    {
      "id": "809c395a8efe244ac3d48a40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1329.0924070313986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.217302600974,
        1335.967511461823
      ],
      "voteCount": 10053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.304455972458513
      }
    },
    {
      "id": "5287dfc6d0ed229188604800",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1350.9549169269985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.5849779312432,
        1354.3248559227538
      ],
      "voteCount": 55606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.956295867063421
      }
    },
    {
      "id": "3fabfc7b25690384f3e981b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1350.009049803441,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.303651066325,
        1357.7144485405568
      ],
      "voteCount": 7738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.455891230201182
      }
    },
    {
      "id": "8d28be6625deda89ba620855",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-1.5-pro-002",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1345.3499237354729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.8790484098247,
        1374.820799061121
      ],
      "voteCount": 405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.09444302280951
      }
    },
    {
      "id": "7fcf668f4f5454ce9ca00802",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1389.0260382851434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.77161783589,
        1401.2804587343965
      ],
      "voteCount": 2389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.09213336821368
      }
    },
    {
      "id": "b04a2571f5ed19471b1a8852",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1365.2662477304318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.9233661778378,
        1372.6091292830258
      ],
      "voteCount": 6996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.035790050635693
      }
    },
    {
      "id": "58aaf85f97a3642886c6ac31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1345.8693107639062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.1247482653162,
        1353.6138732624963
      ],
      "voteCount": 6286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.613403942132967
      }
    },
    {
      "id": "5b63e9c3aaf7b1edd9238785",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1366.6286898823764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.9883148690706,
        1371.2690648956823
      ],
      "voteCount": 24783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.60544347061954
      }
    },
    {
      "id": "dcb854edfdb5e504ae6b279d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1325.5327754510095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.1636550449696,
        1330.901895857049
      ],
      "voteCount": 30116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.504298569922977
      }
    },
    {
      "id": "817e9c90dfa5bc9652a696a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1354.208973935692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.4735106490773,
        1366.9444372223065
      ],
      "voteCount": 2182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.22146655613504
      }
    },
    {
      "id": "470e55f6e2c3fa8693b0c2b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1403.8665947902118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.057745393225,
        1430.6754441871985
      ],
      "voteCount": 506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.09413260362425
      }
    },
    {
      "id": "f8f48d2961e5b6d0bd7775fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1357.1057016616103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.94116072935,
        1375.2702425938703
      ],
      "voteCount": 1036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.89199121497634
      }
    },
    {
      "id": "cc0c99550eaf674a557fc962",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1366.6627588679803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.908277580712,
        1373.4172401552485
      ],
      "voteCount": 8538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.876482240101964
      }
    },
    {
      "id": "91a8a4986d63e31df747e908",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1360.7529223555143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.26524018681,
        1366.2406045242187
      ],
      "voteCount": 14138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.839380035128077
      }
    },
    {
      "id": "2f703a05963f15571ca5d023",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1346.85907126144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.439241662802,
        1355.278900860078
      ],
      "voteCount": 5308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.454845874747736
      }
    },
    {
      "id": "60389346ccc3eb83c8983491",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1342.842789281568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.859442626355,
        1349.8261359367812
      ],
      "voteCount": 7766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.694950742193164
      }
    },
    {
      "id": "0bc60faf67069dddf01c4805",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1381.0616134792385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.2423514579923,
        1392.8808755004848
      ],
      "voteCount": 2590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.365079322035236
      }
    },
    {
      "id": "5d7e409b1ae7a8f12169bdb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1367.255772238098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.0522157350968,
        1374.459328741099
      ],
      "voteCount": 7813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.508208395308118
      }
    },
    {
      "id": "c2c30886c09e5277df6bd5ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1362.4593282358856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.1524623878886,
        1371.7661940838827
      ],
      "voteCount": 3765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.54814016123201
      }
    },
    {
      "id": "e3e1749c4f0110b345d94eb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1376.6058379555952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.749831583862,
        1389.4618443273284
      ],
      "voteCount": 2309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.02451426517778
      }
    },
    {
      "id": "5770deb4e3b3b41b63d8684a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1371.1192717653228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.2333266543037,
        1377.0052168763418
      ],
      "voteCount": 12258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.018539952399975
      }
    },
    {
      "id": "f150109f54be3e3e1c73dad6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1354.1682220725613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.0352788916261,
        1360.3011652534965
      ],
      "voteCount": 10547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.79133027743428
      }
    },
    {
      "id": "db1797879418d3ad13caa305",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1347.5627820302893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.0045610572145,
        1353.1210030033644
      ],
      "voteCount": 13631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.042210479806133
      }
    },
    {
      "id": "a01265e8b80b7f6b6c87c38e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1297.8942780028403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.2615213083434,
        1317.5270346973373
      ],
      "voteCount": 961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.33821873838771
      }
    },
    {
      "id": "032021ff05f26a1a56f97f90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1322.3692896003504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.079619299522,
        1345.6589599011788
      ],
      "voteCount": 662,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.1986352162123
      }
    },
    {
      "id": "14a3a6101e39bc4e2351dad7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1363.2006734908987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.6995144529092,
        1370.7018325288877
      ],
      "voteCount": 6497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.647400776520913
      }
    },
    {
      "id": "5731f30557a43cbf87d55dcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1355.8886597179844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.891456470108,
        1364.8858629658605
      ],
      "voteCount": 4067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.07263674089505
      }
    },
    {
      "id": "d26498a1305f0cb23e76c1c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1357.1093609179638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.7173884541025,
        1364.5013333818251
      ],
      "voteCount": 6937,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.224090236795
      }
    },
    {
      "id": "6e0e2cd29505029908a727f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1360.336920420677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.56866718824,
        1364.105173653114
      ],
      "voteCount": 43762,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.6964427022561592
      }
    },
    {
      "id": "de46ec6850f021b3a58c4de2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1361.9982770433376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.0459112917442,
        1371.950642794931
      ],
      "voteCount": 3466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.78436700138564
      }
    },
    {
      "id": "83598a4658e59512372ca08e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-001",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1366.4444539936108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.4225223192182,
        1392.4663856680033
      ],
      "voteCount": 517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.27181747178054
      }
    },
    {
      "id": "6c759ede321bce86461f503e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1368.7489369296363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.922688248749,
        1383.5751856105237
      ],
      "voteCount": 1508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.222440798622515
      }
    },
    {
      "id": "8b161fda41d842424b44c056",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1343.2414761432854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.4796938816858,
        1353.003258404885
      ],
      "voteCount": 3474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.80630337868973
      }
    },
    {
      "id": "93a229a806a979314ebfa178",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1344.6997192373792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.4803570995523,
        1353.9190813752057
      ],
      "voteCount": 4104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.126135459401606
      }
    },
    {
      "id": "32cd0f4393695e072db44056",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1356.013279055458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.6057353872595,
        1361.4208227236566
      ],
      "voteCount": 14891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.612089544198316
      }
    },
    {
      "id": "ded55442771fad7ad07ad7cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1313.512902223793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.847056910005,
        1320.1787475375809
      ],
      "voteCount": 16266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.566828077912042
      }
    },
    {
      "id": "db435f2d54bfd2bbc4cab0f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1329.2207207635133,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.88184481272,
        1345.5595967143065
      ],
      "voteCount": 1237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.49413746082381
      }
    },
    {
      "id": "88db9c18f5ac59cdd3ee1e37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1377.3954360930766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.2401586987755,
        1415.5507134873774
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 378.97717012959936
      }
    },
    {
      "id": "c61be66eb2bf12e72aa7d38c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1328.8918475192602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.7777866967588,
        1351.0059083417618
      ],
      "voteCount": 627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.3036387704734
      }
    },
    {
      "id": "0a2845fee3aaa65104e56f71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1353.698387416931,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.7547978931043,
        1362.6419769407573
      ],
      "voteCount": 4113,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.82224417968532
      }
    },
    {
      "id": "7b2c78019435256cef6f2e96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1348.3052031522684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.8839235070059,
        1355.726482797531
      ],
      "voteCount": 6186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.337103205816952
      }
    },
    {
      "id": "3babc8e70917eba77c699644",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1358.2539729672949,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.5379066505502,
        1369.9700392840396
      ],
      "voteCount": 2418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.73283389083859
      }
    },
    {
      "id": "5edc62312af2cd6247c32ab1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1326.8308540369007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.2000589893305,
        1335.4616490844712
      ],
      "voteCount": 4510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.391233026338803
      }
    },
    {
      "id": "309832f154d79799f3961d1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1380.1383147073627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.7235233969295,
        1395.553106017796
      ],
      "voteCount": 1435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.85561325404853
      }
    },
    {
      "id": "19ebcbdc29406bbf2f0bd388",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1362.8395445903668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.7933618632721,
        1371.8857273174615
      ],
      "voteCount": 4444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.302694041947063
      }
    },
    {
      "id": "267660ca0485aa44b2f31e19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1337.4254824786713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.3335864540995,
        1348.5173785032425
      ],
      "voteCount": 2399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.02693642246905
      }
    },
    {
      "id": "093da4bfd50858fc8a9de4f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1371.2709197519716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.5394856611376,
        1390.0023538428056
      ],
      "voteCount": 1055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.33681746349163
      }
    },
    {
      "id": "0eb40eb9ea1eff38581e94ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1354.923907687808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.0400155814123,
        1362.8077997942041
      ],
      "voteCount": 5685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.18024756908913
      }
    },
    {
      "id": "35a54afcbbee77d135cfda89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1346.914643616923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.602885435017,
        1354.226401798829
      ],
      "voteCount": 6681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.917058650392908
      }
    },
    {
      "id": "9cecfb2e2322b5c5945476b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1330.9286050687247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.6006167438918,
        1337.256593393558
      ],
      "voteCount": 9249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.424018090082853
      }
    },
    {
      "id": "fc2fe293aefff81a59f59834",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1319.2786353200495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.2147909785785,
        1344.3424796615207
      ],
      "voteCount": 542,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.53065918326865
      }
    },
    {
      "id": "5a43b7e0df62dfa6c2646888",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1343.678143613995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.36874139778,
        1375.9875458302095
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.74506360594364
      }
    },
    {
      "id": "42230507bbd6a29cca9a9df3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1347.3989070565074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.9780195549554,
        1357.8197945580594
      ],
      "voteCount": 2940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.269181420088763
      }
    },
    {
      "id": "0bd5f24ae0622a0e20023e21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1325.833252030036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.6099093197554,
        1336.0565947403165
      ],
      "voteCount": 2814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.207563857983033
      }
    },
    {
      "id": "4416ce23ce77e67db1accfa1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1326.9758746953755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.2180776876558,
        1336.7336717030953
      ],
      "voteCount": 3586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.786053134538143
      }
    },
    {
      "id": "d251c23900427cb38480a8f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1353.295161189511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.0001773876938,
        1357.5901449913285
      ],
      "voteCount": 24955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.802052219979321
      }
    },
    {
      "id": "8f8a01afac6dd3aa1e390e3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1351.3937006943347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.7560034797136,
        1363.031397908956
      ],
      "voteCount": 2296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.25639679634248
      }
    },
    {
      "id": "133047af4760b4547d218560",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.0-flash-lite-preview-02-05",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1333.628703246528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.461598228052,
        1378.795808265004
      ],
      "voteCount": 157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 531.0657932242038
      }
    },
    {
      "id": "339f97e1e7428f97a278226d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1404.7321989077586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.1322110788592,
        1419.332186736658
      ],
      "voteCount": 1689,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.48924368412129
      }
    },
    {
      "id": "6df9e3288a72c81e294bc82b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1383.8317782159365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.8364200522842,
        1391.8271363795884
      ],
      "voteCount": 6001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.6410093531933
      }
    },
    {
      "id": "9aba692d3ae1c5058c125421",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1371.3323030506467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.0246053702174,
        1380.640000731076
      ],
      "voteCount": 4188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.552170973061262
      }
    },
    {
      "id": "e8b44509879f7b666ac9d055",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1378.7664089361137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.105236381467,
        1384.4275814907603
      ],
      "voteCount": 15763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.342891643361142
      }
    },
    {
      "id": "fcc71c04cc16c7d4e32b81c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1344.4245415479245,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.209964000054,
        1350.639119095795
      ],
      "voteCount": 23182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.053725915384748
      }
    },
    {
      "id": "70e3e3f6727a7eb1f3df24b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1369.6099465885845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.6635268435148,
        1384.5563663336548
      ],
      "voteCount": 1577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.15380917071816
      }
    },
    {
      "id": "ba76e1b417e505c428c53477",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1395.4452003970418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.1381865860226,
        1425.7522142080613
      ],
      "voteCount": 403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 239.10580043009446
      }
    },
    {
      "id": "aa25e949e874d70e8781566c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1376.4993151610877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.003207257841,
        1397.995423064334
      ],
      "voteCount": 784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.28832705397116
      }
    },
    {
      "id": "622c237522aa9e42bf6faed1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1382.8585777309813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.522834525412,
        1390.1943209365509
      ],
      "voteCount": 7542,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.008513663654051
      }
    },
    {
      "id": "40461a436fcdd796e7f82bed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1381.1980427003475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.3653552901596,
        1387.0307301105354
      ],
      "voteCount": 14572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.856073698277395
      }
    },
    {
      "id": "bcb305c5e1099d01923ae243",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1362.866977404449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.4655925331533,
        1371.2683622757447
      ],
      "voteCount": 5459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.374078976299508
      }
    },
    {
      "id": "e4f751411ea93f196c8aafb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1360.784382208984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.7515937995906,
        1368.8171706183773
      ],
      "voteCount": 5855,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.797183737199244
      }
    },
    {
      "id": "c6b46fbdc9a1ab692ae91f7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1381.0713268733814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.0632615867437,
        1394.0793921600189
      ],
      "voteCount": 2092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.048308311906446
      }
    },
    {
      "id": "b97e45a6d7d986da2524a060",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1382.7897353864178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.2652655266336,
        1391.3142052462017
      ],
      "voteCount": 5258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.916403840881582
      }
    },
    {
      "id": "1d9187f837f3bbffffb58f70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1369.4922847571338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.614307727541,
        1382.3702617867266
      ],
      "voteCount": 1990,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.17169599250214
      }
    },
    {
      "id": "2b9333663554af3044c9f1e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1402.237942766612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.3551780500502,
        1416.1207074831734
      ],
      "voteCount": 1985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.17134509867856
      }
    },
    {
      "id": "7dbf2de2a78b51537ade92d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1386.4737043614791,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.0338036454805,
        1392.9136050774773
      ],
      "voteCount": 10942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.79598224729184
      }
    },
    {
      "id": "d3cdabd98c449a34aa10f427",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1378.7137644675822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.2442661709958,
        1386.1832627641688
      ],
      "voteCount": 7099,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.524014809724509
      }
    },
    {
      "id": "d6e5ae29cac01ab9d3fac0df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1369.453926929039,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4398869058919,
        1376.4679669521859
      ],
      "voteCount": 8102,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.806790269696824
      }
    },
    {
      "id": "050b93f41d5c8a2ac8dfc2f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1355.2538110514308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.9307444569288,
        1377.5768776459329
      ],
      "voteCount": 727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.72137030289187
      }
    },
    {
      "id": "1eb9d88fa01ac2116de1a558",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1365.5599968651743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.5293201885106,
        1388.590673541838
      ],
      "voteCount": 696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.07568763399533
      }
    },
    {
      "id": "fefb050882703a13672348fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1378.2830185046594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.3687032125326,
        1386.197333796786
      ],
      "voteCount": 6300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.30536456769172
      }
    },
    {
      "id": "633d29c6189549adbf5c5c69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1364.778722985875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.3783883711576,
        1377.1790576005922
      ],
      "voteCount": 2094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.028620827223406
      }
    },
    {
      "id": "8bac68f6fd7cf6f5ae6b5d91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1366.6744404847666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.364685417972,
        1374.9841955515612
      ],
      "voteCount": 5659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.975470385919948
      }
    },
    {
      "id": "7cf23f4d23f7012e20c92829",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1374.4966097468027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.9901193183455,
        1379.00310017526
      ],
      "voteCount": 32907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.2866520063612885
      }
    },
    {
      "id": "5ac0b5c584d5084db8fec1b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1377.4366188244326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.095213732163,
        1390.7780239167025
      ],
      "voteCount": 1844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.33476451112324
      }
    },
    {
      "id": "db32995fb7ff3333d7de2298",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-06-17-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1360.034496512466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.0720628732415,
        1382.9969301516903
      ],
      "voteCount": 713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.25862575835419
      }
    },
    {
      "id": "e9d9fb57b370ecc1a0ddef3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1406.902978573632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.869219100021,
        1419.936738047243
      ],
      "voteCount": 2174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.222493054148224
      }
    },
    {
      "id": "5b77aed98b8c7fe432abd1e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1397.4247977037708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.9040202422952,
        1403.945575165246
      ],
      "voteCount": 9678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.068851883306758
      }
    },
    {
      "id": "0c43e33768910da494c9ecbf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1361.1952339369054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.4703416155216,
        1368.920126258289
      ],
      "voteCount": 6508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.534192649809544
      }
    },
    {
      "id": "fa7137814fef114e311bc761",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1384.9600949048804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.3259962346347,
        1389.5941935751262
      ],
      "voteCount": 22615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.59029043078287
      }
    },
    {
      "id": "05daeded93af33072dc72673",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1350.972072480165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.0459955125502,
        1355.8981494477798
      ],
      "voteCount": 33074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.316932036376626
      }
    },
    {
      "id": "70f8fcd09dc6a1041f1f7d21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1387.4318043069534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.6016125008111,
        1399.2619961130958
      ],
      "voteCount": 2536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.43236715598265
      }
    },
    {
      "id": "aad55906f6094f06cc1e4610",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1393.4101880703215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.7752063442872,
        1416.0451697963558
      ],
      "voteCount": 769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.37183128916908
      }
    },
    {
      "id": "cdd023915f64111c1f0b8087",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1383.313868040018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.7699885822217,
        1404.8577474978142
      ],
      "voteCount": 779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.82356306716576
      }
    },
    {
      "id": "b89f3748dde2fcbfa945f7ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1396.3508708760578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.4783621652668,
        1402.223379586849
      ],
      "voteCount": 12541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.977412011431188
      }
    },
    {
      "id": "92ec17033848dc40dff8e90d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1390.3580691036398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.8604723642463,
        1394.8556658430332
      ],
      "voteCount": 25063,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.265805875942539
      }
    },
    {
      "id": "ad9def545aed9ac1dfb3b479",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1377.7724251820764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.0711354868135,
        1384.4737148773393
      ],
      "voteCount": 9033,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.690163991325198
      }
    },
    {
      "id": "d35366e66973e7ee49ead37e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1345.4262947367806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.6295312061634,
        1352.2230582673976
      ],
      "voteCount": 8558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.025638344023774
      }
    },
    {
      "id": "40cd7952a3cc757dc165caaf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1399.0486609849597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.420480888436,
        1409.6768410814832
      ],
      "voteCount": 3151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.40503007753931
      }
    },
    {
      "id": "1c130ab4e7c6e8954fb6f1e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1402.2893212413733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.0776635233083,
        1409.5009789594383
      ],
      "voteCount": 7455,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.538608500072165
      }
    },
    {
      "id": "8eafde180e337428809d9109",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1369.992205403632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.0048426460075,
        1382.979568161256
      ],
      "voteCount": 2075,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.908212809541254
      }
    },
    {
      "id": "80b1d26d75258d2c1ebe76ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1398.1693799456739,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.0463770998763,
        1410.2923827914715
      ],
      "voteCount": 2530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.25817348542125
      }
    },
    {
      "id": "cbb0201e4fa890b330082935",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1399.4147670474576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.157330159268,
        1404.6722039356478
      ],
      "voteCount": 16631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.195350496638803
      }
    },
    {
      "id": "99546de74ea5caaac139ca50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1370.9059619979532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.5974132426693,
        1377.214510753237
      ],
      "voteCount": 10462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.360071331078737
      }
    },
    {
      "id": "c1568c552548f3be17969e95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1365.2118391442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.4795536466727,
        1370.944124641727
      ],
      "voteCount": 12893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.553806915265213
      }
    },
    {
      "id": "b894d759fc45f8885793555c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1358.9674265022586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.9597481382077,
        1387.9751048663095
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 219.0431925338685
      }
    },
    {
      "id": "c81a4789c0ba02606bd4d2c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1343.3020428364582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.070533255147,
        1365.5335524177692
      ],
      "voteCount": 761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.65946020335647
      }
    },
    {
      "id": "028d2bc5032fd2f31841428a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1385.8124371089004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.7370336743636,
        1391.8878405434373
      ],
      "voteCount": 11479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.608466110203494
      }
    },
    {
      "id": "40c322dcf941a76e82568ffe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1364.7112088050503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.7798385826386,
        1375.6425790274618
      ],
      "voteCount": 2875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.106634358723202
      }
    },
    {
      "id": "49f5387800e38654e7db5b46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1373.7677272883793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.7058785248032,
        1380.8295760519557
      ],
      "voteCount": 8190,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.98197124773879
      }
    },
    {
      "id": "7255ff908364b687dac274f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1379.7919484313716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.3436553672368,
        1383.2402414955063
      ],
      "voteCount": 47246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.0953670496487815
      }
    },
    {
      "id": "cda85f38f93aaaad1e683760",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1375.290552279489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.760235058623,
        1384.8208695003555
      ],
      "voteCount": 3757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.64386827239976
      }
    },
    {
      "id": "67b4133ce113efaf8a5cddec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-lite-preview-09-2025-no-thinking",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1392.3746983438018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.7854743173002,
        1409.9639223703034
      ],
      "voteCount": 1261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.53732092292981
      }
    },
    {
      "id": "15857fedc689b33ecd8d8f40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1448.4318002288726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.665869231424,
        1464.1977312263211
      ],
      "voteCount": 1413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.70577762731226
      }
    },
    {
      "id": "1ee6bc93ee30a8b3522f37ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1428.5071797141516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.9849718170844,
        1436.0293876112185
      ],
      "voteCount": 6846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.729719694475865
      }
    },
    {
      "id": "eeac52b4fb2ca3422ed6428c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1383.622015581909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.4069898743423,
        1392.8370412894756
      ],
      "voteCount": 4531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.10532580322441
      }
    },
    {
      "id": "b3a7c748e6add8408ce42057",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1411.661342985715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.2812467619415,
        1417.0414392094888
      ],
      "voteCount": 15862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.535011236130566
      }
    },
    {
      "id": "0e094571957478a0a0c8b25b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1386.782250708673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.1201665210854,
        1392.4443348962607
      ],
      "voteCount": 23407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.345578813607522
      }
    },
    {
      "id": "f2211bf8dacdaa5ca8c38482",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1440.0135885477707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.265340079035,
        1454.7618370165067
      ],
      "voteCount": 1629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.621935324108264
      }
    },
    {
      "id": "87237f0f23b4ee3522e405d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1442.1926025988366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.304637984525,
        1469.0805672131482
      ],
      "voteCount": 522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.20002370085004
      }
    },
    {
      "id": "b58dfc14af9e2178d4deb3bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1416.9227769416257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.5408576429732,
        1441.3046962402782
      ],
      "voteCount": 601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.7531852960445
      }
    },
    {
      "id": "8f375ef8eb953fc70cd34384",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1423.071518857868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.279151800558,
        1429.8638859151781
      ],
      "voteCount": 8801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.010085854023115
      }
    },
    {
      "id": "ebe5923f5ccbd0d05db4e4c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1420.4130315107361,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.186933948132,
        1425.6391290733402
      ],
      "voteCount": 17495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.109823899900972
      }
    },
    {
      "id": "03fb2020028551a40248a4e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1402.6085885497346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.6046618734863,
        1410.6125152259826
      ],
      "voteCount": 6096,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.6766963356858
      }
    },
    {
      "id": "10d5fbea116b1fbe884e168d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1381.3534354279163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.335898074123,
        1389.3709727817095
      ],
      "voteCount": 5996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.733462004899252
      }
    },
    {
      "id": "194ed4d8d957d46e94e60c16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1428.1841868763702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.37616345566,
        1440.9922102970804
      ],
      "voteCount": 2159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.703949619801094
      }
    },
    {
      "id": "64d893677c0fc2c8c93759eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1436.78884625465,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.300993841979,
        1445.276698667321
      ],
      "voteCount": 5150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.754239454860553
      }
    },
    {
      "id": "6516a97a6a7475c78777317b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1421.8216832288012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3318538015676,
        1436.3115126560347
      ],
      "voteCount": 1636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.65505856766822
      }
    },
    {
      "id": "aae36f500851b4ab946b8434",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1428.2154147519775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.2433630115731,
        1443.1874664923819
      ],
      "voteCount": 1654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.35343909188211
      }
    },
    {
      "id": "a749aac1d7e3f4abbe432c10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1422.9744883798223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.8979396381276,
        1429.0510371215173
      ],
      "voteCount": 11755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.61208913949059
      }
    },
    {
      "id": "7bfe35954fcd329e6e86316e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1394.94509258439,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.5305125302527,
        1402.3596726385272
      ],
      "voteCount": 7309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.311229130728286
      }
    },
    {
      "id": "0646103b7c6b93dbdfe6caeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1401.7595138626732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.089716043485,
        1408.4293116818617
      ],
      "voteCount": 9151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.580549219791228
      }
    },
    {
      "id": "8f783a357449bc6e1a5e06d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1399.8824326852696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.0933671504908,
        1434.6714982200485
      ],
      "voteCount": 303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 315.05715335624825
      }
    },
    {
      "id": "452dd865a9dbc8320c636ad4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1377.8485490688531,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.8045062947808,
        1401.8925918429254
      ],
      "voteCount": 654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.49386701923683
      }
    },
    {
      "id": "b06b8e22cc8e45bdd497e9bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1417.7277262381792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.6089468426815,
        1424.8465056336768
      ],
      "voteCount": 7928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.192128940381362
      }
    },
    {
      "id": "ee92e6a2cd4e0420798cafe1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1412.6440370729429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.526077792113,
        1425.7619963537725
      ],
      "voteCount": 1945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.795704893802416
      }
    },
    {
      "id": "559e319e41aac618b7ee4c35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1400.4160184065597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.2829371744947,
        1408.549099638625
      ],
      "voteCount": 5767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.219242328209262
      }
    },
    {
      "id": "810cbefe93a5d4aea84ca79b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1404.749294998001,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.6934197875498,
        1408.8051702084522
      ],
      "voteCount": 32925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.282259550495346
      }
    },
    {
      "id": "4fe7d50223f84920438b21d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1399.1009611963045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.975730411155,
        1411.2261919814543
      ],
      "voteCount": 2286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.27223678700715
      }
    },
    {
      "id": "d7f11a7247d1df78b688c3d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash-preview-09-2025",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1386.73998220584,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.049663018579,
        1408.4303013931012
      ],
      "voteCount": 850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.4716880761092
      }
    },
    {
      "id": "722cd3c83bbe364519a33fd4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1444.7568897566287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.554786161567,
        1452.9589933516902
      ],
      "voteCount": 6227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.512748808268082
      }
    },
    {
      "id": "c514cb2de2ab7df92291312f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1423.836474512752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.404021591506,
        1428.2689274339978
      ],
      "voteCount": 25169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.11436925816397
      }
    },
    {
      "id": "8facd1dc876e465739490ee0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1397.154209064366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.008161289267,
        1402.3002568394647
      ],
      "voteCount": 17041,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.893685170055739
      }
    },
    {
      "id": "8581d134a576bd9692abeda0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1412.4855201958057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.2190447443604,
        1415.7519956472513
      ],
      "voteCount": 58435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.7775546668407403
      }
    },
    {
      "id": "385a446b2b41534c85470945",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1395.7714197978657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.2581280060688,
        1399.284711589663
      ],
      "voteCount": 87313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.2131593205725246
      }
    },
    {
      "id": "846f3f3867b39969e4fcc4c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1425.0014855060097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.7571140451184,
        1432.2458569669006
      ],
      "voteCount": 7580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.661715591133152
      }
    },
    {
      "id": "d62df2d7b7158a755c5efd6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1426.8177838157183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.088634318422,
        1441.5469333130147
      ],
      "voteCount": 2250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.4753795472168
      }
    },
    {
      "id": "c75ac344cd2f33e6155d2267",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1406.8411014742662,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.0695675188326,
        1419.6126354296998
      ],
      "voteCount": 2537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.460973080356865
      }
    },
    {
      "id": "c9dc6368e838d30a39bb7a22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1418.7289349433365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.6351730702095,
        1422.8226968164636
      ],
      "voteCount": 31300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.362635929763953
      }
    },
    {
      "id": "39e2d6411737ec97f613b2e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1420.296973715113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.041425795447,
        1423.552521634779
      ],
      "voteCount": 62144,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.7590019187884036
      }
    },
    {
      "id": "07e7569b1b2cc808c948a3b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1397.624525536881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.8922429033255,
        1402.3568081704366
      ],
      "voteCount": 21821,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.82968605656019
      }
    },
    {
      "id": "03414a6070f2e30e8ac7a758",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1388.4872319128963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.8975246004002,
        1393.0769392253924
      ],
      "voteCount": 22327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.483701426369712
      }
    },
    {
      "id": "a85b7ebee61abcc6080f9ebb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1427.1177036374165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.214666820142,
        1434.0207404546911
      ],
      "voteCount": 8545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.404640925459155
      }
    },
    {
      "id": "0ac7cc396b38f6f609390969",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1429.895248009749,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.0595442162735,
        1434.7309518032246
      ],
      "voteCount": 19761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.087278887974162
      }
    },
    {
      "id": "db304eb3c85a417c1cc0e1d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1418.817451921178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.326032673769,
        1426.308871168587
      ],
      "voteCount": 6673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.609387985137696
      }
    },
    {
      "id": "5fa8cf74644476bbacd5c3dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1425.6881696718767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.2444931302418,
        1433.1318462135118
      ],
      "voteCount": 7574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.423770510828152
      }
    },
    {
      "id": "79f77f38e7c8af344a8ae6bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1421.8576054623322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.175015368013,
        1425.5401955566513
      ],
      "voteCount": 42632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.5302915990459285
      }
    },
    {
      "id": "08427ecb676d884dee28b07e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1404.5155318135094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.2634275959167,
        1408.767636031102
      ],
      "voteCount": 27514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.706646907125316
      }
    },
    {
      "id": "1822dc206ff2a2e489e8c32b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1401.717170027169,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.7964631405105,
        1405.6378769138275
      ],
      "voteCount": 32997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.0015898148595666
      }
    },
    {
      "id": "0277f2e8d69e7d3584ced9e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1393.7791775508445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.4879518605187,
        1409.07040324117
      ],
      "voteCount": 1831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.867913474138255
      }
    },
    {
      "id": "4153b85ebb76a0bf1e058d34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1377.4876600336797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.27238763014,
        1391.7029324372195
      ],
      "voteCount": 2231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.60344544584361
      }
    },
    {
      "id": "1fcd033471211d6a01aeaae2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1419.4641721963494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.3048068343053,
        1423.6235375583935
      ],
      "voteCount": 30538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.503580806795246
      }
    },
    {
      "id": "aad61eba125adee5e9e1ca89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1406.7358380464077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.885841757839,
        1413.5858343349767
      ],
      "voteCount": 7775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.214747402896586
      }
    },
    {
      "id": "98fc6f5ab494b101c123a73c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1403.1364539961546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.38155117945,
        1407.8913568128594
      ],
      "voteCount": 21210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.885550737784702
      }
    },
    {
      "id": "2ac8d0ac976a8d008c8ba37e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1410.7728437919748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.2723682553324,
        1413.2733193286172
      ],
      "voteCount": 122458,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 1.6276050847311287
      }
    },
    {
      "id": "e7f7cca277f04045b212f657",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1413.2620148842161,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.0568816950995,
        1419.4671480733325
      ],
      "voteCount": 9953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.023191628985863
      }
    },
    {
      "id": "a79bc82eb0eab9c9a98d6c5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1404.0495728300205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.177788122499,
        1416.9213575375422
      ],
      "voteCount": 2907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.13018811089404
      }
    },
    {
      "id": "64a738ba522805400cb83b5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1492.171417358254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.8089882698184,
        1500.5338464466897
      ],
      "voteCount": 6339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.204079107238226
      }
    },
    {
      "id": "736187a2372f7b0e98dfdcc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1464.6801397013135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.2779526841048,
        1469.0823267185222
      ],
      "voteCount": 25765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.04476331493742
      }
    },
    {
      "id": "277834c74bea6c4ff8beb93f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1444.9588468416032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.700172604993,
        1450.2175210782134
      ],
      "voteCount": 17157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.198737775820183
      }
    },
    {
      "id": "1eedb2a9315c9708b3841f00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1448.234504931808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.9190540847273,
        1451.5499557788887
      ],
      "voteCount": 58050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.861468736874784
      }
    },
    {
      "id": "0e1a30ee03281de6a25314f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1445.3630363630032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.7969806631259,
        1448.9290920628807
      ],
      "voteCount": 88991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.310396869575246
      }
    },
    {
      "id": "7ec7a23c4a467c83c870761f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1462.3733292471093,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0329200660526,
        1469.7137384281662
      ],
      "voteCount": 7479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.026339851693805
      }
    },
    {
      "id": "ce3c13d944d5e3c08ad8e914",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1468.0485023183726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.7710981343453,
        1483.3259065024
      ],
      "voteCount": 2097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.75792804150423
      }
    },
    {
      "id": "41048986041e9d2bf05e8352",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1468.526506338958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0825118871646,
        1481.9705007907512
      ],
      "voteCount": 2486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.050090930608704
      }
    },
    {
      "id": "672c700bb39746a7016ef497",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1456.4600518586062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.3610840994604,
        1460.5590196177523
      ],
      "voteCount": 31612,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.373738591184993
      }
    },
    {
      "id": "955d129b4000381723400d91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1458.343683758279,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0874298148044,
        1461.5999377017533
      ],
      "voteCount": 63005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.760198726398575
      }
    },
    {
      "id": "0fdfebe49c2dd244bb37e468",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1435.8470912000037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.1029022640373,
        1440.59128013597
      ],
      "voteCount": 22001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.859057642085879
      }
    },
    {
      "id": "6123b503cf07be96b50ac6a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1430.631085001898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.9181806492616,
        1435.3439893545349
      ],
      "voteCount": 22489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.7820397077920695
      }
    },
    {
      "id": "6d0b332ad60e6492202ab039",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1468.3789758964542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.3774817577662,
        1475.3804700351425
      ],
      "voteCount": 8651,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.761016702823122
      }
    },
    {
      "id": "31b33324fad286e4d0af2bdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1470.5614556269168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.7200568903374,
        1475.402854363496
      ],
      "voteCount": 20064,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.1016251431057205
      }
    },
    {
      "id": "d0a8dd88edefc60794de4a75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1448.252348648031,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.490825567239,
        1456.013871728823
      ],
      "voteCount": 6465,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.68186549577049
      }
    },
    {
      "id": "326985a18139b73ec1a05ff5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1467.5797359235812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.0376285389143,
        1475.1218433082481
      ],
      "voteCount": 7660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.807755713900493
      }
    },
    {
      "id": "dfbd6c0cc9000717ee6d1197",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1459.9327001076222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.236904265279,
        1463.6284959499656
      ],
      "voteCount": 42919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.5556562092246202
      }
    },
    {
      "id": "4b63856c6faddd5582686b85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1445.8808719333083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.5038471227144,
        1450.2578967439022
      ],
      "voteCount": 27283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.9872579889044255
      }
    },
    {
      "id": "f6e00d5e62082a171c5c2498",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1439.532373871508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.5604665996325,
        1443.5042811433839
      ],
      "voteCount": 33361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.106785498101019
      }
    },
    {
      "id": "6c9c74ff10aee5904bdf6c01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1450.60855897471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.5212319451416,
        1466.6958860042782
      ],
      "voteCount": 1796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.37078361014797
      }
    },
    {
      "id": "c77d37583a0eb66ca8c7cdfd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1416.5755335080125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.742122883201,
        1430.4089441328238
      ],
      "voteCount": 2368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.815254684954816
      }
    },
    {
      "id": "438d82f3e43d926b65fe96af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1456.9218214907737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.7703191577978,
        1461.0733238237497
      ],
      "voteCount": 31190,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.486569406356491
      }
    },
    {
      "id": "605cd5b270610bfdfb9fde08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1441.7376189973909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.6412846579951,
        1448.8339533367864
      ],
      "voteCount": 7541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.10907220590378
      }
    },
    {
      "id": "c941d7008db9b9b77b3ab67e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1448.5324329814118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.6930020307964,
        1453.371863932027
      ],
      "voteCount": 20759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.096666141417033
      }
    },
    {
      "id": "831fab7782ee275d07bfab36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1445.888741236957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.3617382724026,
        1448.4157442015116
      ],
      "voteCount": 122636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 1.662322643800538
      }
    },
    {
      "id": "e1a826c7e7f23853571ee374",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1452.9531462406467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.6045961273603,
        1459.301696353933
      ],
      "voteCount": 9801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.491870516427005
      }
    },
    {
      "id": "64662cd67f2cd666491e0854",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-2.5-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1450.2496525463348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.2981846125588,
        1463.2011204801108
      ],
      "voteCount": 2864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.66583880477959
      }
    },
    {
      "id": "83184e77283a975fc6ca0962",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1495.3161064712667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.8004462360007,
        1507.831766706533
      ],
      "voteCount": 2567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.7766315965146
      }
    },
    {
      "id": "3d9eaa59c437763fc6f6c20d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1494.5441674881286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.5467370269205,
        1500.5415979493366
      ],
      "voteCount": 12797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.363414737978824
      }
    },
    {
      "id": "a6e641c3a82dccb1cd5a78e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1449.3355845878766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.0735669631415,
        1456.597602212612
      ],
      "voteCount": 8245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.72835228582168
      }
    },
    {
      "id": "21b65243b7e8114959953250",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1463.3872288486007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.7318471232434,
        1468.042610573958
      ],
      "voteCount": 24662,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.641757472978645
      }
    },
    {
      "id": "2ebd993076f3dd2ee196859a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1467.4355612376974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.5847398720146,
        1472.2863826033802
      ],
      "voteCount": 38106,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.1253989747344875
      }
    },
    {
      "id": "6e28c0934c191895b451bfa3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1468.3637732178818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.646820773706,
        1478.0807256620576
      ],
      "voteCount": 4154,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.57898658023716
      }
    },
    {
      "id": "befe4c0c45bfce9984e1b545",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1481.9027553108524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.6828606320732,
        1500.1226499896316
      ],
      "voteCount": 1420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.41627506651749
      }
    },
    {
      "id": "0dc158b146f7e24cb905e1cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1472.0446822243728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.895065222726,
        1493.1942992260197
      ],
      "voteCount": 869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.44177907275458
      }
    },
    {
      "id": "d965a61b7705a6a0bfbef883",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1474.2703864744963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.6943929737533,
        1479.8463799752392
      ],
      "voteCount": 15325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.093722976499093
      }
    },
    {
      "id": "89db9282e9f1a718a8f8e447",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1477.8130291719349,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.4136291487437,
        1482.212429195126
      ],
      "voteCount": 31426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.038377727698112
      }
    },
    {
      "id": "ace51c691734ae679c848383",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1458.883242373036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.3969165069755,
        1465.3695682390965
      ],
      "voteCount": 10224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.952199464974013
      }
    },
    {
      "id": "62539f80154aa15148ceac92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1442.633896353969,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.0817065609158,
        1449.1860861470223
      ],
      "voteCount": 10252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.175751996329865
      }
    },
    {
      "id": "2cb32bfd5e5ddf223bc4b8a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1476.0476505226522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.3040521858677,
        1485.791248859437
      ],
      "voteCount": 4071,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.713972732743926
      }
    },
    {
      "id": "f246fb702180e1bf0f04473f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1484.7661793610034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.8843259162054,
        1491.6480328058014
      ],
      "voteCount": 8567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.328625411926568
      }
    },
    {
      "id": "e33839858dbeec535d2f629a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1451.0339773296007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.9233253926095,
        1463.144629266592
      ],
      "voteCount": 2584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.18025838226945
      }
    },
    {
      "id": "333ef00881b9c788662a81f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1484.8755959908913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.5055014410361,
        1495.2456905407466
      ],
      "voteCount": 3681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.994276651781334
      }
    },
    {
      "id": "f7d7e1f361367e069e7f068a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1489.40408302973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.304697039959,
        1494.5034690195012
      ],
      "voteCount": 19479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.769234992860071
      }
    },
    {
      "id": "3e52e2c26e57e888f6ad3477",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1449.0339431050681,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.8932017097175,
        1455.1746845004186
      ],
      "voteCount": 11986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.816246026492264
      }
    },
    {
      "id": "8d27b5d5138fffaf70759470",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1445.3855738813143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.8937862386142,
        1450.8773615240145
      ],
      "voteCount": 15758,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.851114100206404
      }
    },
    {
      "id": "472ec7f1e04b756929bc88f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1439.0556832831485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.184055831715,
        1470.927310734582
      ],
      "voteCount": 400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.43095808571417
      }
    },
    {
      "id": "a2c69c14f30f470b26210860",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1441.8706660561738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.4956188857168,
        1464.2457132266306
      ],
      "voteCount": 803,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.32620138557456
      }
    },
    {
      "id": "f6739eaf63fcc72dae73822d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1464.3639298900896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.8455951014905,
        1469.8822646786887
      ],
      "voteCount": 17413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.927201685728509
      }
    },
    {
      "id": "869565ffc8f2cf591d3149c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1455.2484031519725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.5963248507665,
        1465.9004814531788
      ],
      "voteCount": 3175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.5374172758994
      }
    },
    {
      "id": "4b8e84d592633befe0b732da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1479.1611381222583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.3781349174023,
        1485.9441413271145
      ],
      "voteCount": 9507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.976994840927322
      }
    },
    {
      "id": "f58b444bd2c23cf958c1a7a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1461.4302682364603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.9315003083675,
        1464.9290361645533
      ],
      "voteCount": 52876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.186647986099991
      }
    },
    {
      "id": "ff5208929f73c33c36043e6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1473.7652029071958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.4205247088316,
        1482.1098811055601
      ],
      "voteCount": 5785,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.12687770050702
      }
    },
    {
      "id": "85f7d8dd344cf67748870b7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash (thinking-minimal)",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1439.509139606238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.6650846891475,
        1456.3531945233285
      ],
      "voteCount": 1479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.85792723366907
      }
    },
    {
      "id": "dea91d0ffbc342cc9eb8bb8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1521.0670305945212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1505.6536034021522,
        1536.48045778689
      ],
      "voteCount": 1516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.8446660249577
      }
    },
    {
      "id": "5ce6b0682f8300b50e4105e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1508.7457502484128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.7629738553655,
        1516.7285266414603
      ],
      "voteCount": 6383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.588676832381456
      }
    },
    {
      "id": "0767fabd27a4695b146a6d88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1459.0957492825673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.6004920371215,
        1468.5910065280134
      ],
      "voteCount": 4684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.470226902211543
      }
    },
    {
      "id": "fc124d4988eddc13e7baa302",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1475.0283885868548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.9840016867274,
        1481.072775486982
      ],
      "voteCount": 14112,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.510609043006351
      }
    },
    {
      "id": "1b334eeb389c1d33f8b3c59b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1485.4797642042317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.1581058593545,
        1491.801422549109
      ],
      "voteCount": 21833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.403173922904683
      }
    },
    {
      "id": "80fe1a9d23a450def7e5832d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1496.9721010016601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.6153949072673,
        1510.328807096053
      ],
      "voteCount": 1928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.44110636587691
      }
    },
    {
      "id": "5f3b17dae6b2756e85923b4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1507.9013539168136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.5236748316806,
        1531.2790330019466
      ],
      "voteCount": 754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.2677958861236
      }
    },
    {
      "id": "177f2b809d276c8d872cede0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1494.4304157808535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.8807120703134,
        1520.9801194913935
      ],
      "voteCount": 527,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.49455246538162
      }
    },
    {
      "id": "8d0d27522176d9c9c6d68550",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1487.5578831047105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.1977081226669,
        1494.9180580867544
      ],
      "voteCount": 7867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.101980079670183
      }
    },
    {
      "id": "4d8c0534fb456e334d8479ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1492.430045419313,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.7608172336745,
        1498.0992736049516
      ],
      "voteCount": 16571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.36665176461032
      }
    },
    {
      "id": "77342c667992a4396f3f4a5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1469.7804220293178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.4293522929436,
        1478.1314917656919
      ],
      "voteCount": 5626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.154656602354024
      }
    },
    {
      "id": "bdeff51cc867169c5e332090",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1453.6442801338014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.0863604843441,
        1462.2021997832587
      ],
      "voteCount": 5589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.065150023743797
      }
    },
    {
      "id": "7c056155c81d21a5b792d9d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1487.0172038377448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.4081256216987,
        1499.6262820537909
      ],
      "voteCount": 2313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.387624045815585
      }
    },
    {
      "id": "c6f837ec28e65c81e272f88d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1485.4201862608375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.5273342661958,
        1494.3130382554791
      ],
      "voteCount": 4893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.586662590935376
      }
    },
    {
      "id": "af1976ac48efba07d293bb5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1472.166273045647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.4977048845838,
        1487.8348412067098
      ],
      "voteCount": 1415,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.909061551132126
      }
    },
    {
      "id": "f236d01268ab0efc67dcb4f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1484.831634301416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.5058976527962,
        1498.1573709500358
      ],
      "voteCount": 2068,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.225995257781165
      }
    },
    {
      "id": "ad6267fc292c0aed41c83d92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1500.870176250864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.2087169669765,
        1507.5316355347516
      ],
      "voteCount": 10515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.551611474224371
      }
    },
    {
      "id": "e2c8670a6a0965fb123ba8c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1461.1728232592504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.207895078591,
        1469.1377514399098
      ],
      "voteCount": 6831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.514580497728733
      }
    },
    {
      "id": "bd51d8b87bb77eff3f566aeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1457.9415477178707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.6416506401963,
        1465.241444795545
      ],
      "voteCount": 8090,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.87194288210787
      }
    },
    {
      "id": "79766e43f6f1646245f8d8fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1492.896350399365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.73475963185,
        1531.05794116688
      ],
      "voteCount": 272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 379.1025956238519
      }
    },
    {
      "id": "cc13f541a14c1dc178c4c4a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1448.2446170014582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.4186202077133,
        1475.0706137952031
      ],
      "voteCount": 533,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.3335463343535
      }
    },
    {
      "id": "87306358905e30eadb80b802",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1475.1764331503418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.7808373251457,
        1482.572028975538
      ],
      "voteCount": 7878,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.238038246047262
      }
    },
    {
      "id": "6cfa4790701248d01ecc68f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1476.331219905227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.1854435529247,
        1489.4769962575294
      ],
      "voteCount": 2004,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.98588790638829
      }
    },
    {
      "id": "7b8ea6034269710a4aed7e06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1483.6643731454712,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.9998894014886,
        1492.3288568894536
      ],
      "voteCount": 5312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.542908580801097
      }
    },
    {
      "id": "787fcfb5074a41ac528a2428",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1473.2456484893928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.8195717156677,
        1477.671725263118
      ],
      "voteCount": 30732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.099665653417
      }
    },
    {
      "id": "73eed70645732e7221f5d854",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1485.0873700900615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.5658365186684,
        1495.6089036614549
      ],
      "voteCount": 3272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.817872027572726
      }
    },
    {
      "id": "fecd7272465d74602c9df6ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1468.4244287834229,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.2911221349837,
        1489.557735431862
      ],
      "voteCount": 834,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.26225107269647
      }
    },
    {
      "id": "ac18cb893d3b0de595941348",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1528.1127251999883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1514.5202482642298,
        1541.7052021357465
      ],
      "voteCount": 2108,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.09512163812186
      }
    },
    {
      "id": "393ad1db651b892a9589bf22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1518.7693155941488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1511.6537568166164,
        1525.8848743716812
      ],
      "voteCount": 8575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.1801950976977
      }
    },
    {
      "id": "e9673d11ef9e39c78a4c41aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1485.3194664554414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.9661764378886,
        1493.6727564729943
      ],
      "voteCount": 6290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.16431136563346
      }
    },
    {
      "id": "546be98bde442741a81ff459",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1489.3107554013645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.0351569474872,
        1494.5863538552417
      ],
      "voteCount": 18969,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.245148352657092
      }
    },
    {
      "id": "1fd7c563644dd610bbddab46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1501.5727205156325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.0603196927366,
        1507.0851213385286
      ],
      "voteCount": 29678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.910162323898971
      }
    },
    {
      "id": "b7b14caa0be83296407fe6a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1502.811034709312,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.7490005477569,
        1514.8730688708672
      ],
      "voteCount": 2534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.874327151640365
      }
    },
    {
      "id": "bdbe442886201b8a3aeca087",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1510.3972551693837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.9585010271012,
        1531.8360093116662
      ],
      "voteCount": 891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.6473008371811
      }
    },
    {
      "id": "24ab05195ba13c931f3b85d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1518.1622595027393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.312905611432,
        1541.0116133940467
      ],
      "voteCount": 760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.91007937861127
      }
    },
    {
      "id": "69db03502c9aea96ebf3561b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1502.3040135772324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.7833712815097,
        1508.8246558729552
      ],
      "voteCount": 10734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.068393007291089
      }
    },
    {
      "id": "5b6faf0d926196ca00384a7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1504.1249618048585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1499.1155486069028,
        1509.1343750028143
      ],
      "voteCount": 22465,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.53247158414624
      }
    },
    {
      "id": "8c9d96129d55d35a24887488",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1475.371675454228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.882360065916,
        1482.8609908425396
      ],
      "voteCount": 7577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.601183457557
      }
    },
    {
      "id": "9c6c3726c6a61736b8b8a87a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1468.5688368888132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.9871655852621,
        1476.150508192364
      ],
      "voteCount": 7677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.96351840228748
      }
    },
    {
      "id": "70b74081ee52841d09ccc215",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1502.2822131093765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.0461927231431,
        1513.51823349561
      ],
      "voteCount": 2907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.86463815250297
      }
    },
    {
      "id": "e149a396802884efc5fb7520",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1498.812138806159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.9143245639332,
        1506.709953048385
      ],
      "voteCount": 6722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.237443303748712
      }
    },
    {
      "id": "f6232c8fea8c515db00b1641",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1482.1950308193466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.747970916505,
        1495.6420907221882
      ],
      "voteCount": 1941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.07154976034246
      }
    },
    {
      "id": "d66b35557f1a7004ff395f51",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1509.391784241334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.1395324394769,
        1521.6440360431914
      ],
      "voteCount": 2541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.07829843376778
      }
    },
    {
      "id": "0a0fc8b6d0e923f20e78ea70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1510.8445877206082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.947780840995,
        1516.7413946002214
      ],
      "voteCount": 14260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.051855817934024
      }
    },
    {
      "id": "9f0a3e00c731d62ef439f522",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1481.2065898403196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.1453626024208,
        1488.2678170782183
      ],
      "voteCount": 9252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.979686216246407
      }
    },
    {
      "id": "85a65b0bd31536dbb49dec40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1474.356617752634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.9260216100172,
        1480.787213895251
      ],
      "voteCount": 11187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.76480802727086
      }
    },
    {
      "id": "54a88afd5a3be6b167cdf7e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1507.3519384819613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.9380638184118,
        1539.7658131455107
      ],
      "voteCount": 406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 273.5052800889954
      }
    },
    {
      "id": "e89868113b5f5524528908cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1453.061944296333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.4810916794086,
        1477.6427969132571
      ],
      "voteCount": 664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.28876543463156
      }
    },
    {
      "id": "0511b1017ba04d442410b976",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1492.4114490567972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.7466593465704,
        1499.0762387670243
      ],
      "voteCount": 10496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.563164921164091
      }
    },
    {
      "id": "d519194b65ac48eae039a362",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1478.166966915756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.710870286608,
        1489.6230635449037
      ],
      "voteCount": 2653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.16466402538674
      }
    },
    {
      "id": "439a115c6e1e94c4a73ecf76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1495.3940535070456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.490669071926,
        1503.2974379421648
      ],
      "voteCount": 6770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.260355361039682
      }
    },
    {
      "id": "1062aba8fed4da8495c1e917",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1485.9741804559108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.1091208644905,
        1489.8392400473313
      ],
      "voteCount": 41332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.8888053582026525
      }
    },
    {
      "id": "ebc0f9704e9943709cfa5fa7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1502.39844391147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.7591279700046,
        1512.0377598529356
      ],
      "voteCount": 4045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.187793272401198
      }
    },
    {
      "id": "a83438019f83028bdf7e5704",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1473.3030081948705,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.6349536923453,
        1492.9710626973958
      ],
      "voteCount": 1039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.69934000864981
      }
    },
    {
      "id": "07b6e4e68bafc09003fc8384",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1473.6931147411685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.4322147007604,
        1487.954014781577
      ],
      "voteCount": 1933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.94167644513982
      }
    },
    {
      "id": "933a4c5b4582de76c9e493d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1458.9560002547953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.9141608727432,
        1465.9978396368474
      ],
      "voteCount": 9137,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.908507990633872
      }
    },
    {
      "id": "f7c11a48b0f7c7e5a31c29b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1413.96932361919,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.2146729714564,
        1422.7239742669235
      ],
      "voteCount": 5375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.95177132993768
      }
    },
    {
      "id": "759848bd20b48ddff2ccfa0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1435.7046450392604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.1389182858672,
        1441.2703717926533
      ],
      "voteCount": 16489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.063945427856405
      }
    },
    {
      "id": "2d10c1216ff279a0f79452ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1428.452452702752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.622359726258,
        1434.282545679246
      ],
      "voteCount": 25479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.84819692234052
      }
    },
    {
      "id": "9ea942bce68a170131f6fcb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1447.098991615594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.8241903172877,
        1458.3737929139004
      ],
      "voteCount": 2999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.09189301509164
      }
    },
    {
      "id": "7655d529e113461a6a6fc760",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1447.951669585579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.2636964345027,
        1468.6396427366553
      ],
      "voteCount": 1048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.41398439416862
      }
    },
    {
      "id": "5516db99979fafc261085248",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1447.1477794342493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.9039370048781,
        1472.3916218636202
      ],
      "voteCount": 571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 165.8879114272971
      }
    },
    {
      "id": "b1db45368052f17fe5bb3fd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1441.9765781889537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.3556884606724,
        1448.5974679172352
      ],
      "voteCount": 10731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.411336900948795
      }
    },
    {
      "id": "792c9c3ada8ef7d7aa12c243",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1444.654271152673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.4148058896862,
        1449.8937364156595
      ],
      "voteCount": 21672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.146242488441859
      }
    },
    {
      "id": "2b9a5a7cb398ae96196d1764",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1421.366174745253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.5595530020876,
        1429.1727964884185
      ],
      "voteCount": 6658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.864635255897714
      }
    },
    {
      "id": "685dcec0852b4afd0d2d85e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1403.1726175339713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.357443438037,
        1410.9877916299056
      ],
      "voteCount": 6787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.899414519488543
      }
    },
    {
      "id": "a448b3b7eba360c6a00c64f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1435.2682961749354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.382715777541,
        1447.1538765723296
      ],
      "voteCount": 2683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.77431621078698
      }
    },
    {
      "id": "09103f677df800bf9366bf2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1453.4447730300858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.2327646131712,
        1461.6567814470006
      ],
      "voteCount": 5703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.555070973608135
      }
    },
    {
      "id": "36de2df35ab0c13614c327a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1434.290968494818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.3852058471516,
        1448.1967311424842
      ],
      "voteCount": 1912,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.33770862557064
      }
    },
    {
      "id": "0ed700abfdd4aee8a5a9259f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1456.8692396777487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.5232060563853,
        1469.2152732991121
      ],
      "voteCount": 2482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.67881820279231
      }
    },
    {
      "id": "b6caedcf5ecf7e0b5c7f687b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1454.3084384135836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.2707619802009,
        1460.3461148469662
      ],
      "voteCount": 13474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.489503445370275
      }
    },
    {
      "id": "f233d180cf7353b23058dea5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1422.1365880086903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.9058253165717,
        1429.3673507008089
      ],
      "voteCount": 8038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.6104359177503
      }
    },
    {
      "id": "c159a7faa1d5356becd1af2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1410.4884933365536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.0672708900408,
        1416.909715783066
      ],
      "voteCount": 10967,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.733447794748736
      }
    },
    {
      "id": "f3915ba4fccf2c467b7f2bc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1422.862687337747,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.2274132579441,
        1459.4979614175502
      ],
      "voteCount": 278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 349.3837548569045
      }
    },
    {
      "id": "8e3c245dad78bb4fa5504ab7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1416.2920746197178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.579456351421,
        1441.0046928880147
      ],
      "voteCount": 646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.97957785844616
      }
    },
    {
      "id": "3e99676d4247c59e03238153",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1430.1007962828617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.7403766035316,
        1436.461215962192
      ],
      "voteCount": 12714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.531139440901528
      }
    },
    {
      "id": "997c5959db1fe3b83f81f696",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1435.9320524093205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.2069372907492,
        1448.6571675278917
      ],
      "voteCount": 2157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.15288054334224
      }
    },
    {
      "id": "a3a133e3e6794bc0ba853c02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1439.1409797245249,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.1573363886594,
        1447.1246230603904
      ],
      "voteCount": 6347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.59228014392571
      }
    },
    {
      "id": "aedc088389f8af98f36d1004",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1433.4903753005551,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.2404405474529,
        1437.7403100536576
      ],
      "voteCount": 35135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.701845379241389
      }
    },
    {
      "id": "427d9b10f71f46be8bd1d179",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1432.1046736253895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.2910872187276,
        1441.9182600320516
      ],
      "voteCount": 3855,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.070287788122126
      }
    },
    {
      "id": "1ef13210f2663bb6e3641a18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-flash-lite-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1445.80707041769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.7980072709524,
        1464.8161335644277
      ],
      "voteCount": 1060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.06439027019576
      }
    },
    {
      "id": "136ce4771f7307a03e7fcc6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1533.5230386550725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1520.148112914265,
        1546.8979643958796
      ],
      "voteCount": 2265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.56789176248028
      }
    },
    {
      "id": "7ed2eb310a5fca584747607b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1524.6400136399675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1518.127053076226,
        1531.152974203709
      ],
      "voteCount": 11296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.042329824372821
      }
    },
    {
      "id": "049a30a7d96e1815924c867e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1483.3640301849043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.2760518098946,
        1491.452008559914
      ],
      "voteCount": 7005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.028789646846867
      }
    },
    {
      "id": "6f29a215e4988a148f4acc05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1489.538008401757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.2511175273376,
        1494.8248992761767
      ],
      "voteCount": 20506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.276198033790344
      }
    },
    {
      "id": "6b5568ef18912b11e97610b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1503.3443421876364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.7393784372418,
        1508.9493059380309
      ],
      "voteCount": 32069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.178043839491158
      }
    },
    {
      "id": "c3c9b2f373e200424ec5e984",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1518.1348829025628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.7518058048047,
        1528.517960000321
      ],
      "voteCount": 3755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.064413820400876
      }
    },
    {
      "id": "eae05b7b7d48d76508a16bac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1505.208344635412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.4676433093073,
        1523.949045961517
      ],
      "voteCount": 1319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.42721621855249
      }
    },
    {
      "id": "d35f44664399c225169e6059",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1499.6042059755366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.108563891352,
        1522.099848059721
      ],
      "voteCount": 765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.7348268979457
      }
    },
    {
      "id": "e1cf0489a4f8d9d467f0258b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1507.9796111437095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1501.80199807888,
        1514.1572242085392
      ],
      "voteCount": 13169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.93448191431029
      }
    },
    {
      "id": "a09d6f0b8eb21594519ddb1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1508.902148984086,
      "unit": "Arena rating",
      "confidenceInterval": [
        1503.8795204613914,
        1513.9247775067806
      ],
      "voteCount": 26732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.566983652431308
      }
    },
    {
      "id": "d21c874ffc1af56b37460815",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1476.4114288091196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.2045450550406,
        1483.6183125631987
      ],
      "voteCount": 8389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.52068989130128
      }
    },
    {
      "id": "8c18cab45873f220da8d42dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1469.328738736398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.9427141353292,
        1476.7147633374668
      ],
      "voteCount": 8536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.20120895575195
      }
    },
    {
      "id": "368be5d265cafd38aac538c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1499.06951306971,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.1055638033322,
        1510.0334623360875
      ],
      "voteCount": 3326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.292326464138114
      }
    },
    {
      "id": "b0aeee364512364327f7bb26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1509.1763986953542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1501.535749777,
        1516.8170476137084
      ],
      "voteCount": 7077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.197225486071417
      }
    },
    {
      "id": "469b214c77f138b6af642c7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1494.5974508015945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.6462789683937,
        1507.5486226347953
      ],
      "voteCount": 2280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.66384222304006
      }
    },
    {
      "id": "a319bf916ac6ad21cb4762ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1503.3281615998776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.1749027662677,
        1514.4814204334875
      ],
      "voteCount": 3186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.38227673803828
      }
    },
    {
      "id": "413b9dfb0a356c2d86e41715",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1514.108195418871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1508.428711915612,
        1519.7876789221302
      ],
      "voteCount": 16588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.396948755515703
      }
    },
    {
      "id": "d5758e96d95747e3ad667a3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1479.2412816479336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.4341100986617,
        1486.0484531972056
      ],
      "voteCount": 10210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.062496739935114
      }
    },
    {
      "id": "4f31fef49d03aef91f987840",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1484.357205428239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.2296435441237,
        1490.4847673123543
      ],
      "voteCount": 13488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.774155183284648
      }
    },
    {
      "id": "b1f3c3a3394e29ea4f709aba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1511.2991454685139,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.9186836773217,
        1545.6796072597058
      ],
      "voteCount": 351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 307.6998109697369
      }
    },
    {
      "id": "ba4ed692dfb8d1bb8a810c33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1474.4236278239878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.3466174261675,
        1497.5006382218082
      ],
      "voteCount": 795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.6318150886444
      }
    },
    {
      "id": "9c379635bed71f6132109016",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1499.0495051162168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.0314039770471,
        1505.0676062553866
      ],
      "voteCount": 15876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.428069650563604
      }
    },
    {
      "id": "71d9c038282e4a23216bbc76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1500.4878320284472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.4908877513,
        1512.4847763055946
      ],
      "voteCount": 2601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.46667052986085
      }
    },
    {
      "id": "bc942b16db956056b58816c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1496.4330662954576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.8017716441293,
        1504.064360946786
      ],
      "voteCount": 7482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.160037051984258
      }
    },
    {
      "id": "d45dcacaf82df95a0338f110",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1487.449481853994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.3827525217912,
        1491.5162111861969
      ],
      "voteCount": 43742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.305210138478085
      }
    },
    {
      "id": "8e657976d52803a19bcda549",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1498.4005633052357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.044575467178,
        1507.7565511432936
      ],
      "voteCount": 4710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.786788173891953
      }
    },
    {
      "id": "695a33895b1129d7e0bb709c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.1-pro-preview",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1488.2642354277355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.1766890562058,
        1505.3517817992652
      ],
      "voteCount": 1463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.00868696710853
      }
    },
    {
      "id": "5159e6d87c0a28ae635fab43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1514.0872275040902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.8873506003463,
        1541.2871044078338
      ],
      "voteCount": 492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.5917569630824
      }
    },
    {
      "id": "cbce5436908b0065420fcdbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1506.2564061463584,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.9326676431579,
        1518.580144649559
      ],
      "voteCount": 2592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.5356393974894
      }
    },
    {
      "id": "8410534473e21a524cca300e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1464.244509746484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.4283828152202,
        1481.0606366777477
      ],
      "voteCount": 1376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.61321262771655
      }
    },
    {
      "id": "7077cee3c4773a6c6b5d6787",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1474.6017534970717,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.2318146302223,
        1483.9716923639214
      ],
      "voteCount": 4357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.854795135519286
      }
    },
    {
      "id": "9807b1c3ad5267fa478d4e88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1490.732495126458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.4969718661287,
        1499.9680183867872
      ],
      "voteCount": 6732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.203775667878052
      }
    },
    {
      "id": "53d68e59c4a81facd45ff4cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1512.0969688032064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.1401264372814,
        1532.0538111691317
      ],
      "voteCount": 899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.67820554859406
      }
    },
    {
      "id": "05e3af8635fa9145bfce4d94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1462.8710486839848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.4249080848456,
        1498.3171892831238
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 327.0707671277108
      }
    },
    {
      "id": "f8411eff756ade4baa7f39f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1482.2161327139372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.7999959846381,
        1493.6322694432363
      ],
      "voteCount": 2982,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.926740830844565
      }
    },
    {
      "id": "24ad5b79c104b9625ed4970b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1493.6978797432714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.41274354794,
        1501.983015938603
      ],
      "voteCount": 5907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.86911821243725
      }
    },
    {
      "id": "0bac05c0399fd24fb9ab719f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1453.9838702113966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.7448551989805,
        1468.2228852238125
      ],
      "voteCount": 1818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.77931067009909
      }
    },
    {
      "id": "dce110569432dfdd050c93ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1449.741855138482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.9780523189688,
        1464.505657957995
      ],
      "voteCount": 1778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.74143180170185
      }
    },
    {
      "id": "2ed308d619b0973c19302c7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1474.7077393514387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.5782068592778,
        1497.8372718435996
      ],
      "voteCount": 689,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.2635710225477
      }
    },
    {
      "id": "1c06e74d88399538ed7208cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1497.018291038474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.289459464137,
        1512.7471226128112
      ],
      "voteCount": 1445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.40161257518268
      }
    },
    {
      "id": "4a5f3ba94eeb7210e56ffc05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1506.209195103314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.5976385745846,
        1531.820751632043
      ],
      "voteCount": 561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.75591811388125
      }
    },
    {
      "id": "a332ec5c7fc22216938bcd5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1488.1129220324362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.0783652257114,
        1512.1474788391608
      ],
      "voteCount": 633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.37514336579542
      }
    },
    {
      "id": "8d597a31da7751549fd3a21b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1501.1480865582384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.8321128824693,
        1511.4640602340073
      ],
      "voteCount": 3669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.70283838677965
      }
    },
    {
      "id": "e77f197567d440bbceada962",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1465.9695707821547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.4800863492098,
        1479.4590552150994
      ],
      "voteCount": 2056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.36903316167286
      }
    },
    {
      "id": "3b21f83c11315fd41b11fa8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1463.151257444765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.929362389444,
        1474.3731525000862
      ],
      "voteCount": 2954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.78205872056859
      }
    },
    {
      "id": "b10438199a81e523ae83a429",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1466.791469221364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.4517071951727,
        1508.131231247555
      ],
      "voteCount": 192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 444.87680439935554
      }
    },
    {
      "id": "8ab6da2a094ccbd1b9992f57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1480.175424841105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.6487974466188,
        1490.7020522355913
      ],
      "voteCount": 3663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.845782155833867
      }
    },
    {
      "id": "704cdb14a773412c92ca0afc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1523.82896713276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.6994973690457,
        1549.9584368964745
      ],
      "voteCount": 526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.73174775552957
      }
    },
    {
      "id": "b664e0910a6b94a245edf6ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1487.934392926633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.5360834511941,
        1503.3327024020716
      ],
      "voteCount": 1580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.723409196546534
      }
    },
    {
      "id": "5ba093132264a6e7c73a43ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1479.0806071130476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.3367114025896,
        1485.8245028235053
      ],
      "voteCount": 9045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.839285926619581
      }
    },
    {
      "id": "c10665d542e04736692cf29a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1509.0063638180784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.517453279139,
        1529.4952743570177
      ],
      "voteCount": 903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.28021740365925
      }
    },
    {
      "id": "e89997f5a348dbd1baf51b98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-3.5-flash",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1461.3740455161837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.7372864000995,
        1494.010804632268
      ],
      "voteCount": 333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.27956886150855
      }
    },
    {
      "id": "051813e74fb39533a9933390",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1344.8078526329207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.6992245073275,
        1355.916480758514
      ],
      "voteCount": 5932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.12363442969866
      }
    },
    {
      "id": "34a3fdafb1e8e5e15d58beb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1337.573049067789,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.5485689853624,
        1346.5975291502157
      ],
      "voteCount": 8138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.200602312691124
      }
    },
    {
      "id": "a92c88e41521143b464256c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1343.3405432458126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.4157234218937,
        1353.2653630697312
      ],
      "voteCount": 7025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.641833775912232
      }
    },
    {
      "id": "176f714e698e5dcd6465d02e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1342.094195751418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.0351824102265,
        1348.1532090926098
      ],
      "voteCount": 26318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.556693012292577
      }
    },
    {
      "id": "5a915abf3c28e4e8e9696a2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1284.3675864385154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.934690508936,
        1291.800482368095
      ],
      "voteCount": 34077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.382021122375571
      }
    },
    {
      "id": "2325939bc565181bf301dff0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1293.478945371941,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.0768963914652,
        1307.880994352417
      ],
      "voteCount": 2449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.99485573518262
      }
    },
    {
      "id": "b0c7e44407130461d7180852",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1367.1482227312385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.2264846440635,
        1393.0699608184136
      ],
      "voteCount": 754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.91701377621146
      }
    },
    {
      "id": "5fb6dcfc1328c3973ed75b8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1326.6553060988351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.4256636587756,
        1343.8849485388944
      ],
      "voteCount": 1779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.27808430825557
      }
    },
    {
      "id": "3fd4c3da3dd7afd086ca52ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1328.624147040247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.8631583900992,
        1337.3851356903947
      ],
      "voteCount": 8405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.980670289769865
      }
    },
    {
      "id": "97538cd61059a9db418350fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1325.2545267722885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.9395352851725,
        1332.5695182594045
      ],
      "voteCount": 14100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.929369792622346
      }
    },
    {
      "id": "0af4c25806419d2c1768d45c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1314.9566048775855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.4464602824933,
        1325.4667494726782
      ],
      "voteCount": 6130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.755518298069774
      }
    },
    {
      "id": "50b295c7c6532b4ff7b22723",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1336.4637887028102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.9306613174044,
        1345.9969160882163
      ],
      "voteCount": 7526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.65781386404548
      }
    },
    {
      "id": "fe0f6a56753edf112e6828b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1376.2748107857665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.1479530487018,
        1390.4016685228312
      ],
      "voteCount": 2962,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.95112555891018
      }
    },
    {
      "id": "dc93563912b24c4ef6801f0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1343.1628505363292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.9136721352263,
        1352.4120289374318
      ],
      "voteCount": 8815,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.26948278986572
      }
    },
    {
      "id": "50314c8c0293ba94599f74cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1317.0224435270604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.1396220668548,
        1326.905264987266
      ],
      "voteCount": 5787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.425278409375565
      }
    },
    {
      "id": "28546aa2af7694d142508d47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1341.613651759324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.3553220321737,
        1355.8719814864744
      ],
      "voteCount": 2701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.922594279274605
      }
    },
    {
      "id": "2ea3774748abc7accef9db56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1340.5129159341384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.8754009946556,
        1348.1504308736212
      ],
      "voteCount": 13757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.184761095599779
      }
    },
    {
      "id": "068172934af2b5389e505f0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1338.7652746302158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.8921173331055,
        1346.638431927326
      ],
      "voteCount": 13201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.13621509909584
      }
    },
    {
      "id": "15b3470744a48d5579293b3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1315.1796031775602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.397707083139,
        1321.9614992719812
      ],
      "voteCount": 18524,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.97308542987686
      }
    },
    {
      "id": "28a8cd0aba82f4239b4a927e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1290.947444948209,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.7282353040016,
        1311.1666545924168
      ],
      "voteCount": 1212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.42218431031978
      }
    },
    {
      "id": "67ebc7c07156bff1bebf5a3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1285.2499738569736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.7282165029405,
        1305.7717312110065
      ],
      "voteCount": 1945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.63088361876719
      }
    },
    {
      "id": "321f1089f903cfadffb7af13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1323.2158406750905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.7422631904292,
        1333.6894181597515
      ],
      "voteCount": 5486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.55577280596203
      }
    },
    {
      "id": "22a37f4a5f4c1682bf673226",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1304.686269481855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.1941205344883,
        1314.1784184292223
      ],
      "voteCount": 6395,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.454863333071465
      }
    },
    {
      "id": "b8ba6ec2b6171159740adf0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1321.0662791270217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.4925609121099,
        1330.6399973419336
      ],
      "voteCount": 7776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.859706621031602
      }
    },
    {
      "id": "9e05d7b2c6d7b118e46147cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1334.8488078710966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.695182993708,
        1340.002432748485
      ],
      "voteCount": 50148,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.914000804527591
      }
    },
    {
      "id": "ba46e809fec8c2bca4729575",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1332.2253317721895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.7516254579054,
        1342.6990380864734
      ],
      "voteCount": 5861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.556475307484572
      }
    },
    {
      "id": "0aa56d276ff86843dd85c29f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-advanced-0514",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1294.3935519041265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.9240337636354,
        1318.8630700446179
      ],
      "voteCount": 898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.86717077436657
      }
    },
    {
      "id": "2223379a3210fe45202cef79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1233.7348392599172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.9656782338484,
        1251.5040002859862
      ],
      "voteCount": 1867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.19353592167741
      }
    },
    {
      "id": "a1c1d5676dd09b9f02332889",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1238.4520578295505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.3895524846266,
        1252.5145631744745
      ],
      "voteCount": 2681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.47889533806848
      }
    },
    {
      "id": "be30eacec1a77c9333e6fc83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1202.084486203118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.151906782822,
        1216.017065623414
      ],
      "voteCount": 3046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.53204482035391
      }
    },
    {
      "id": "73948818fc541f82eea114b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1246.0526636758614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.5433109455194,
        1254.5620164062034
      ],
      "voteCount": 12477,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.849371363635974
      }
    },
    {
      "id": "1ba366aa703caac756578769",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1128.2554940199602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.4328168136312,
        1139.0781712262897
      ],
      "voteCount": 12956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.491109596544824
      }
    },
    {
      "id": "64f87cfb30f69088292a0317",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1173.7202204071345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.0633202114573,
        1197.3771206028118
      ],
      "voteCount": 694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.68656153578337
      }
    },
    {
      "id": "a5b1bf5a7101ed3f1c8cf54b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1248.8794142722554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.3696314388196,
        1281.3891971056912
      ],
      "voteCount": 462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 275.12620314544586
      }
    },
    {
      "id": "8f6a910e6c9eb4bb8cf86e21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1211.7466528617888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.005364964719,
        1241.4879407588583
      ],
      "voteCount": 450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.2625765532869
      }
    },
    {
      "id": "61f5d4b2ffedfbf90b18159a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1235.5480674274638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.7332967658588,
        1248.3628380890689
      ],
      "voteCount": 3298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.74895417982375
      }
    },
    {
      "id": "3845c18b8bd7f89d5e669682",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1230.3871275409056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.9920549017907,
        1241.78220018002
      ],
      "voteCount": 4515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.80165882586178
      }
    },
    {
      "id": "1c0bee496269bb77fac28a0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1228.689352467788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.5141038617805,
        1245.8646010737957
      ],
      "voteCount": 1672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.79092200313139
      }
    },
    {
      "id": "abfb888c7c9c9dbe40cf06d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1186.1757627192076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.004487316492,
        1200.347038121923
      ],
      "voteCount": 2882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.27832860208184
      }
    },
    {
      "id": "491352c0e523085130b4acbf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1267.2169611952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.8165892932916,
        1288.6173330971083
      ],
      "voteCount": 970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.21927031284405
      }
    },
    {
      "id": "2efc68fe23d245a1fd4235c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1254.475432579872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.5673256209643,
        1268.3835395387796
      ],
      "voteCount": 3251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.35468248113638
      }
    },
    {
      "id": "bf5937525516042a224c0f7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1195.312665327831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.3875378602686,
        1210.237792795393
      ],
      "voteCount": 1975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.988238406452226
      }
    },
    {
      "id": "ed55dee85be22727dd8b612c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1260.6528893236668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.7087173141408,
        1281.5970613331929
      ],
      "voteCount": 1076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.190561877571
      }
    },
    {
      "id": "e1e9775e75eee82f4e365488",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1247.0441350014648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.4326866363149,
        1258.6555833666143
      ],
      "voteCount": 4907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.09753440808087
      }
    },
    {
      "id": "b9dd3a885ec9fae2dcdbe1a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1215.1112824551924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.223473444756,
        1226.9990914656282
      ],
      "voteCount": 4634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.78810828514057
      }
    },
    {
      "id": "46b22296de0b0dd491159531",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1206.4847575563995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.9036348537595,
        1217.0658802590397
      ],
      "voteCount": 5876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.145218750020405
      }
    },
    {
      "id": "0d27eba112e303bb0ec321ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1105.609629330247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1060.258520679591,
        1150.9607379809026
      ],
      "voteCount": 173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 535.4015627510902
      }
    },
    {
      "id": "1e5453640b34b838978c030c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1223.2043167257611,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.2943324950506,
        1241.114300956472
      ],
      "voteCount": 1351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.50148995905273
      }
    },
    {
      "id": "7beafd0094053ed1d6014214",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1194.709460967328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.8549707487255,
        1208.5639511859304
      ],
      "voteCount": 2274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.967189074974506
      }
    },
    {
      "id": "904d06daf4f21b0b2754c3ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1186.5890392551776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.958266952643,
        1201.219811557712
      ],
      "voteCount": 2528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.72349155884833
      }
    },
    {
      "id": "a5170d05171579a0d9adea28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1234.9737752870492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.6541842659685,
        1242.2933663081299
      ],
      "voteCount": 18354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.946892369968133
      }
    },
    {
      "id": "158ba39bda1245f9ec3804ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1265.6464234674315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.4548838257783,
        1285.8379631090847
      ],
      "voteCount": 953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.13110594968927
      }
    },
    {
      "id": "4bcc20d331b58b2a091dc6df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro-dev-api",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1224.8097941809933,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.3883791481485,
        1268.2312092138382
      ],
      "voteCount": 213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 490.8081464514802
      }
    },
    {
      "id": "b1e0f54619e9a0d4b80b25e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1216.219902627207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.857649571611,
        1254.5821556828025
      ],
      "voteCount": 236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 383.09989204456684
      }
    },
    {
      "id": "60cbdb16a36962ad4b1cbfb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1247.5269062453265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.7941996045113,
        1271.2596128861414
      ],
      "voteCount": 678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.62173689453093
      }
    },
    {
      "id": "4eecd68348408b75cfbde62d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1183.2891273636756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.0621831273652,
        1204.516071599986
      ],
      "voteCount": 953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.29480456333825
      }
    },
    {
      "id": "f5fd10dab45329b1cb46a7cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1241.0518257888316,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.1618763563451,
        1253.9417752213183
      ],
      "voteCount": 5086,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.2520050656272
      }
    },
    {
      "id": "59153496262933583e37e278",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1103.6914569904575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.928377782741,
        1120.4545361981736
      ],
      "voteCount": 4502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.14950846548295
      }
    },
    {
      "id": "9fe13f4a6dae46d5053ae38a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1240.5195311937432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.0803129525975,
        1259.9587494348891
      ],
      "voteCount": 1189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.36971407612722
      }
    },
    {
      "id": "6d0a33019fb9aeb449814cfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1228.4956447428465,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.378309570879,
        1246.6129799148139
      ],
      "voteCount": 1407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.44614144115614
      }
    },
    {
      "id": "39c5caa2695ddf669798f21c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1178.4749352526615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.513140867853,
        1208.43672963747
      ],
      "voteCount": 431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.68963840547727
      }
    },
    {
      "id": "a83fc453ced78caa0ad83e7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1175.8657400254904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.9468175208392,
        1196.7846625301418
      ],
      "voteCount": 1035,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.9154001594984
      }
    },
    {
      "id": "9ed76be50a3515fa5fef43db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1224.8836911483404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.883450494356,
        1258.8839318023245
      ],
      "voteCount": 309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.9316039784999
      }
    },
    {
      "id": "4cecb3e40c742822b696d85d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1239.4068686277228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.9058614461728,
        1259.9078758092728
      ],
      "voteCount": 1125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.40929346784324
      }
    },
    {
      "id": "1b090999adc214f9f29859ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1212.7365672713436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.0200021889752,
        1233.4531323537117
      ],
      "voteCount": 844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.72215786877796
      }
    },
    {
      "id": "129ce6c12a44174138eaf4ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1238.164911252371,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.0958843536573,
        1277.2339381510844
      ],
      "voteCount": 262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 397.3461474036032
      }
    },
    {
      "id": "53fd21f26667309901839445",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1227.238046565775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.2390673641075,
        1246.2370257674424
      ],
      "voteCount": 1416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.96461801461443
      }
    },
    {
      "id": "2d87079a6c5faaf82ca4b69b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1205.1991333426424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.382132321447,
        1224.0161343638379
      ],
      "voteCount": 1319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.17319355975683
      }
    },
    {
      "id": "bd6271115ebec01d50d68d98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1215.6116637725322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.0002329256067,
        1232.2230946194577
      ],
      "voteCount": 1897,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.83199083006878
      }
    },
    {
      "id": "2279439c0f7091d0ffb52ed1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1198.198835502656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.1506312332217,
        1217.2470397720901
      ],
      "voteCount": 993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.45216070923063
      }
    },
    {
      "id": "d707f5028808ae76a472fe41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1197.0000920934592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.1202049282879,
        1221.8799792586306
      ],
      "voteCount": 641,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.13898762028293
      }
    },
    {
      "id": "877cf07f960c32c52b02c735",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemini-pro",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1221.6508284725678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.9063810471268,
        1233.395275898009
      ],
      "voteCount": 6390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.906162675987694
      }
    },
    {
      "id": "f478d5e88e15ff018140ba8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1137.2116017012372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.150813771289,
        1155.2723896311854
      ],
      "voteCount": 1291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.91359035097686
      }
    },
    {
      "id": "94a682c8d54335cf7eaac974",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1171.3003904911334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.375582324329,
        1185.2251986579377
      ],
      "voteCount": 1963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.475689453639845
      }
    },
    {
      "id": "717e782ecf875f4703a93035",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1091.5591860467239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.572418104272,
        1108.5459539891754
      ],
      "voteCount": 1486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.11476722756213
      }
    },
    {
      "id": "338a22997d7a4a8a4e9ca1c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1138.0857841390698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.3550397511326,
        1147.8165285270068
      ],
      "voteCount": 5934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.6488094140908
      }
    },
    {
      "id": "41c18f76baccf4828a3de7b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 925.1212615301363,
      "unit": "Arena rating",
      "confidenceInterval": [
        911.5070937917493,
        938.7354292685234
      ],
      "voteCount": 7496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.24874399550314
      }
    },
    {
      "id": "868377b36b3f8c9568d81af1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1110.0036017126192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.2557726014802,
        1135.7514308237585
      ],
      "voteCount": 578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.5778499472849
      }
    },
    {
      "id": "e01281d755f446a19b507b72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1047.408820735726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1012.3872558278479,
        1082.4303856436043
      ],
      "voteCount": 365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 319.2823523161197
      }
    },
    {
      "id": "7839b7b9fab7c3d2943b76de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1149.8357379389822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.4640464488634,
        1164.207429429101
      ],
      "voteCount": 1941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.76746853942039
      }
    },
    {
      "id": "6c41509b833e968593240401",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1136.7300629127253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.8871786132124,
        1148.5729472122384
      ],
      "voteCount": 3183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.5105849309372
      }
    },
    {
      "id": "358a70ef5ccc0550fcb486ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1101.462813449335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1082.1429916527154,
        1120.7826352459545
      ],
      "voteCount": 1137,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.165043717868
      }
    },
    {
      "id": "c1c6d63bb7f7b08b9778844f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1085.6820691839707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.871216039585,
        1102.4929223283564
      ],
      "voteCount": 1499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.56704747678032
      }
    },
    {
      "id": "1d466f4b18f74d976e4c752c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1119.9622290605882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.178926285688,
        1147.7455318354885
      ],
      "voteCount": 578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.94238910578653
      }
    },
    {
      "id": "fe38637f5a37836bf2f4429c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1126.5342665075589,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.2536102172694,
        1142.8149227978483
      ],
      "voteCount": 1929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.99976847718729
      }
    },
    {
      "id": "fa5e1a2f5dca1773875bbe9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1113.1575689003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.0671178285672,
        1130.2480199720328
      ],
      "voteCount": 1224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.03453049185991
      }
    },
    {
      "id": "9ba8e979f6d542ad93edcbc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1142.526106066287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.7178682713945,
        1169.3343438611796
      ],
      "voteCount": 628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.08559617922455
      }
    },
    {
      "id": "861a2123559222a59757fef8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1156.3588030481567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.4440914804723,
        1168.2735146158411
      ],
      "voteCount": 3194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.95480242463259
      }
    },
    {
      "id": "53226c1872e1754be57d2ad9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1089.074359673804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1075.8598777619663,
        1102.288841585642
      ],
      "voteCount": 2596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.45734845772439
      }
    },
    {
      "id": "61dcc48ac98022a14485a130",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1097.2833561871769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.3067522221113,
        1108.2599601522425
      ],
      "voteCount": 3877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.36460397722551
      }
    },
    {
      "id": "f4d81109e01e0c93a7b393be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1012.0851766040385,
      "unit": "Arena rating",
      "confidenceInterval": [
        978.5579504514249,
        1045.612402756652
      ],
      "voteCount": 386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.61667141478983
      }
    },
    {
      "id": "a9aae114337503057a0fc54b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1114.7687647932266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.8596552876913,
        1132.677874298762
      ],
      "voteCount": 1179,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.49333371828257
      }
    },
    {
      "id": "0f4125a47b54be46f95bd26d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1106.4670109481215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1090.5438610120693,
        1122.3901608841734
      ],
      "voteCount": 1355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.00271295897484
      }
    },
    {
      "id": "2069043158b38d688aacb279",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1049.9229683658386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1031.961963057134,
        1067.8839736745435
      ],
      "voteCount": 1478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.9779174415378
      }
    },
    {
      "id": "8a3b461dde4a9b7090516053",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1114.5669626658373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1106.8363836890023,
        1122.2975416426723
      ],
      "voteCount": 10854,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.557071963167342
      }
    },
    {
      "id": "3d09cde8dd7cf679fa4b42e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1087.460247114355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.8502455455896,
        1106.0702486831206
      ],
      "voteCount": 1166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.15641571471427
      }
    },
    {
      "id": "6afc30837172632788ffa9ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1174.988107395926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.3195693745145,
        1187.6566454173371
      ],
      "voteCount": 3219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.778882214060495
      }
    },
    {
      "id": "d5f3266e0c10d7f9fa3a27a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1216.443332827759,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.073714006285,
        1226.812951649233
      ],
      "voteCount": 4332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.991708234226895
      }
    },
    {
      "id": "ac1e87d942083edf8a19b58b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1147.4559029888173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.7641866088409,
        1159.147619368794
      ],
      "voteCount": 3409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.584458480570234
      }
    },
    {
      "id": "16da1af3814e5f937822ae02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1207.412137614935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.2524222982977,
        1214.5718529315725
      ],
      "voteCount": 12733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.344285545674488
      }
    },
    {
      "id": "c5558bc9e2c7e2aea37e74b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1039.4903731119557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1030.3204342055942,
        1048.660312018317
      ],
      "voteCount": 15506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.889543392582038
      }
    },
    {
      "id": "e60b49a7cd729cb7e6a6dfab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1167.8944267401994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.1811988309878,
        1185.607654649411
      ],
      "voteCount": 1247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.676898701463
      }
    },
    {
      "id": "4f68fb6e574c7fde2e1745dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1175.77346742272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.9489498801754,
        1208.5979849652645
      ],
      "voteCount": 401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.4791102006728
      }
    },
    {
      "id": "2624399df3c3febba87ffe1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1154.390361189266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.4906133938334,
        1176.2901089846985
      ],
      "voteCount": 827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.84813085068899
      }
    },
    {
      "id": "5475764fc6f6d6cb4c611daa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1207.6360009904927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.2847801076937,
        1217.9872218732917
      ],
      "voteCount": 4180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.892469701167165
      }
    },
    {
      "id": "095c5354caea9391551586ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1192.0567873223583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.4369030047312,
        1200.6766716399852
      ],
      "voteCount": 6987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.342236665144437
      }
    },
    {
      "id": "45eb0099473ae19642bd0860",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1172.553480395135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.562129360902,
        1185.5448314293678
      ],
      "voteCount": 2712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.935184411053115
      }
    },
    {
      "id": "9315e6f25a2234f0c3096ff9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1149.5483642330005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.0408321102304,
        1161.05589635577
      ],
      "voteCount": 3421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.472137210793164
      }
    },
    {
      "id": "87dc6df19ac7ca4862e40cc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1211.4743373756116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.9756967727726,
        1228.9729779784507
      ],
      "voteCount": 1416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.7099324084374
      }
    },
    {
      "id": "5f43b98aa0fdee6f4a464801",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1195.0909158336674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.8650516109801,
        1206.3167800563547
      ],
      "voteCount": 4147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.805252751203945
      }
    },
    {
      "id": "94a3a05c0c05c82edcbdd38d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1159.8560404286654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.88971599763,
        1171.8223648597009
      ],
      "voteCount": 2659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.275661948374314
      }
    },
    {
      "id": "2ca0486fe66ce64559963db3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1212.9777204325328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.2444870797513,
        1231.710953785314
      ],
      "voteCount": 1255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.35436515920944
      }
    },
    {
      "id": "ad452347b9267dfbd95a56f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1213.3642683986611,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.5634051847687,
        1222.1651316125535
      ],
      "voteCount": 7051,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.16296332330539
      }
    },
    {
      "id": "1dae12555635006da999f112",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1151.200394405867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.8774508859299,
        1160.523337925804
      ],
      "voteCount": 6034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.626111571913583
      }
    },
    {
      "id": "86bcee067d6a9bc3b87c07e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1153.1807619013225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.1719583293993,
        1161.1895654732455
      ],
      "voteCount": 8852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.697025179110877
      }
    },
    {
      "id": "bee757bbc9f8e0069682c249",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1051.1825594782144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1021.328881327281,
        1081.0362376291482
      ],
      "voteCount": 449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.00615722817653
      }
    },
    {
      "id": "9412021f2a6d0186f60c3104",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1094.9545098512158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1069.9745461396665,
        1119.934473562765
      ],
      "voteCount": 770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.43792167413355
      }
    },
    {
      "id": "4fb10d8ff6a1d97043719483",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1164.5763736460535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.895520614669,
        1177.2572266774378
      ],
      "voteCount": 2649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.860147696314954
      }
    },
    {
      "id": "b2ab85e7e9dcf2c676f42c04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1158.801021815856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.4296152129107,
        1170.1724284188015
      ],
      "voteCount": 3039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.6614016094399
      }
    },
    {
      "id": "81e08016f622b8f0993b5200",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1123.9577851101237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.1866453518383,
        1135.7289248684092
      ],
      "voteCount": 3635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.06956046558676
      }
    },
    {
      "id": "acc46fea33317a501b6e9d11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1180.6316178109598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.5603195057215,
        1186.7029161161981
      ],
      "voteCount": 23893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.59548568179881
      }
    },
    {
      "id": "2d747079da9296010587b472",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1135.8679423236122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1123.0906348860542,
        1148.6452497611704
      ],
      "voteCount": 2709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.49937145606972
      }
    },
    {
      "id": "9b0746dc9b6beb6b6a4d662e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-1.1-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1152.2706145527286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.5559262354172,
        1184.9853028700397
      ],
      "voteCount": 411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.6053115897864
      }
    },
    {
      "id": "c69766ab3e8da3ef7ac296d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1297.8595384905432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.1719566731822,
        1306.5471203079042
      ],
      "voteCount": 6872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.647243757178003
      }
    },
    {
      "id": "761f049d420ecf5c10ccbae2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1305.0242790685938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.6211112582725,
        1311.427446878915
      ],
      "voteCount": 12088,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.6731738958807
      }
    },
    {
      "id": "77357bb4ecfa1e6de3039b74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1291.8951770034842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.0647147595105,
        1298.7256392474578
      ],
      "voteCount": 11429,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.145181464660041
      }
    },
    {
      "id": "382ec214dbac2b62e5d0979b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1298.3614255383372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.1043388080973,
        1302.618512268577
      ],
      "voteCount": 41283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.717683639131167
      }
    },
    {
      "id": "d040f1ab194b73772607f008",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1210.3441896202535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.1149784131203,
        1215.5734008273866
      ],
      "voteCount": 47955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.118298314562088
      }
    },
    {
      "id": "35b96b41b4c9b4f7468bdf75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1255.1716804297862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.6590663722786,
        1265.6842944872935
      ],
      "voteCount": 4025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.769032672367263
      }
    },
    {
      "id": "28a6f0fb03e3fd6379f32824",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1313.4926093947613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.6023902029901,
        1336.3828285865327
      ],
      "voteCount": 793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.39665530832374
      }
    },
    {
      "id": "506b0bf678596303620438eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1268.4508310238962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.2719269468028,
        1282.6297351009894
      ],
      "voteCount": 2037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.33462864274281
      }
    },
    {
      "id": "e8a6b2d9e1b781135bb5c9d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1288.7045586119561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.4154262862914,
        1294.9936909376206
      ],
      "voteCount": 12606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.296397086608074
      }
    },
    {
      "id": "08b59f023ca8ac586050c47b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1281.4771175678939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.256389940374,
        1286.697845195414
      ],
      "voteCount": 20494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.095220392294888
      }
    },
    {
      "id": "d9f90fc5a4c3d8de0df5b8b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1279.321367920204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.726808209538,
        1286.91592763087
      ],
      "voteCount": 8733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.014435892989592
      }
    },
    {
      "id": "e1918a9a201764b787c783d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1272.2827963094776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.8591810441008,
        1278.7064115748544
      ],
      "voteCount": 12280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.741448757772885
      }
    },
    {
      "id": "b3868526b1963a9f26ea1dfd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1311.982433145678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.6388396139491,
        1322.3260266774068
      ],
      "voteCount": 4458,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.851379422125483
      }
    },
    {
      "id": "6162048a0eceaf63f36205dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1303.5370441206585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.9878510175295,
        1310.0862372237875
      ],
      "voteCount": 12863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.165531717016323
      }
    },
    {
      "id": "aa19ca04e3d0a0d38b2ee062",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1262.0026031109483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.9736140750904,
        1269.0315921468061
      ],
      "voteCount": 8869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.861438628485132
      }
    },
    {
      "id": "e3c95a9acd307e9b1d0d040f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1290.7167503394671,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.508288675393,
        1301.9252120035412
      ],
      "voteCount": 3862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.703620873988456
      }
    },
    {
      "id": "0aa85b7245bdd6063cae7c4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1310.332980325867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.8753696378435,
        1315.7905910138911
      ],
      "voteCount": 19950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.753698741107108
      }
    },
    {
      "id": "5a607c8c369c2111f6e267d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1296.2684057068764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.7894737841261,
        1301.7473376296264
      ],
      "voteCount": 20390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.81439979322894
      }
    },
    {
      "id": "856b0f196c6f9e1626549e95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1269.3040080715116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.5692904002601,
        1274.0387257427628
      ],
      "voteCount": 29545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.835687032670024
      }
    },
    {
      "id": "e2256e51d2ebc8690ebfd7bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1227.9050305822998,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.8256326457436,
        1242.984428518856
      ],
      "voteCount": 1808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.19320048520649
      }
    },
    {
      "id": "c5012e787492092c954f66bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1235.8226260791548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.1475090425083,
        1254.4977431158013
      ],
      "voteCount": 1440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.78842507790364
      }
    },
    {
      "id": "00a765705d8effaef5aee437",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1298.7802185664689,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.843317974493,
        1305.7171191584448
      ],
      "voteCount": 9918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.52664471208927
      }
    },
    {
      "id": "429854da1f2bc96c56854f58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1244.8103542870485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.9971455248954,
        1251.623563049202
      ],
      "voteCount": 10170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.083902445241911
      }
    },
    {
      "id": "62e8fd3c17a84ff351c4f31b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1279.6067566290526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.10337431677,
        1286.1101389413357
      ],
      "voteCount": 13588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.009875017239166
      }
    },
    {
      "id": "ab2a5f5fe84dc51a18858627",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1288.3437579598276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.975290306641,
        1291.7122256130142
      ],
      "voteCount": 75754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.953714945332801
      }
    },
    {
      "id": "dc35ca1a79dbd96d24e316c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1289.0649358066566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.8218839141668,
        1296.3079876991467
      ],
      "voteCount": 9678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.656739058267895
      }
    },
    {
      "id": "0466fdd4c3dab5d76c2db74f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-27b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1290.3787129227362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.9496241731763,
        1312.8078016722961
      ],
      "voteCount": 845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.95650522806727
      }
    },
    {
      "id": "4c50b4b058273a2ddd87df6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1197.4382411792183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.4570610160927,
        1208.4194213423439
      ],
      "voteCount": 3790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.390761531900864
      }
    },
    {
      "id": "378158d886bc35e8aac237b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1193.1003933424295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.0494710623627,
        1201.151315622496
      ],
      "voteCount": 7298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.87310800014271
      }
    },
    {
      "id": "2e32f49fe8ecbc1f9c7d059b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1182.9450952084103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.648915253047,
        1191.2412751637737
      ],
      "voteCount": 7094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.916787622712626
      }
    },
    {
      "id": "0554d2c7d084ea1c81a1ae41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1221.6323448705405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.609497157502,
        1226.6551925835788
      ],
      "voteCount": 25669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.56755683868484
      }
    },
    {
      "id": "9c24b93d6d1b3ee214d7a3df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1063.7093052801192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1056.9219824597758,
        1070.4966281004627
      ],
      "voteCount": 30730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.992254301773464
      }
    },
    {
      "id": "eacd9a205391933d42f5a190",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1167.5688530533357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.7892467941958,
        1180.3484593124756
      ],
      "voteCount": 2525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.51466532944269
      }
    },
    {
      "id": "e75efe3370feac2caf1aa43b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1209.6042595300494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.6364027027594,
        1239.5721163573394
      ],
      "voteCount": 469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.7842170747708
      }
    },
    {
      "id": "333678e3a4562f92127f7253",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1155.0492822292222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.2183973958895,
        1173.8801670625544
      ],
      "voteCount": 1158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.30926066315466
      }
    },
    {
      "id": "78b1ebd940d9d30b640d4d9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1195.3295665175676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.5133617561391,
        1203.1457712789963
      ],
      "voteCount": 7586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.903608426951916
      }
    },
    {
      "id": "87bd00671182bf68c8e893d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1184.4278857884165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.9864839239794,
        1190.869287652854
      ],
      "voteCount": 12322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.801015946248807
      }
    },
    {
      "id": "20d1c4f1cf5063f50f815441",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1181.4626843765834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.0759443858828,
        1190.849424367284
      ],
      "voteCount": 5197,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.936829929911287
      }
    },
    {
      "id": "5274d5ffc08e17eb257f8d00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1171.9022818567623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.0724907571264,
        1179.732072956398
      ],
      "voteCount": 7532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.958944641988404
      }
    },
    {
      "id": "97547b26b955c43ca70edbd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1221.4187638872725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.580489958384,
        1234.2570378161608
      ],
      "voteCount": 2655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.905907668533274
      }
    },
    {
      "id": "ea2fc1e2f96762a1d17c09a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1213.9473123113844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.9500520599506,
        1221.9445725628184
      ],
      "voteCount": 7909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.648928054266452
      }
    },
    {
      "id": "6a8e37050ce79158efad8fff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1180.4348506531455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.9803139898188,
        1188.8893873164725
      ],
      "voteCount": 5632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.607303508364094
      }
    },
    {
      "id": "04e6679469ade4e51cc1b5f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1212.5397232905648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.6254410147294,
        1226.4540055664002
      ],
      "voteCount": 2336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.399408216653434
      }
    },
    {
      "id": "51dbd46539241db760dde714",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1199.856188459897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.127274136616,
        1206.5851027831782
      ],
      "voteCount": 11839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.786743027451157
      }
    },
    {
      "id": "524064fbcf5ba85b030eb8f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1192.5216945945926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.9888758786499,
        1199.0545133105354
      ],
      "voteCount": 12543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.109769066237437
      }
    },
    {
      "id": "3369e307326138b1f24ddc9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1169.7698052338767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.1371933106261,
        1175.4024171571273
      ],
      "voteCount": 18240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.258924163662456
      }
    },
    {
      "id": "ed88af6751e431c71fbd371b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1119.4287230208338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.2440216590155,
        1137.613424382652
      ],
      "voteCount": 1228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.08275633129445
      }
    },
    {
      "id": "ec53578b164da089b57e203a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1091.069011388428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.446531006345,
        1116.691491770511
      ],
      "voteCount": 717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.90161096965932
      }
    },
    {
      "id": "d4762e89b79b3c2b0091fd5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1185.4022715651072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.668610868952,
        1194.1359322612625
      ],
      "voteCount": 5866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.856214192550464
      }
    },
    {
      "id": "9ec0ab8935f6a140433d9710",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1161.8678002940978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.8223800290411,
        1169.9132205591545
      ],
      "voteCount": 6599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.850053654795513
      }
    },
    {
      "id": "91bb57820fb425a6396f807a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1164.0397869296908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.893693564346,
        1172.1858802950355
      ],
      "voteCount": 7933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.274384606034648
      }
    },
    {
      "id": "240a97f83acee1b2bb2c1616",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1199.321304256147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.2395502885904,
        1203.4030582237033
      ],
      "voteCount": 46616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.337080320088283
      }
    },
    {
      "id": "4a402eda5e85c25190856f67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1169.7129514526907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.8374667827825,
        1178.588436122599
      ],
      "voteCount": 5974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.506331527339032
      }
    },
    {
      "id": "ff5215d599739f9ef4e2b12d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1188.2761103983532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.6548031260522,
        1215.8974176706542
      ],
      "voteCount": 544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.60595962161304
      }
    },
    {
      "id": "d7f2b8c99600c0ed3ca546db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1288.2554849309063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.2799362891922,
        1309.2310335726206
      ],
      "voteCount": 753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.53295775312321
      }
    },
    {
      "id": "efd43bc06c65aa1024feaf7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1271.9439198115988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.9973420779565,
        1286.890497545241
      ],
      "voteCount": 1471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.1550385869933
      }
    },
    {
      "id": "66cf8cf2e5a10ec44233b383",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1283.2264356875698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.620787829793,
        1297.832083545347
      ],
      "voteCount": 1671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.53227544603413
      }
    },
    {
      "id": "c435d5484b704caceee75c63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1296.221147006247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.523662925371,
        1304.9186310871232
      ],
      "voteCount": 5834,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.69205785301747
      }
    },
    {
      "id": "fcd2b0875b3718a327a09f32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1195.727211148796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.9454113837928,
        1206.5090109137989
      ],
      "voteCount": 6321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.261213668721
      }
    },
    {
      "id": "40a3962075d8e29a9bd46e3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1230.374611485693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.858145430522,
        1259.8910775408644
      ],
      "voteCount": 369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.79450933920268
      }
    },
    {
      "id": "24d2e8b0b407b64f7f77bf08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1268.7979739339728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.4372301751628,
        1300.1587176927828
      ],
      "voteCount": 318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.0215519707269
      }
    },
    {
      "id": "6b26fda31bc2b8d815905cec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1279.2144227041372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.331223151019,
        1293.0976222572551
      ],
      "voteCount": 1661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.17448808597911
      }
    },
    {
      "id": "afdf74bf2f64a42162f627e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1271.8421656070825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.418164224459,
        1283.2661669897059
      ],
      "voteCount": 2554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.973501651802096
      }
    },
    {
      "id": "d4660c46001a1837691bbcfd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1285.3589857492495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.047802302217,
        1302.6701691962821
      ],
      "voteCount": 1121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.01126767842476
      }
    },
    {
      "id": "e01b8a9d4ea7c9ef5216eaa0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1267.9978581915886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.843031340169,
        1282.152685043008
      ],
      "voteCount": 1692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.15704047491507
      }
    },
    {
      "id": "43acc1f15a7618f9426b4239",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1327.3647280103528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.7038416411006,
        1352.0256143796048
      ],
      "voteCount": 543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.31467806995067
      }
    },
    {
      "id": "322366adad59bd1d014b5e8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1295.0474160552353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.112583829707,
        1309.9822482807638
      ],
      "voteCount": 1596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.06367424872636
      }
    },
    {
      "id": "b6a88f3d837ea68b2a3c5d5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1235.4886773757942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.709539696732,
        1251.2678150548563
      ],
      "voteCount": 1139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.81422748918365
      }
    },
    {
      "id": "6c2565480bcbd94e899ab764",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1299.8146052931406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.5221006398692,
        1326.107109946412
      ],
      "voteCount": 516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.95658243640491
      }
    },
    {
      "id": "bcbccd5ef37dd0fa11d5c091",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1282.6340688300988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.6390042938651,
        1294.6291333663323
      ],
      "voteCount": 2537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.454930521007185
      }
    },
    {
      "id": "0e5b17e61880260bb995778c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1273.2489446502555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.5440684113814,
        1284.953820889129
      ],
      "voteCount": 2801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.66460924409871
      }
    },
    {
      "id": "f3f27b240f27497c508b81d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1250.2764214585632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.2626175401188,
        1260.2902253770073
      ],
      "voteCount": 3741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.103694871556684
      }
    },
    {
      "id": "a66fd44f51ccacd365d9f109",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1188.5515551131089,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.9143673559015,
        1221.1887428703162
      ],
      "voteCount": 291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.28685231792724
      }
    },
    {
      "id": "61744fbc1e395b7958ff524a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1287.6877742996517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.5488068821644,
        1306.8267417171392
      ],
      "voteCount": 841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.35441896041391
      }
    },
    {
      "id": "62ce5f765b51169d90fb72d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1204.7002966890304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.5250968393693,
        1219.8754965386913
      ],
      "voteCount": 1285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.94771810036978
      }
    },
    {
      "id": "0d832b4da1fb018e41c1b74e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1271.7267698627184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.183370099767,
        1286.27016962567
      ],
      "voteCount": 1660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.05993596120306
      }
    },
    {
      "id": "7c7a30b696942117ee025b8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1279.4287758070382,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.5703338918795,
        1286.2872177221966
      ],
      "voteCount": 10072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.244886044386833
      }
    },
    {
      "id": "75a5b9715f6cd886d756d456",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it-simpo",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1270.3291713377084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.3796984695714,
        1287.2786442058452
      ],
      "voteCount": 1119,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.78529483645492
      }
    },
    {
      "id": "54ae634577291d337f0408d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1262.9440010448723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.3450767527368,
        1272.5429253370075
      ],
      "voteCount": 4980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.98550963758593
      }
    },
    {
      "id": "165b90ebbad1273d98c1bd2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1270.8188005787601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.5506851662094,
        1278.0869159913107
      ],
      "voteCount": 8921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.751416874647095
      }
    },
    {
      "id": "15d6aad1dce4f7584b715e70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1257.8321405128027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.3610029273923,
        1265.3032780982128
      ],
      "voteCount": 8340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.530390517122136
      }
    },
    {
      "id": "58e16a388c390ea615596e72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1277.4028934219991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.6604457040921,
        1282.1453411399061
      ],
      "voteCount": 29787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.854757634240803
      }
    },
    {
      "id": "fbc1cf418a2820d446b47396",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1172.7030660148785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.7663099550382,
        1178.6398220747187
      ],
      "voteCount": 34710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.174918737689584
      }
    },
    {
      "id": "dd83519bd8147cf6cf5de481",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1232.5510951560245,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.6580957507767,
        1244.4440945612725
      ],
      "voteCount": 2847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.82023977226126
      }
    },
    {
      "id": "ad0fd9059da04d24ff5100db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1260.6330658171091,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.4129043293615,
        1286.853227304857
      ],
      "voteCount": 591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.96765279377547
      }
    },
    {
      "id": "1e043ae045f543f93d39d75e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1244.5022700081765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.6272438051592,
        1260.377296211194
      ],
      "voteCount": 1580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.60436248564409
      }
    },
    {
      "id": "fd8af6570cc760744a784f39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1262.0147215344898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.8551953634355,
        1269.1742477055438
      ],
      "voteCount": 9094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.343580495481332
      }
    },
    {
      "id": "ad6e49359b99f59a635bfe43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1256.5854924839364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.658338293707,
        1262.512646674166
      ],
      "voteCount": 14756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.145264451489737
      }
    },
    {
      "id": "70a9a7d9410fe65dd10b2a0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1261.8677507176626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.3116916080085,
        1270.4238098273167
      ],
      "voteCount": 6175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.056861183447147
      }
    },
    {
      "id": "931abdb0ee7e4d3ca615e4f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1247.4331652164733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.398711310016,
        1254.4676191229305
      ],
      "voteCount": 9128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.881445323714486
      }
    },
    {
      "id": "873ab2cf09a3d530b7e0480b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1285.3217215378431,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.7705782694554,
        1296.872864806231
      ],
      "voteCount": 3243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.733916731850044
      }
    },
    {
      "id": "8f7c89b7365763036fa2d710",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1279.2790494704038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.9323975880682,
        1286.6257013527395
      ],
      "voteCount": 9169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.05020759027
      }
    },
    {
      "id": "d15213a124eca076c0833f8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1235.3022606304226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.332622310327,
        1243.2718989505183
      ],
      "voteCount": 6297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.53411839558937
      }
    },
    {
      "id": "559bc4733f36ed2a7e0b6006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1259.0623837222702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.4595010119065,
        1271.6652664326339
      ],
      "voteCount": 2812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.34696218934943
      }
    },
    {
      "id": "3391f9321adcfe86487d7831",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1281.0435746154876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.9355035690614,
        1287.151645661914
      ],
      "voteCount": 14591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.7120738890156
      }
    },
    {
      "id": "a7314644c875b837c1fe22ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1267.1936144140402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.1935001315228,
        1273.1937286965576
      ],
      "voteCount": 14640,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.371796779215401
      }
    },
    {
      "id": "5e1ed242fb2d47df065c6e11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1243.1301294584164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.8805272854797,
        1248.379731631353
      ],
      "voteCount": 21359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.173921226395211
      }
    },
    {
      "id": "9aaf7b1f963de94ac29b1308",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1194.2093398792485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.2319783298108,
        1211.1867014286863
      ],
      "voteCount": 1301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.03160091880146
      }
    },
    {
      "id": "06a20afb8b509f9d2b0d33c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1200.5656713962253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.9227989896046,
        1221.208543802846
      ],
      "voteCount": 1087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.92873855641697
      }
    },
    {
      "id": "d4d8081b0e44a3c73ca78fab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1264.043069146874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.1366843586052,
        1271.9494539351426
      ],
      "voteCount": 6877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.272703506130995
      }
    },
    {
      "id": "8783f75c6d402e53b71633aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1217.3371512207736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.7154386110367,
        1224.9588638305108
      ],
      "voteCount": 7110,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.1219903210958
      }
    },
    {
      "id": "4a9f2fda28cec1f212d7de83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1251.064523849915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.788833245762,
        1258.3402144540687
      ],
      "voteCount": 9730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.780096634695019
      }
    },
    {
      "id": "dc239bddfdaf39370eec69c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1265.8354584142617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.0285312378137,
        1269.6423855907096
      ],
      "voteCount": 54611,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.772705944081764
      }
    },
    {
      "id": "bb00810a9bd4dbf7f7fac440",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1257.596937934251,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.4600981942376,
        1265.7337776742645
      ],
      "voteCount": 6684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.235160923239505
      }
    },
    {
      "id": "9bd05d3930d55d451821c232",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2-9b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1263.8247171929454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.1054723780371,
        1289.5439620078537
      ],
      "voteCount": 614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.19488343484562
      }
    },
    {
      "id": "0b6ceaf962049ad963224c54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1100.6111637415572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1075.1515320324947,
        1126.0707954506197
      ],
      "voteCount": 598,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.73611745341427
      }
    },
    {
      "id": "27c5844690ac3c034f1952a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1136.131226807923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.1454912768652,
        1158.1169623389806
      ],
      "voteCount": 742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.83046946583495
      }
    },
    {
      "id": "b7dd029ea68f9572f66e996c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1076.731189973139,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.4135196170225,
        1100.0488603292554
      ],
      "voteCount": 696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.5383520207219
      }
    },
    {
      "id": "9d8f3afa947f95337b87b25f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1118.1311039138616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.8300094327064,
        1131.4321983950167
      ],
      "voteCount": 3028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.05518961795037
      }
    },
    {
      "id": "ebc2bbac3e3b4b864932b23d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 903.2485004873886,
      "unit": "Arena rating",
      "confidenceInterval": [
        885.1575416481878,
        921.3394593265892
      ],
      "voteCount": 3331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.19752703284624
      }
    },
    {
      "id": "7880c1349afa3543ee4dd651",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1114.0228989078194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1093.7632312129858,
        1134.2825666026527
      ],
      "voteCount": 832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.84850580564311
      }
    },
    {
      "id": "498e474f33ed98df410a16bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1110.5574898521143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.9779995514787,
        1128.1369801527499
      ],
      "voteCount": 1191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.44820826018965
      }
    },
    {
      "id": "048c987896d2b770654c510b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1103.136386626335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.9474960168718,
        1131.3252772357982
      ],
      "voteCount": 447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.85202962782313
      }
    },
    {
      "id": "f11c70e35d7fc54dbcfef6c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1067.1024631194973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1044.0323839449034,
        1090.1725422940915
      ],
      "voteCount": 677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.54855094499467
      }
    },
    {
      "id": "bd0b85a1a326a24760bd2f41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1140.4722402274037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.3288960094605,
        1178.615584445347
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 378.74015472736704
      }
    },
    {
      "id": "b9ab14f8894d12782d622569",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1075.6409294889709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1052.6656542968399,
        1098.6162046811019
      ],
      "voteCount": 879,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.41219021027263
      }
    },
    {
      "id": "01d0797109fb790b82583155",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1073.6889271781745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1049.1979607680303,
        1098.1798935883185
      ],
      "voteCount": 525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.14053506746404
      }
    },
    {
      "id": "147df4cff4eee7af71998689",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1091.133192577356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1052.5971461956672,
        1129.669238959045
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 386.5788857950968
      }
    },
    {
      "id": "e83cd4504138554151a2246b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1130.1137961238937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.3409509182757,
        1147.886641329512
      ],
      "voteCount": 1285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.2276227461395
      }
    },
    {
      "id": "a436777f2c6933a26a49207f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1055.565643675676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1036.8073347576735,
        1074.3239525936785
      ],
      "voteCount": 1152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.59909552268255
      }
    },
    {
      "id": "ca8ca9432bc4f7db5033f4c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1067.0607468894011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.9332068470821,
        1083.1882869317203
      ],
      "voteCount": 1522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.70801405326704
      }
    },
    {
      "id": "9a7e62e57ed02845bbe894ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1082.3653622579702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1051.18941957847,
        1113.5413049374704
      ],
      "voteCount": 377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 253.01309927353537
      }
    },
    {
      "id": "7bacf5eeaa363cd05279e35a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1069.3007879568881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1047.3326047331755,
        1091.268971180601
      ],
      "voteCount": 597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.62963620768764
      }
    },
    {
      "id": "df6fb971b4c96280b51acda5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1034.4502078598184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1011.1148163645855,
        1057.7855993550515
      ],
      "voteCount": 768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.75356854076452
      }
    },
    {
      "id": "72a2bd98c2124dd4dba16863",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1091.7495140286123,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.2557547862486,
        1103.2432732709763
      ],
      "voteCount": 4780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.389670093496285
      }
    },
    {
      "id": "39643f7a61fdb75deeacaee6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-2b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1028.0449979843918,
      "unit": "Arena rating",
      "confidenceInterval": [
        991.5376418081769,
        1064.5523541606067
      ],
      "voteCount": 300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 346.94815620493813
      }
    },
    {
      "id": "95e6ec41322d1e24233407dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1316.957527425016,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.5659643315153,
        1340.3490905185165
      ],
      "voteCount": 543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.43683181233502
      }
    },
    {
      "id": "9d34d96f8f87fe3be8c55f10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1333.823336766635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.5241730774312,
        1357.122500455839
      ],
      "voteCount": 600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.31377009482708
      }
    },
    {
      "id": "24263f13ba81e1f2f99738d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1348.6010044344634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.7022818548255,
        1360.4997270141012
      ],
      "voteCount": 2330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.85568572660172
      }
    },
    {
      "id": "1772de3aaef78d60e698eeeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1295.8669609146577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.4302101262572,
        1310.3037117030585
      ],
      "voteCount": 2526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.25537095533138
      }
    },
    {
      "id": "4404fbbf439c9cfdc6f74abb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1271.316542555329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.8286805746268,
        1312.8044045360314
      ],
      "voteCount": 186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 448.07006194037155
      }
    },
    {
      "id": "102c8705a0d155ac9d8ed239",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1370.5703519977906,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.6347123362611,
        1413.50599165932
      ],
      "voteCount": 166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 479.88778200974843
      }
    },
    {
      "id": "e040e68ed808d0183470ebe2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1337.4359347968455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.574409792873,
        1358.297459800818
      ],
      "voteCount": 700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.29113386479794
      }
    },
    {
      "id": "438e20e2ba6169f5bdabd03b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1331.8433909644873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.9703560367395,
        1349.716425892235
      ],
      "voteCount": 977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.15730883476421
      }
    },
    {
      "id": "c3738906b7d9fb91350b2fb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1385.383608630758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.1244185699943,
        1415.6427986915223
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.35178922157374
      }
    },
    {
      "id": "be21a2dc193806585a77055d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1306.4488317140504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.133902009159,
        1327.7637614189416
      ],
      "voteCount": 697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.26919134912443
      }
    },
    {
      "id": "907ef551210e2a7fe76cedca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1380.703931834857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.9231226949105,
        1419.4847409748031
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 391.50521396899575
      }
    },
    {
      "id": "1b08a28aab74f1b6322d7ca4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1366.8744345373589,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.111750615315,
        1387.6371184594027
      ],
      "voteCount": 760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.22013921492433
      }
    },
    {
      "id": "4e896f8f128a6ea14bdbcd68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1349.614510964656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.3253838657906,
        1379.9036380635214
      ],
      "voteCount": 333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.82365091849547
      }
    },
    {
      "id": "e13784d3ac7d014765f6dc18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1320.6040012787175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.0926651298585,
        1367.1153374275768
      ],
      "voteCount": 155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 563.1465782473963
      }
    },
    {
      "id": "3be948f7d333a707ecc69745",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1335.0266111536348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.95432291738,
        1354.098899389889
      ],
      "voteCount": 867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.69115654897072
      }
    },
    {
      "id": "a15f0196fa5f7cafe2863db9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1313.6520409370346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.8686469210952,
        1331.4354349529742
      ],
      "voteCount": 1010,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.32526170071162
      }
    },
    {
      "id": "4d419bb8bcf12bda599d5288",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1321.1879901299096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.8801412215885,
        1337.4958390382308
      ],
      "voteCount": 1145,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.23045343710773
      }
    },
    {
      "id": "e313244a49e328c0a2525a9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1345.5600112923923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.0284222558953,
        1374.0916003288894
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.91209145916645
      }
    },
    {
      "id": "be06c807b2dd44755fda5267",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1317.4453339617812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.2403352820106,
        1344.6503326415518
      ],
      "voteCount": 389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.664294402769
      }
    },
    {
      "id": "2048b70c9d0e53913ab84d25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1344.363934936435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.585978981519,
        1370.1418908913508
      ],
      "voteCount": 471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.98194363919052
      }
    },
    {
      "id": "2b619cfc1de9ccd63d8950f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1341.8839374734498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.3766271616562,
        1351.3912477852432
      ],
      "voteCount": 3829,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.529849878334044
      }
    },
    {
      "id": "f6a2fa3695e1fd37fdc80465",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-12b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1357.8022023385656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.119668632738,
        1389.4847360443932
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 261.30253866408003
      }
    },
    {
      "id": "4088f0230803fa221e86cdca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1373.4301927854742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.7758899016303,
        1386.084495669318
      ],
      "voteCount": 2290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.685044393401064
      }
    },
    {
      "id": "d34f7379d4f0c775e8ffa2bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1358.3581350945046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.4240733399517,
        1365.2921968490577
      ],
      "voteCount": 8077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.516394073245742
      }
    },
    {
      "id": "1bf623889f81a194d79e80cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1348.2006514918007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.5597444102682,
        1355.8415585733333
      ],
      "voteCount": 6398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.198252474840762
      }
    },
    {
      "id": "78406dfd22cd1f5ee4119aad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1373.8081738051915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.2322045507517,
        1378.3841430596312
      ],
      "voteCount": 24837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.450922577843244
      }
    },
    {
      "id": "c0e4c3bdb933856d22223683",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1331.6564786031731,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.4926740592055,
        1336.8202831471408
      ],
      "voteCount": 33361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.941341457223554
      }
    },
    {
      "id": "44bd7bc6169750335e0bcb9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1334.8056468131235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.933506205798,
        1347.677787420449
      ],
      "voteCount": 2226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.132573209470515
      }
    },
    {
      "id": "12a82b0c05dc221f30444b51",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1388.8318679944523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.5552433077696,
        1414.1084926811347
      ],
      "voteCount": 600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.31904320035588
      }
    },
    {
      "id": "0dd78f2f9c72e24e155479c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1370.5997412583024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.8578172068112,
        1388.3416653097936
      ],
      "voteCount": 1164,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.94175279275944
      }
    },
    {
      "id": "cc7a7a3f09f41ace26d98c35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1369.9839682414326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.5893506747784,
        1376.378585808087
      ],
      "voteCount": 9914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.644688836304159
      }
    },
    {
      "id": "55451fa7a13c4d3695217db6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1365.3546619320948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.1693536528037,
        1370.539970211386
      ],
      "voteCount": 17867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.999273767153854
      }
    },
    {
      "id": "595a218aa04a1522abc5d2d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1376.6576203256964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.0230504571732,
        1384.2921901942193
      ],
      "voteCount": 6583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.173052685966063
      }
    },
    {
      "id": "0753613b10b6179864a48c31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1327.9672659474697,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.1015153586036,
        1334.833016536336
      ],
      "voteCount": 8097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.27099738635139
      }
    },
    {
      "id": "edc742a93d5accb06ca2fc74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1381.544101756202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.0404538945986,
        1393.0477496178055
      ],
      "voteCount": 2717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.448869635380326
      }
    },
    {
      "id": "8298116e1a0746a5b51ef83b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1389.9621302770774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.851926385295,
        1397.0723341688597
      ],
      "voteCount": 7943,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.160364783913565
      }
    },
    {
      "id": "5f9642579db27d13f64515bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1340.4698484962291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.4206979726362,
        1350.5189990198223
      ],
      "voteCount": 3196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.288301127118263
      }
    },
    {
      "id": "7fd5af90e362be065943b2a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1401.5100945312693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.8852588446289,
        1414.13493021791
      ],
      "voteCount": 2363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.4911322896531
      }
    },
    {
      "id": "965309712c44c3a6956e4c4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1378.158143552467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.5988595408917,
        1383.7174275640423
      ],
      "voteCount": 14438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.045287002652849
      }
    },
    {
      "id": "5a6cf1e11ab315e1f34e1d06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1354.6851970134871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.5547447302333,
        1360.8156492967412
      ],
      "voteCount": 10690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.7833783860429
      }
    },
    {
      "id": "9aede0fc3286b50a1bd49234",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1343.6254114754402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.9494879725644,
        1349.301334978316
      ],
      "voteCount": 12523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.386425343660536
      }
    },
    {
      "id": "578601c6081676afb69ecaf1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1308.397931356733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.636734569171,
        1328.1591281442943
      ],
      "voteCount": 951,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.65536498089384
      }
    },
    {
      "id": "377cd056cdb1f5d528ea2a2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1326.034958308163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.001047789624,
        1347.068868826702
      ],
      "voteCount": 866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.17119207904621
      }
    },
    {
      "id": "97d6003ccae52e1b23bc079d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1363.9165631978904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.4462084131483,
        1371.3869179826324
      ],
      "voteCount": 6645,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.527345785743883
      }
    },
    {
      "id": "02857dae67209f07357a5d23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1322.1182882354542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.64530087485,
        1331.5912755960585
      ],
      "voteCount": 3579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.360263306936858
      }
    },
    {
      "id": "6333d3268ca9072cc6b86c08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1358.5112537769069,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.0887104495418,
        1365.933797104272
      ],
      "voteCount": 7027,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.341986213626976
      }
    },
    {
      "id": "c3096274da95603c608fce3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1365.7737876963345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.1059047768667,
        1369.4416706158022
      ],
      "voteCount": 47545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.502150026559885
      }
    },
    {
      "id": "8c7df54f9369a1a4161f8987",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1367.7726651242747,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.3762171970188,
        1378.1691130515305
      ],
      "voteCount": 2987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.13674037630626
      }
    },
    {
      "id": "08a1f5c6f0e169d16839f961",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-27b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1350.3202469623839,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.6613652271562,
        1371.9791286976113
      ],
      "voteCount": 775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.11693003019366
      }
    },
    {
      "id": "0fabe81f2a3f8c1a95912e2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1274.5536945131394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.8510773906853,
        1298.2563116355934
      ],
      "voteCount": 605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.25018376537923
      }
    },
    {
      "id": "f89b2cfbf6c3e79c7bbd594b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1275.761098847595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.4609822138987,
        1298.0612154812916
      ],
      "voteCount": 666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.4547787932832
      }
    },
    {
      "id": "8d5772b833a4d662976f1331",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1308.302543331899,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.6719934100033,
        1319.9330932537946
      ],
      "voteCount": 2572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.21310465623237
      }
    },
    {
      "id": "0bbc4a7f9d80b8cfebdda68e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1234.673699915749,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.6522067505043,
        1248.6951930809937
      ],
      "voteCount": 2830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.17906497497714
      }
    },
    {
      "id": "30d14e96b1e47ec552b55e57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1257.105491448338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.0865832801387,
        1298.1243996165372
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 437.9978820148179
      }
    },
    {
      "id": "d4ace7cfacc57f05a4f683a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1288.9332725619347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.9947220453842,
        1330.8718230784852
      ],
      "voteCount": 162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 457.8578351417683
      }
    },
    {
      "id": "965a04aaaa0e5c88071f5fd3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1283.4377698352944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.9678583393647,
        1303.9076813312242
      ],
      "voteCount": 764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.0776437310564
      }
    },
    {
      "id": "125aea452db3521fc6be5e54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1283.821029021125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.5238566471862,
        1301.1182013950638
      ],
      "voteCount": 1092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.88503953810252
      }
    },
    {
      "id": "f20d190f752af431f6a6ed84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1329.0517488878486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.8598043427992,
        1359.2436934328978
      ],
      "voteCount": 390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.29357985064053
      }
    },
    {
      "id": "41e9f6bb92b8614fa65081d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1248.7002866976627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.0237380458373,
        1269.376835349488
      ],
      "voteCount": 761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.29096629859279
      }
    },
    {
      "id": "8e4cd76242818ff4c265a76d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1338.313331182318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.1756753045881,
        1374.4509870600482
      ],
      "voteCount": 245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 339.95683236329995
      }
    },
    {
      "id": "cb730ea1c40de1ce188b66e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1314.0245157849386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.2050346409426,
        1334.8439969289348
      ],
      "voteCount": 780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.83494509174125
      }
    },
    {
      "id": "40e45911033defc2e9c1af84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1274.399255774158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.234823599393,
        1304.563687948923
      ],
      "voteCount": 365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.8613099597384
      }
    },
    {
      "id": "ee1ee6a9bc183fe01eff0c3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1349.3347960104106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.827502411044,
        1387.842089609777
      ],
      "voteCount": 197,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 386.0022271642832
      }
    },
    {
      "id": "9eaa02f98d4e746ae5014092",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1301.1829458158484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.5547046570082,
        1319.8111869746886
      ],
      "voteCount": 986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.3332262219077
      }
    },
    {
      "id": "c12952a72b4542e10ed279ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1297.9600527802604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.8007889905766,
        1315.1193165699444
      ],
      "voteCount": 1080,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.64805157295767
      }
    },
    {
      "id": "606b83190c3bb9e838dafa3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1267.21458253174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.8763869154247,
        1283.552778148055
      ],
      "voteCount": 1233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.48835024834334
      }
    },
    {
      "id": "92807e7536ae6ce308dcfd6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1310.6225574694186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.1740369671998,
        1338.0710779716374
      ],
      "voteCount": 444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.1289481230444
      }
    },
    {
      "id": "6d0c33ecbc07c2aaf832327b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1253.5065143926308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.3821288638578,
        1281.630899921404
      ],
      "voteCount": 423,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.90642729527994
      }
    },
    {
      "id": "59bfbd653ff1e9ae0a56829e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1272.1262757523882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.486886052266,
        1295.7656654525106
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.47097117997234
      }
    },
    {
      "id": "7431b20e2ee3f451a3a608d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1303.2634946652734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.949148150738,
        1312.5778411798087
      ],
      "voteCount": 4171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.584402187385933
      }
    },
    {
      "id": "20c40870e30d61cd4e978364",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3-4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1314.43427583244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.918417057301,
        1344.9501346075795
      ],
      "voteCount": 307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 242.41250010743983
      }
    },
    {
      "id": "cee6b59a29a25126fc5441ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1332.8648479023252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.4758218666616,
        1350.2538739379888
      ],
      "voteCount": 1214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.71442610293346
      }
    },
    {
      "id": "0ea809102f63579c33dacceb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1308.681266718354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.4440129533828,
        1318.9185204833257
      ],
      "voteCount": 3530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.28165770874644
      }
    },
    {
      "id": "15e6a72f04be722b8970eb52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1299.546682169274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.3831624248353,
        1310.7102019137128
      ],
      "voteCount": 2884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.44188702820817
      }
    },
    {
      "id": "d4cdb13904d2a217064e1f16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1328.261474599187,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.8048829991685,
        1334.7180661992056
      ],
      "voteCount": 10951,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.852016651813967
      }
    },
    {
      "id": "acd3d4202c73713f9e390206",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1262.2658002119674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.1631060836305,
        1269.3684943403043
      ],
      "voteCount": 16043,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.132579635878136
      }
    },
    {
      "id": "82bf1d640715f6eed0592efd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1277.9859343647029,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.569386596363,
        1296.4024821330427
      ],
      "voteCount": 1070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.29177860150959
      }
    },
    {
      "id": "d5410e3666971328536ae0bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1340.3664995240038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.1772501010782,
        1374.5557489469295
      ],
      "voteCount": 295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.286686559303
      }
    },
    {
      "id": "907a54ee654fe8e19310cd1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1316.261988321191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.9789671556086,
        1338.5450094867733
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.2563724986317
      }
    },
    {
      "id": "a3c318b3d7e79912459fd906",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1317.7454211911072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.6821143331833,
        1326.808728049031
      ],
      "voteCount": 4553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.383420995789095
      }
    },
    {
      "id": "a00ea0cc39e05c79ab9db8c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1312.6690458568523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.5834906712278,
        1319.7546010424767
      ],
      "voteCount": 8559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.06927774887815
      }
    },
    {
      "id": "ed28d88951305ace0f2cd704",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1316.3966846404353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8957784275794,
        1326.8975908532911
      ],
      "voteCount": 3294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.704988505192617
      }
    },
    {
      "id": "53397f11cec88fd66b87390d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1279.495093005738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.9916896826448,
        1288.9984963288316
      ],
      "voteCount": 3914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.510514868688396
      }
    },
    {
      "id": "8ee2f83c7773ee090c6230bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1324.2849781542084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.4427384264072,
        1340.1272178820095
      ],
      "voteCount": 1407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.33365872389405
      }
    },
    {
      "id": "396d6ebfc6c2a44192e5a050",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1338.278660414594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.231894416832,
        1348.3254264123564
      ],
      "voteCount": 3698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.275826899414977
      }
    },
    {
      "id": "b7d0b2473a1daa86bd7c8a4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1285.0052963254122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.4038028052896,
        1300.6067898455349
      ],
      "voteCount": 1410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.363063726516486
      }
    },
    {
      "id": "78e939377a620e52ba2074e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1338.8223042207405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.0874799391613,
        1355.55712850232
      ],
      "voteCount": 1334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.90312269564724
      }
    },
    {
      "id": "d87a9e60f6867818691834a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1334.581069326122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.8455063999545,
        1342.3166322522893
      ],
      "voteCount": 6615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.577137899367893
      }
    },
    {
      "id": "6fac8309e3adf90f2d042ffb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1299.9496727738979,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.2249228632336,
        1308.6744226845626
      ],
      "voteCount": 4905,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.81571703790522
      }
    },
    {
      "id": "c9721bc51f37310a1d67e15d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1280.9380843712197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.381144041878,
        1289.4950247005613
      ],
      "voteCount": 4985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.060786856666585
      }
    },
    {
      "id": "dc5813f13f22a31c519b0174",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1290.2833521787932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.8509216058892,
        1313.7157827516971
      ],
      "voteCount": 674,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.93497032847395
      }
    },
    {
      "id": "3805d4b4a80c28365e15d3c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1274.2960204412466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.001957819223,
        1301.5900830632704
      ],
      "voteCount": 489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.92785115950957
      }
    },
    {
      "id": "23776a6ac13f81e057f06217",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1310.8632759698899,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.819467459883,
        1321.9070844798966
      ],
      "voteCount": 2853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.749840906445474
      }
    },
    {
      "id": "6832e3153405a53fe1d36ffb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1259.5917863118739,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.7614006194676,
        1274.4221720042801
      ],
      "voteCount": 1573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.25437914385507
      }
    },
    {
      "id": "d0b09cdd68b856bb11c40bb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1292.7637877101438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.434137644678,
        1303.0934377756093
      ],
      "voteCount": 3428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.776341086923974
      }
    },
    {
      "id": "5f81f8e4204234737a35b671",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1318.145447333442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.0045021689207,
        1323.2863924979633
      ],
      "voteCount": 22600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.880020955122362
      }
    },
    {
      "id": "9274c6a73e3285c81a003bc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1312.7907372625514,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.4743990258512,
        1328.1070754992513
      ],
      "voteCount": 1394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.06800252998919
      }
    },
    {
      "id": "f3369e5fe2aa014b7c7ab946",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-3n-e4b-it",
      "organization": "google",
      "license": "Gemma",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1301.6221673784883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.6050748449798,
        1331.6392599119968
      ],
      "voteCount": 408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 234.55303993142948
      }
    },
    {
      "id": "01ca7db0d68640398095b399",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1476.330983529393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.652464205862,
        1506.0095028529238
      ],
      "voteCount": 383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 229.29167026135988
      }
    },
    {
      "id": "00c6680e5168ddda21b8fec6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1479.9851535879477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.646842937753,
        1495.3234642381426
      ],
      "voteCount": 1365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.24334128860122
      }
    },
    {
      "id": "bbf00d2d443bea0a5145226e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1404.281642678348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.2957504610615,
        1423.2675348956343
      ],
      "voteCount": 943,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.8352121190465
      }
    },
    {
      "id": "1e2b9c635834572286c5d3f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1448.416353252597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.0440170080592,
        1459.7886894971348
      ],
      "voteCount": 2517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.66690564587606
      }
    },
    {
      "id": "2fdb5e6967df4a2e9577242a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1435.5609363567658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.275823262884,
        1446.8460494506473
      ],
      "voteCount": 3954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.152451577937235
      }
    },
    {
      "id": "106221a7dc1c9a220c17768d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1477.544684114848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.5465092499235,
        1504.5428589797725
      ],
      "voteCount": 406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.74600016806542
      }
    },
    {
      "id": "50d6e9d82a369b263eb0db1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1478.0956954424337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.0044072494509,
        1519.1869836354165
      ],
      "voteCount": 214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 439.54498646784054
      }
    },
    {
      "id": "f58803b2e50609f40da3604f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1467.3436580284524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.5257729356451,
        1482.1615431212597
      ],
      "voteCount": 1488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.15789986887476
      }
    },
    {
      "id": "8e57d782a480a2a159138293",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1461.312103528901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.168451775373,
        1471.4557552824292
      ],
      "voteCount": 3257,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.78505112239166
      }
    },
    {
      "id": "bf660087feb08593bb0c02a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1448.0120201544435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.3848224168023,
        1465.6392178920846
      ],
      "voteCount": 1048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.88544341749734
      }
    },
    {
      "id": "d07693f7306b236959ce1a7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1411.9009310487158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.9032249330107,
        1429.898637164421
      ],
      "voteCount": 1055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.32146237838916
      }
    },
    {
      "id": "40d3e2b63a49e630c15366e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1459.1935028758253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.3719035007266,
        1488.015102250924
      ],
      "voteCount": 386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 216.24196153392316
      }
    },
    {
      "id": "6c839d2a530f90c6a87966f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1452.1181953903595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.7855072096697,
        1471.4508835710492
      ],
      "voteCount": 871,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.29450444147861
      }
    },
    {
      "id": "327c130b6fdf9f09cc28faa3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1475.5101773254758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.3817002550286,
        1507.638654395923
      ],
      "voteCount": 296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 268.7101663840642
      }
    },
    {
      "id": "f2c272f7bcf15efad1e32ca9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1435.2638323361202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.0309077335996,
        1465.496756938641
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.93818252008262
      }
    },
    {
      "id": "04d40d03de279b2c2fe8f7a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1474.9493508501014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.6108785669342,
        1487.2878231332688
      ],
      "voteCount": 2093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.630230438075884
      }
    },
    {
      "id": "1464da7ceb977a493acad72e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1410.7383455110005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.078566356092,
        1426.398124665909
      ],
      "voteCount": 1315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.837384344574744
      }
    },
    {
      "id": "d863de7a387d2088034d7b66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1439.018581223839,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.8710537672766,
        1453.1661086804015
      ],
      "voteCount": 1592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.10326141099213
      }
    },
    {
      "id": "20b2bae0f0be2b7ddf29b52c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1449.1029934743192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.5589412088307,
        1463.6470457398077
      ],
      "voteCount": 1547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.06487669781614
      }
    },
    {
      "id": "f0251eabd810882dcc4774f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1468.305311142668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.8896315786,
        1496.7209907067358
      ],
      "voteCount": 369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.19380469159543
      }
    },
    {
      "id": "7eb71e8ac703055c0e4fbd16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1446.9294974068537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.361294310059,
        1464.4977005036485
      ],
      "voteCount": 1081,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.34493520731193
      }
    },
    {
      "id": "375139c8311410c672441097",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1438.658620262443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.0063254914842,
        1446.3109150334021
      ],
      "voteCount": 5789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.243587916703248
      }
    },
    {
      "id": "e1574ce4bb8e9e2417482a3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-26b-a4b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1447.8858880764126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.917999636065,
        1468.8537765167603
      ],
      "voteCount": 679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.44931890937848
      }
    },
    {
      "id": "8ad66da74470b7676a917e7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1480.3814249684285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.5605487633472,
        1510.2023011735096
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.4966004186108
      }
    },
    {
      "id": "2cea8ea09dc569512dd859a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1498.3387016922516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.8833464328302,
        1513.7940569516732
      ],
      "voteCount": 1355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.18158708564905
      }
    },
    {
      "id": "93f189e18225348c0c8eadb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1422.0319728879886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.6244919458652,
        1441.439453830112
      ],
      "voteCount": 934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.04877107880198
      }
    },
    {
      "id": "7963ff5f489fcb58bce6de9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1460.782621925932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.5112222836271,
        1472.0540215682367
      ],
      "voteCount": 2590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.071928094648555
      }
    },
    {
      "id": "f8b8ae877412eff60a347c9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1455.0600888815397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.8171769905252,
        1466.3030007725542
      ],
      "voteCount": 4012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.90496493367965
      }
    },
    {
      "id": "00598bb249abacd56808d21d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1483.54624214938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.3202518892697,
        1509.7722324094905
      ],
      "voteCount": 437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.04723107226272
      }
    },
    {
      "id": "75a44a05c213b7e22035edf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1462.4591095562405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.3951280754172,
        1500.5230910370638
      ],
      "voteCount": 240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 377.16574712901814
      }
    },
    {
      "id": "ae955577a1de602933835f01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1484.7171844089453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.9966141572854,
        1499.4377546606052
      ],
      "voteCount": 1521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.409608601478105
      }
    },
    {
      "id": "c2e010eacdec7f58c7ed7deb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1474.14550073022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.1534419814116,
        1484.1375594790284
      ],
      "voteCount": 3336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.99044860296019
      }
    },
    {
      "id": "b682f0f0fa7d7c872d89fcb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1442.735907395475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.5582318385952,
        1459.9135829523548
      ],
      "voteCount": 1130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.81262544006835
      }
    },
    {
      "id": "ebcb974b917e1040f24e6124",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1416.312677400762,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.1307645138238,
        1434.4945902876998
      ],
      "voteCount": 1038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.05635818542201
      }
    },
    {
      "id": "1d24771abc2b9632e177fe99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1462.8997745914337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.7451928985288,
        1490.0543562843384
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.95085547823157
      }
    },
    {
      "id": "7bc89647f34750fa5e37cda2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1471.8358890022473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.253168034733,
        1491.4186099697615
      ],
      "voteCount": 872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.82742973208077
      }
    },
    {
      "id": "3b98ff159f3e3e3b83616df8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1473.4754530738044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.0854407419877,
        1503.8654654056209
      ],
      "voteCount": 322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 240.41721976888974
      }
    },
    {
      "id": "33f0f22755861411bcea7df8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1468.659245806776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.3345526626858,
        1496.983938950866
      ],
      "voteCount": 402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.84988728367986
      }
    },
    {
      "id": "488959dc30f435da0e7dd8bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1490.196086360183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.8677270154174,
        1502.5244457049487
      ],
      "voteCount": 2107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.565293089932666
      }
    },
    {
      "id": "25f02656d068efb8a2bbeeca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1433.8600934348274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.9227490825676,
        1449.797437787087
      ],
      "voteCount": 1345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.1204393586613
      }
    },
    {
      "id": "5b429165b5adaa40aa2dcd5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1453.0574169970425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.8426724597061,
        1467.2721615343787
      ],
      "voteCount": 1646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.599538793239375
      }
    },
    {
      "id": "993e377fb7f977022c352b17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1467.3826916326884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.3823002255403,
        1481.3830830398365
      ],
      "voteCount": 1637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.025136205397736
      }
    },
    {
      "id": "a7a76092b186f65e8d0da278",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1469.8313622112057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.2360707736354,
        1497.4266536487758
      ],
      "voteCount": 398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.23201160512184
      }
    },
    {
      "id": "fd343256f4a118ad25825081",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1464.789647885133,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.8657134589178,
        1482.7135823113485
      ],
      "voteCount": 1053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.63162025441675
      }
    },
    {
      "id": "b47189c7c3342fd84a7b0330",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1451.9310496706478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.303089139504,
        1459.5590102017916
      ],
      "voteCount": 5855,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.146793075390384
      }
    },
    {
      "id": "406d8c07ebd71a357f8769f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1467.7292569860535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.0987721860245,
        1490.3597417860829
      ],
      "voteCount": 646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.3188421870965
      }
    },
    {
      "id": "67d3f162c3a24db85c638f1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-4-31b",
      "organization": "google",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1467.963783374606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.5517003756615,
        1507.3758663735505
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 404.3547930145508
      }
    },
    {
      "id": "a1d57ddceaed20ea90a5b156",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1136.1850540051116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.1571203458561,
        1156.2129876643671
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.41817689121139
      }
    },
    {
      "id": "827f80f90c0191cabe5221af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1167.2360722532803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.5929616166484,
        1183.8791828899123
      ],
      "voteCount": 1381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.10623479054274
      }
    },
    {
      "id": "5010070b3aa4bb3095adde6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1099.6965547400407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1081.8291356415598,
        1117.5639738385219
      ],
      "voteCount": 1345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.105059859286
      }
    },
    {
      "id": "61413814b50ad9cae6acce59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1166.8497280046035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.7559065716605,
        1177.9435494375468
      ],
      "voteCount": 5689,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.038056303774276
      }
    },
    {
      "id": "de01b3bc87521ee4a0c9e6e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 974.9404632119989,
      "unit": "Arena rating",
      "confidenceInterval": [
        960.6000909808874,
        989.2808354431104
      ],
      "voteCount": 5988,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.533380240601645
      }
    },
    {
      "id": "4517892e6821f07bcad5dc03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1115.7646121692064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.3676096248241,
        1147.1616147135887
      ],
      "voteCount": 340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.6139101795262
      }
    },
    {
      "id": "058685de5472dcae07022bfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1130.1628739686869,
      "unit": "Arena rating",
      "confidenceInterval": [
        1083.1648213916014,
        1177.1609265457723
      ],
      "voteCount": 199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 574.9943053247044
      }
    },
    {
      "id": "6bcb6d5e033855cf73d9184b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1168.3035617337987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.884827320637,
        1183.7222961469606
      ],
      "voteCount": 1588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.887262626093644
      }
    },
    {
      "id": "f1d9c4b7d42b8c3b32392a63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1152.5925600883356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.0155511217622,
        1166.169569054909
      ],
      "voteCount": 2267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.985721332061416
      }
    },
    {
      "id": "e51043a26aa9afe297854dab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1124.9493099583287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.1975506727692,
        1146.7010692438882
      ],
      "voteCount": 818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.166498484404
      }
    },
    {
      "id": "c4dc8ebbd9d772778d7e1496",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1089.023197652227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1071.301731419784,
        1106.7446638846704
      ],
      "voteCount": 1291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.75289130676681
      }
    },
    {
      "id": "59bcff92b7af2a26e7f98211",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1158.2401058015964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.3948397155968,
        1187.085371887596
      ],
      "voteCount": 462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 216.59723933257408
      }
    },
    {
      "id": "1471af183c90e0581d874cb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1137.7090716719308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.5463022178503,
        1154.8718411260113
      ],
      "voteCount": 1588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.67937340551637
      }
    },
    {
      "id": "26f7f06a47407466eae7cfdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1121.2594770700118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.6517960623673,
        1138.8671580776563
      ],
      "voteCount": 982,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.70643079572048
      }
    },
    {
      "id": "3cef74ffd73c14d8360ba25e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1157.916679819801,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.0663639178929,
        1183.766995721709
      ],
      "voteCount": 538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.95444372033924
      }
    },
    {
      "id": "00e5eb5eae59982f9694b640",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1165.3634112685702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.4407221033582,
        1179.2861004337824
      ],
      "voteCount": 2374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.460328390579285
      }
    },
    {
      "id": "81770c8b85825af52c11e726",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1102.9920889279251,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.2522735371801,
        1117.7319043186703
      ],
      "voteCount": 2191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.55720076519957
      }
    },
    {
      "id": "9bd5d11db2cb8dc928742712",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1101.8121349213666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.0008492431962,
        1114.623420599537
      ],
      "voteCount": 2835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.725706141511694
      }
    },
    {
      "id": "c0bf3b9797eb5c589e89cef7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1109.7347808491463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.8192943506629,
        1132.6502673476298
      ],
      "voteCount": 676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.69794366487386
      }
    },
    {
      "id": "7683cbc495f88e3fdd2a97c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1116.809724858113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.3379610576835,
        1133.281488658543
      ],
      "voteCount": 1120,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.62915818218227
      }
    },
    {
      "id": "2a4e29e84f303a8a09a248e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1041.243377626312,
      "unit": "Arena rating",
      "confidenceInterval": [
        1022.3826668934862,
        1060.1040883591377
      ],
      "voteCount": 1332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.60190619017197
      }
    },
    {
      "id": "4de3975c11b8a96c560a72ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1136.0791617145305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.585159602751,
        1145.57316382631
      ],
      "voteCount": 8925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.464022473157627
      }
    },
    {
      "id": "73767981b38915105bc73575",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gemma-7b-it",
      "organization": "google",
      "license": "Gemma license",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1076.8164224395018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.4422398650981,
        1100.1906050139055
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.22524216017214
      }
    },
    {
      "id": "b9ab3db322ad714e48f8b805",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1302.595237733013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.5523259638512,
        1319.6381495021744
      ],
      "voteCount": 1227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.61211902277822
      }
    },
    {
      "id": "c5f945332d83477adc7494ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1307.8327930479506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.8323476522876,
        1321.833238443614
      ],
      "voteCount": 1718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.02552973391667
      }
    },
    {
      "id": "bb2e235f1f4fd67c18b51763",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1240.8129900556664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.5820761739594,
        1256.0439039373737
      ],
      "voteCount": 1547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.3887086911588
      }
    },
    {
      "id": "c38b119a396b84884480198e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1287.6154813847807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.421095777529,
        1296.8098669920323
      ],
      "voteCount": 5169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.006412313841597
      }
    },
    {
      "id": "eb7cb922d404f7b5ec9574f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1191.3527289126546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.383458481914,
        1202.321999343395
      ],
      "voteCount": 6229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.322708220773226
      }
    },
    {
      "id": "659f1600d2ff19d5afa46128",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1249.0673430754568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.9896860892436,
        1274.14500006167
      ],
      "voteCount": 514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.71095182130136
      }
    },
    {
      "id": "c3e09bbca345a788068202fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1227.2166525613413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.4324584036162,
        1257.0008467190664
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.92743226771805
      }
    },
    {
      "id": "4adea56dd9dff5383778048a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1284.4384940976474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.819619633564,
        1298.0573685617305
      ],
      "voteCount": 1775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.28211112645711
      }
    },
    {
      "id": "28a8d432cc4171e232029cfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1277.3171858386027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.159975559176,
        1288.4743961180295
      ],
      "voteCount": 2970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.405225990904285
      }
    },
    {
      "id": "e5392cb27b71f33cf983c7a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1245.994708513648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.5545505901782,
        1263.4348664371178
      ],
      "voteCount": 1186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.17802131759022
      }
    },
    {
      "id": "83a5189cb7a062ef93eedefe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1233.1627189470937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.6370969570385,
        1247.688340937149
      ],
      "voteCount": 1605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.925408300967256
      }
    },
    {
      "id": "23f7e1316c4d9eb5f3d04e89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1313.0358268448322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.2533217355005,
        1337.818331954164
      ],
      "voteCount": 556,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.8800320819458
      }
    },
    {
      "id": "3552e82d57f110ce12870928",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1290.4222513465056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.3142740406172,
        1305.5302286523943
      ],
      "voteCount": 1590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.41778603629502
      }
    },
    {
      "id": "d115b1c755704b843b242788",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1264.2763273750093,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.7933921575368,
        1280.7592625924815
      ],
      "voteCount": 1067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.72499434844863
      }
    },
    {
      "id": "5551aa575b8430a856c351ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1281.0629987415734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.694767568516,
        1305.431229914631
      ],
      "voteCount": 554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.57947572018415
      }
    },
    {
      "id": "f3a896dd894d11c46f3ff73b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1296.1436546945047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.5460595444479,
        1307.7412498445615
      ],
      "voteCount": 2832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.013837071489924
      }
    },
    {
      "id": "ea4b24587e6dccae5f710ce3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1253.313502256353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.2797831290168,
        1265.3472213836892
      ],
      "voteCount": 2609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.696719604415776
      }
    },
    {
      "id": "19f9da2954c5b191237a0993",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1254.7512253425984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.4431445308192,
        1265.0593061543775
      ],
      "voteCount": 3766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.660463116188993
      }
    },
    {
      "id": "ae09f3b2906e1983a0f168f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1103.5581477327573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1067.3692503909797,
        1139.7470450745352
      ],
      "voteCount": 302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 340.92160086648784
      }
    },
    {
      "id": "43724a2116005634834e9991",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1266.570950804681,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.7945988943557,
        1283.3473027150062
      ],
      "voteCount": 1174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.26539123702368
      }
    },
    {
      "id": "11bf6b3d8ee121ce0e89395c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1246.5525846133016,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.00299981346,
        1262.1021694131432
      ],
      "voteCount": 1191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.942126606935844
      }
    },
    {
      "id": "16e434a32439a9feb398098a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1258.1364357364696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.5376570725668,
        1272.7352144003723
      ],
      "voteCount": 1631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.480052871974266
      }
    },
    {
      "id": "03f760aa4880c89c5214c5b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1272.8253405146097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.8356999391685,
        1279.814981090051
      ],
      "voteCount": 9788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.71784435399175
      }
    },
    {
      "id": "786cbd3cbcf3c60f4e108db0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-0520",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1259.7454964779135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.5486248556936,
        1275.942368100134
      ],
      "voteCount": 1264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.29141286988494
      }
    },
    {
      "id": "7289d0337ec5103f3303f74a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1402.1253110828825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.9772327760875,
        1432.2733893896773
      ],
      "voteCount": 387,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.60454739129662
      }
    },
    {
      "id": "b168c9b2549d68043bb9e5d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1330.7146106998036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.5564397596752,
        1348.872781639932
      ],
      "voteCount": 894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.83176008934774
      }
    },
    {
      "id": "5ccf08968d55c25fe17c895b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1317.0479350156645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.9070097458207,
        1336.1888602855083
      ],
      "voteCount": 918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.37392883455144
      }
    },
    {
      "id": "cb037015c4243c3c3f393a72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1351.7599493812595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.4783756602792,
        1362.0415231022398
      ],
      "voteCount": 3466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.51838900640582
      }
    },
    {
      "id": "cd1d11a6b6d57543cb1cc93a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1300.3365157197247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.637909667479,
        1313.0351217719706
      ],
      "voteCount": 3826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.97743700946314
      }
    },
    {
      "id": "12f2df967fc990e1cea463c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1308.8204431450285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.4140676478746,
        1338.2268186421827
      ],
      "voteCount": 354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 225.10586739112074
      }
    },
    {
      "id": "7431a1419ca9c6d9302355d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1348.7377755102239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.194720485519,
        1387.2808305349288
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 386.7195146371507
      }
    },
    {
      "id": "5d898d5d219d9647cf53641f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1324.1771900012982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.4949219025934,
        1341.859458100003
      ],
      "voteCount": 955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.39163263449298
      }
    },
    {
      "id": "2dbbbe0c50eb58c13e5ced19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1325.6418418588914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.225391795992,
        1340.058291921791
      ],
      "voteCount": 1468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.10289218680744
      }
    },
    {
      "id": "5a6121c67b0c6b9ddcded6e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1344.5246141700247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.6336991250269,
        1368.4155292150228
      ],
      "voteCount": 592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.5830900002146
      }
    },
    {
      "id": "c9557cfc419481a0ead91002",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1300.5997153564958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.186031892853,
        1318.0133988201387
      ],
      "voteCount": 1062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.93781657593227
      }
    },
    {
      "id": "a6e38a91c0039938cd2598da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1381.1618571400918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.3417756843587,
        1410.981938595825
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.48426145718258
      }
    },
    {
      "id": "2392fc3c97c2655e9b7e633c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1364.9606013637886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.4562077030075,
        1383.4649950245694
      ],
      "voteCount": 986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.13608103998271
      }
    },
    {
      "id": "36d4d14a92668d2ccff21866",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1303.7786612875543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.9289273108532,
        1324.6283952642552
      ],
      "voteCount": 638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.1631047448408
      }
    },
    {
      "id": "34319a2653c27d00b4a83162",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1412.6389382117966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.8411659474095,
        1446.4367104761832
      ],
      "voteCount": 293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 297.3582337735303
      }
    },
    {
      "id": "b2b1947c12e2672b8c6869b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1349.8896077531685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.048849265246,
        1364.7303662410914
      ],
      "voteCount": 1406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.33449785023353
      }
    },
    {
      "id": "224790269660abe0af96f920",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1332.283019276789,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.14109821379,
        1347.424940339788
      ],
      "voteCount": 1459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.68507907541864
      }
    },
    {
      "id": "34cef8903522cfc45f3508c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1314.3709592669736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.8954192054782,
        1326.8464993284688
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.51562364473101
      }
    },
    {
      "id": "91eaf5a163be03371baeb13d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1219.9100689510888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.6893930944348,
        1258.1307448077425
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 380.27742353240706
      }
    },
    {
      "id": "5e6d217d277c3726d9f98227",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1339.2491694341097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.8069446107484,
        1359.691394257471
      ],
      "voteCount": 765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.78277634467551
      }
    },
    {
      "id": "084b0ffb771de534e507b55c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1297.5110093218095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.2637085542067,
        1316.7583100894121
      ],
      "voteCount": 721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.4369538059041
      }
    },
    {
      "id": "90b61b198082dce88c39827f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1333.6590442038676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.1798824098069,
        1353.1382059979283
      ],
      "voteCount": 851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.77438804111186
      }
    },
    {
      "id": "b002275bcb9cc0167ab19fd4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1342.864930600441,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.449239537148,
        1351.2806216637343
      ],
      "voteCount": 5760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.43670839090126
      }
    },
    {
      "id": "5a90b78c7ab5d197906cbf1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus-0111",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1329.8629486991172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.1418867479074,
        1351.5840106503272
      ],
      "voteCount": 653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.81910448881169
      }
    },
    {
      "id": "8bea392a629529a1709fa17d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1342.332890481402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.451406332962,
        1355.214374629842
      ],
      "voteCount": 2427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.19521348832997
      }
    },
    {
      "id": "d48f4e735ed640c36a50c569",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1352.1740449832562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.8004325931058,
        1361.5476573734063
      ],
      "voteCount": 4449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.8727192824372
      }
    },
    {
      "id": "7ede44d4b5a7c005c31cf627",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1289.7351791537496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.493983151489,
        1299.9763751560101
      ],
      "voteCount": 3801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.302673398895443
      }
    },
    {
      "id": "96cdb6db3092beff08c0c33b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1325.440767962385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.0434018101735,
        1331.8381341145966
      ],
      "voteCount": 13191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.653841573152125
      }
    },
    {
      "id": "dfc219b487a79053a3bec265",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1264.533611235202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.8065796463027,
        1272.2606428241013
      ],
      "voteCount": 16416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.542797661712239
      }
    },
    {
      "id": "e28d2bf1dd56eb845bc4f4f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1301.8328927982775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.1080777875486,
        1316.5577078090064
      ],
      "voteCount": 1608,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.44214534649239
      }
    },
    {
      "id": "1e7f0cc79941cfadf48ff6b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1347.9252617036454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.7836961861412,
        1384.0668272211497
      ],
      "voteCount": 286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 340.0303944479162
      }
    },
    {
      "id": "0411fa827550727145aff7dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1303.3316999361082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.6242522152284,
        1326.039147656988
      ],
      "voteCount": 659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.22717932541048
      }
    },
    {
      "id": "6d66e58fc7facc76e9e6b048",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1327.206973181892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.592073233669,
        1336.821873130115
      ],
      "voteCount": 4016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.06541507521182
      }
    },
    {
      "id": "ea1bd14208db74ce5d03bb3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1319.1962795778607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.4460320471546,
        1326.9465271085664
      ],
      "voteCount": 7067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.63633494224465
      }
    },
    {
      "id": "2fff5a4e8d0f37cc4eb67418",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1319.144332269695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.907774270364,
        1330.3808902690262
      ],
      "voteCount": 3267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.86778319532188
      }
    },
    {
      "id": "0d4d952a1f449f101f4592b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1280.3092980702015,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.2949104661934,
        1290.3236856742096
      ],
      "voteCount": 3855,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.10673802958811
      }
    },
    {
      "id": "a2d9970058501eeec0209ac3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1349.7775370156792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.6489924516695,
        1364.9060815796888
      ],
      "voteCount": 1723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.57967306385618
      }
    },
    {
      "id": "0ea2725520fb28a81e074e68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1334.0773135651004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.4365200186992,
        1343.7181071115017
      ],
      "voteCount": 4702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.195209305286063
      }
    },
    {
      "id": "feef090b47c4e3644d7ed069",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1299.7997411401768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.3227356614088,
        1310.2767466189448
      ],
      "voteCount": 2991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.574468431318618
      }
    },
    {
      "id": "3fc487715edc1a935a7267c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1338.7317868967934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.1757585537712,
        1354.2878152398157
      ],
      "voteCount": 1513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.994302191994706
      }
    },
    {
      "id": "3b628069ec2edfa5bdc26961",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1340.7463812620729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.7419545269688,
        1348.7508079971767
      ],
      "voteCount": 7097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.678780210396972
      }
    },
    {
      "id": "c2e7a1f229850dfbde8f8e35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1308.7706554710226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.4893380853055,
        1317.0519728567397
      ],
      "voteCount": 7164,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.85264943451525
      }
    },
    {
      "id": "e7da4fc1631d1a6b677233fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1300.4148672133506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.5094806301636,
        1307.320253796538
      ],
      "voteCount": 10743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.413087342335565
      }
    },
    {
      "id": "061e56ae1f882107dc820e6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1232.3454982765593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.618378772625,
        1259.0726177804936
      ],
      "voteCount": 485,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.95511505405406
      }
    },
    {
      "id": "df0b8abb42b7d71791397145",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1286.0039717266789,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.2933908939772,
        1318.7145525593805
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.53535553958193
      }
    },
    {
      "id": "e9c68551a635e12ed5ea4369",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1325.3794813499435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.2606685285612,
        1335.498294171326
      ],
      "voteCount": 3992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.654033713076203
      }
    },
    {
      "id": "9299e3a17fdaa75d30bc5b48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1287.2866845732683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.3934927940754,
        1297.179876352461
      ],
      "voteCount": 3599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.478665306166654
      }
    },
    {
      "id": "0932020cefcdfa2b085f4ba5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1313.7839150815066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.3414114935513,
        1323.2264186694617
      ],
      "voteCount": 4844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.21016003822137
      }
    },
    {
      "id": "f08407c970317e9c52483dcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1319.261953635816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.343446323273,
        1324.180460948359
      ],
      "voteCount": 26126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.2975331280962585
      }
    },
    {
      "id": "bb082a3b2f44f7bcbef737bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1306.19081958181,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.094601820812,
        1316.2870373428084
      ],
      "voteCount": 3904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.535131010223513
      }
    },
    {
      "id": "f8354e396fcf33d902f944cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4-plus",
      "organization": "zai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1338.7888317019124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.664960775049,
        1370.9127026287758
      ],
      "voteCount": 332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 268.6331238972691
      }
    },
    {
      "id": "e438528c35192a4bcb7ea16e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1414.6954770449474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.8191145480894,
        1429.5718395418057
      ],
      "voteCount": 1616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.609926714752675
      }
    },
    {
      "id": "7142fb8ddaf9ebcf318daab8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1426.761368034602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.0691271255198,
        1434.4536089436842
      ],
      "voteCount": 6104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.40315098123762
      }
    },
    {
      "id": "b50515da51f58651ee7383c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1328.5633417466142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.0059791148446,
        1338.1207043783834
      ],
      "voteCount": 4023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.778253194612386
      }
    },
    {
      "id": "fc9eaf21a6aa5051f3da274b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1389.7556286195822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.2657906611776,
        1395.245466577987
      ],
      "voteCount": 14832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.845540513719586
      }
    },
    {
      "id": "1ed275a29b9f16455b8c67b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1343.011167310053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.0551157666873,
        1348.9672188534187
      ],
      "voteCount": 21887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.234655802146056
      }
    },
    {
      "id": "202b774c4cd21837397e93a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1389.3552357209965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.5857493383648,
        1405.1247221036283
      ],
      "voteCount": 1391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.73496460052425
      }
    },
    {
      "id": "4f4c04e3bc94f41853765493",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1406.1586597202195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6317164660159,
        1434.6856029744233
      ],
      "voteCount": 470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.84308602884232
      }
    },
    {
      "id": "e72100612358c05192c5e14e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1346.1923289685506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.9818823131895,
        1369.4027756239118
      ],
      "voteCount": 673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.23964829174508
      }
    },
    {
      "id": "80f5028d36ac48f78d8c198d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1403.0889161611576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.0877793474292,
        1410.090052974886
      ],
      "voteCount": 7660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.75971420557511
      }
    },
    {
      "id": "df7a97bb1ee4d81344c1dac3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1390.876850402677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3818746934073,
        1396.371826111947
      ],
      "voteCount": 14883,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.860232129212389
      }
    },
    {
      "id": "627d7678001539ef91c8694a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1371.313694534429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.099064874908,
        1379.5283241939499
      ],
      "voteCount": 5513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.566279789220346
      }
    },
    {
      "id": "b6050b863707100390b4eafe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1326.0269308066736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.994309761752,
        1334.0595518515952
      ],
      "voteCount": 5692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.796483800302383
      }
    },
    {
      "id": "f9158c0f21d93a4a16311034",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1372.7293739118193,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.170653295901,
        1386.2880945277377
      ],
      "voteCount": 1935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.856534020404496
      }
    },
    {
      "id": "7b88c3be8636904dee1b0d0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1396.3313722808402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.7992703466548,
        1404.863474215026
      ],
      "voteCount": 4933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.950291233937303
      }
    },
    {
      "id": "03e220640a4121599cfe14f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1391.4622935112038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.1322691756409,
        1406.7923178467665
      ],
      "voteCount": 1456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.17718739113868
      }
    },
    {
      "id": "bd21dc1ae1ede3867aa4aacc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1394.9105149952638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.3205971622838,
        1409.5004328282437
      ],
      "voteCount": 1646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.41272529758478
      }
    },
    {
      "id": "f5f805c5fa31f422692008f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1414.5134269320545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.3233208556812,
        1420.7035330084282
      ],
      "voteCount": 10659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.974703628303484
      }
    },
    {
      "id": "f26f3f9e65a5196b99cd236b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1342.4432523409346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.0476071395306,
        1349.8388975423386
      ],
      "voteCount": 7022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.238228365329102
      }
    },
    {
      "id": "4417c0d2f05bddcf65d77d14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1362.4226264414729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.5644370256778,
        1369.280815857268
      ],
      "voteCount": 8114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.243984449226748
      }
    },
    {
      "id": "46eab557aca7617b2183bc1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1326.5817893452029,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.705029285986,
        1348.4585494044195
      ],
      "voteCount": 785,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.58616713794702
      }
    },
    {
      "id": "e780d268c12c1fdc54ddcdca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1283.2966878094928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.1125436437414,
        1307.4808319752442
      ],
      "voteCount": 636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.2527915382328
      }
    },
    {
      "id": "e7946162b0d57f1a67cd686d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1379.634039136099,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.0659752307265,
        1387.202103041472
      ],
      "voteCount": 6632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.909854289537115
      }
    },
    {
      "id": "b2a874d0c3cd395ddf7a5d0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1390.4955888148588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.6782142588347,
        1405.3129633708832
      ],
      "voteCount": 1540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.15396128959193
      }
    },
    {
      "id": "da4b89645a1925dc5fcdeb45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1369.7017463928196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.2142918525292,
        1378.18920093311
      ],
      "voteCount": 5122,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.752481267124228
      }
    },
    {
      "id": "fef8d3e45f69116d91dd2b5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1373.0638233103914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.820423937038,
        1377.3072226837448
      ],
      "voteCount": 31095,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.687395878038279
      }
    },
    {
      "id": "88ce4fc7f5380495b92ec16a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1357.4000943358476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.6286256711483,
        1372.171563000547
      ],
      "voteCount": 1487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.80037108214214
      }
    },
    {
      "id": "de487e6636b323af14d9e987",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5-air",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1363.2775954458286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.4321054409647,
        1386.1230854506928
      ],
      "voteCount": 724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.86411775410855
      }
    },
    {
      "id": "e43a1f9a2f35d2d876fc27ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1440.9333586266498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.3056339165626,
        1457.561083336737
      ],
      "voteCount": 1345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.97297743894309
      }
    },
    {
      "id": "c17c4a8bab44aed2c93f471e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1454.4368326820322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.6836864904965,
        1463.189978873568
      ],
      "voteCount": 4772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.94491463442332
      }
    },
    {
      "id": "c236902e4d9df5c9795cab10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1374.372778524387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.5051520715435,
        1385.2404049772304
      ],
      "voteCount": 3134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.744909741659367
      }
    },
    {
      "id": "da9297f915401ded124b233b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1419.5128928008367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.228189530588,
        1425.797596071085
      ],
      "voteCount": 11444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.28189993402933
      }
    },
    {
      "id": "41c0defc43d8245d80056c2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1396.9959337198695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.1946266154002,
        1403.7972408243388
      ],
      "voteCount": 17349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.041721775100319
      }
    },
    {
      "id": "babcd063426b29d5686133e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1439.501505248622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.845604622422,
        1457.157405874822
      ],
      "voteCount": 1106,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.14907421184496
      }
    },
    {
      "id": "93e3788ac6e10e58233af2ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1418.2676581666306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.058061430418,
        1452.4772549028432
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.6489793278138
      }
    },
    {
      "id": "31710a41fa8e640b2a665273",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1373.9347040613159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.9640710199892,
        1399.9053371026425
      ],
      "voteCount": 519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.5775115781087
      }
    },
    {
      "id": "38df851950f338929b39e955",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1432.297627355888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.1575132943863,
        1440.4377414173896
      ],
      "voteCount": 5698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.24903481388475
      }
    },
    {
      "id": "34fe5b3d807355a6b2b4ed9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1432.9817554359076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.6341593196635,
        1439.3293515521518
      ],
      "voteCount": 11205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.488717525202478
      }
    },
    {
      "id": "5000b9196699e34775c7c6f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1410.9821444508004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.6860152733534,
        1420.2782736282475
      ],
      "voteCount": 4283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.496145791865047
      }
    },
    {
      "id": "fa31b103ddbcb7bcdbc5d834",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1383.890509054975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.741649632457,
        1393.0393684774929
      ],
      "voteCount": 4329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.789021473324304
      }
    },
    {
      "id": "c3bd05dddb5d7c185f9b11ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1414.5750320102447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.9435202762668,
        1430.2065437442225
      ],
      "voteCount": 1485,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.60712700424977
      }
    },
    {
      "id": "c7acb2cf55d91cd29386c335",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1421.6423751649056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.9037818617653,
        1431.3809684680457
      ],
      "voteCount": 3882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.688589400740135
      }
    },
    {
      "id": "eb1fa7b73798ea5abdf355d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1418.7253910864172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.9806458626829,
        1435.4701363101512
      ],
      "voteCount": 1262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.98958694996638
      }
    },
    {
      "id": "968bcdaa6c6e3b9c4f80c4fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1433.3884908190546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.073403006965,
        1449.7035786311442
      ],
      "voteCount": 1384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.29192859813031
      }
    },
    {
      "id": "3b5461bafa689f499098dd40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1443.4716293334493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.422791229378,
        1450.520467437521
      ],
      "voteCount": 8274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.934179679279389
      }
    },
    {
      "id": "829135d96ae0eb4f085d29e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1383.4144718787602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.0031815207328,
        1391.8257622367878
      ],
      "voteCount": 5362,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.41743170743197
      }
    },
    {
      "id": "c15ee1eb6e64c1ec0a5aacda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1405.0256305834505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.1810355772222,
        1412.8702255896787
      ],
      "voteCount": 6165,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.019349336828792
      }
    },
    {
      "id": "db407f7b2911d5f41cf9d4c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1393.3033649078218,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.2631896218795,
        1417.343540193764
      ],
      "voteCount": 707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.44545698771807
      }
    },
    {
      "id": "88a2038ae113e9c2710cbdd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1348.2065936434292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.2687809260924,
        1373.144406360766
      ],
      "voteCount": 606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.89019124057455
      }
    },
    {
      "id": "d03fcf34414a1aabbd68ef53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1416.6756459378714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.0563675750216,
        1425.2949243007213
      ],
      "voteCount": 5017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.33951734587851
      }
    },
    {
      "id": "452f75ffc8d7a631d70ce6f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1413.3569345601927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.8698459851764,
        1428.8440231352088
      ],
      "voteCount": 1424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.4371947548446
      }
    },
    {
      "id": "507ac096cb3bdf06082d7c2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1406.4859692851624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.7791629013207,
        1416.1927756690038
      ],
      "voteCount": 3904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.527684551975238
      }
    },
    {
      "id": "628256a4d6d50516eac1afcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1411.2143055328104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.3360076641445,
        1416.092603401476
      ],
      "voteCount": 24322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.194987687289303
      }
    },
    {
      "id": "62ea7736c61e42469547e45f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1395.8911725587739,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.7891737950094,
        1411.9931713225385
      ],
      "voteCount": 1251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.49372472550007
      }
    },
    {
      "id": "598997955faf9f7b5bf46724",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1427.4490438740365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.5648165361565,
        1452.3332712119168
      ],
      "voteCount": 623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.19521231556826
      }
    },
    {
      "id": "6d778e6f0c47236c3374f2b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1346.930753196183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.6016587599138,
        1389.2598476324529
      ],
      "voteCount": 173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 466.42494932976035
      }
    },
    {
      "id": "eb25fe18166b7dc4bc5eb61f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1404.501592368807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.0557635415323,
        1422.9474211960817
      ],
      "voteCount": 991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.57275764409624
      }
    },
    {
      "id": "0dbf3ee4850d3a661f436d3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1310.657429243358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.1106204518505,
        1333.2042380348653
      ],
      "voteCount": 640,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.33477447219926
      }
    },
    {
      "id": "2e73437a2cdd994f96221b41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1380.5876541579235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.7725485979593,
        1392.4027597178874
      ],
      "voteCount": 2379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.339506918851114
      }
    },
    {
      "id": "6fcb74845fc104175f52a7aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1313.9543232172696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.7238168919523,
        1326.1848295425866
      ],
      "voteCount": 3473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.93970805252424
      }
    },
    {
      "id": "d6342fb6106019935b3bf8c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1401.4723642618212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.0993969120573,
        1442.845331611585
      ],
      "voteCount": 196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 445.591767925115
      }
    },
    {
      "id": "b616205c8a5f0fdb258d90ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1396.8879518649533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.416258986901,
        1413.3596447430057
      ],
      "voteCount": 1235,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.62854996838247
      }
    },
    {
      "id": "c8483e0fad171bcd495acb3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1375.7141536543472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.7816543735598,
        1387.6466529351346
      ],
      "voteCount": 2391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.065225929003425
      }
    },
    {
      "id": "3e77cb524a6c68cb1c5e6597",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1342.866128549536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.6556417819738,
        1362.076615317098
      ],
      "voteCount": 921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.06839981171416
      }
    },
    {
      "id": "b634554f36c3a403444cb7cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1321.6152233457321,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.9088152303148,
        1340.3216314611495
      ],
      "voteCount": 882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.09292092250581
      }
    },
    {
      "id": "6d3651bddd11b8437e9a0cd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1369.4029172119713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.4179371427526,
        1403.3878972811897
      ],
      "voteCount": 277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.6615257941208
      }
    },
    {
      "id": "c34bfc5c20d9ee4b6a57c729",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1359.3357658786686,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.5230920795677,
        1381.1484396777691
      ],
      "voteCount": 749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.85730538170995
      }
    },
    {
      "id": "fe01af6495e6bc697f9b574e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1340.0578399730916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.9871377361255,
        1377.1285422100577
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 357.7383042449191
      }
    },
    {
      "id": "c8da13b1f019ddf7b8adad8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1386.466600468363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.8066385578088,
        1424.1265623789168
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 369.2015969204397
      }
    },
    {
      "id": "f4fe5dbf9fab1b0db674870c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1396.6239212993437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.78903515142,
        1410.4588074472676
      ],
      "voteCount": 1760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.825882213005535
      }
    },
    {
      "id": "ff4c7508edc6eae91d0e652d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1319.9039517041224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.425174603793,
        1337.3827288044515
      ],
      "voteCount": 1097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.52907038263965
      }
    },
    {
      "id": "943e4ff3a10935b8c320beff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1342.115457811071,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.2751805141606,
        1357.9557351079816
      ],
      "voteCount": 1302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.31747353149473
      }
    },
    {
      "id": "13e37c11b98441991369f772",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1341.9783105603503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.9129820776966,
        1360.043639043004
      ],
      "voteCount": 1070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.9562909351211
      }
    },
    {
      "id": "2533c5b7fa9554209f9ac1fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1357.0421362766556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.3398618805566,
        1390.7444106727546
      ],
      "voteCount": 276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 295.6801966354832
      }
    },
    {
      "id": "997d62b614a22dd555053ac8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1358.8010551854754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.035046691763,
        1378.567063679188
      ],
      "voteCount": 895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.70487567608912
      }
    },
    {
      "id": "f25bd74bb0dfc2a5fb0e970e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1353.4769426115488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.1279053618168,
        1361.8259798612808
      ],
      "voteCount": 4958,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.14582070277625
      }
    },
    {
      "id": "e3b3151b6de4d700449c9eea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1317.9364295309806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.0342338668802,
        1348.838625195081
      ],
      "voteCount": 318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.58933583200425
      }
    },
    {
      "id": "b669f81651863bc111e16cc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.5v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1355.10765224568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.6972270585682,
        1400.5180774327916
      ],
      "voteCount": 177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 536.8030250814105
      }
    },
    {
      "id": "86bd02e15be87419aed9fa9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1483.151896800328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.3940998079518,
        1497.909693792704
      ],
      "voteCount": 1647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.695277037703654
      }
    },
    {
      "id": "0acc6f264af28fb4cbdd74f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1459.514007768124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.2373868563313,
        1466.7906286799168
      ],
      "voteCount": 7481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.783620849636574
      }
    },
    {
      "id": "baa4585b8d065b7dc93a9902",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1403.3723319853934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.7771834359926,
        1411.9674805347943
      ],
      "voteCount": 5087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.23138631300454
      }
    },
    {
      "id": "ee4861e844fc0275f4ad33eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1437.0863457261166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.9029816185468,
        1442.2697098336864
      ],
      "voteCount": 17208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.994026156653653
      }
    },
    {
      "id": "c14fb37180eb1471e4e5828d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1417.3085914351952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.7476880859979,
        1422.8694947843926
      ],
      "voteCount": 25036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.049974632690903
      }
    },
    {
      "id": "bf62da891eb53818f315ce1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1442.0213227293132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.343576013708,
        1455.6990694449187
      ],
      "voteCount": 1854,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.70044531219263
      }
    },
    {
      "id": "f6723f4f9835372245753866",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1449.5771198783398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.6815963300328,
        1474.472643426647
      ],
      "voteCount": 639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.34159486638066
      }
    },
    {
      "id": "9f3874e2806a62755e14a478",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1429.226842746215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.0238802531312,
        1452.4298052392987
      ],
      "voteCount": 642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.14922288251262
      }
    },
    {
      "id": "125694069d9ac3525b533796",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1448.2408488892745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.6931200716883,
        1454.7885777068607
      ],
      "voteCount": 9616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.160539438218402
      }
    },
    {
      "id": "a782c455b6dbf0f550742aa6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1442.5880173506823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.534666865161,
        1447.6413678362035
      ],
      "voteCount": 19087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.6475660215209915
      }
    },
    {
      "id": "475bb8ca258f76b99909d1e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1413.0088002540942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.3555636040844,
        1420.662036904104
      ],
      "voteCount": 6845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.247340647132278
      }
    },
    {
      "id": "a89a340edc650f104a00d2c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1395.4993175694324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.9201400553886,
        1403.0784950834761
      ],
      "voteCount": 6586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.953676316906648
      }
    },
    {
      "id": "ac1c5b694a66e66e83d1b2ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1436.5040615082432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.3774397354744,
        1448.6306832810121
      ],
      "voteCount": 2397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.28101835365241
      }
    },
    {
      "id": "d3ac85e87c7e9264e998fd6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1447.3317376070818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.2948964303203,
        1455.3685787838433
      ],
      "voteCount": 5858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.814137314849372
      }
    },
    {
      "id": "7c862e4e31b5baab5d1f7b14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1441.5480776264749,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.3150667996074,
        1455.7810884533421
      ],
      "voteCount": 1677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.73480900183625
      }
    },
    {
      "id": "709186fa16c10b7e09f7e26a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1450.6983027705255,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.846864081424,
        1464.549741459627
      ],
      "voteCount": 1901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.94518038937826
      }
    },
    {
      "id": "b91aeb2e23adccf6b210b724",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1453.9769341833403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.0977585829658,
        1459.856109783715
      ],
      "voteCount": 12604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.997807175190472
      }
    },
    {
      "id": "622125d8219a4720b2594507",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1405.651466215875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.599139630531,
        1412.703792801219
      ],
      "voteCount": 7955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.946985139713915
      }
    },
    {
      "id": "1f15e8d0bc9c341435a06d34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1415.9409260328143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.5440345594388,
        1422.3378175061898
      ],
      "voteCount": 10005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.652260620810063
      }
    },
    {
      "id": "069b73403947b0f5786f1695",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1373.7681089127896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.980780852385,
        1407.555436973194
      ],
      "voteCount": 310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 297.17448259802643
      }
    },
    {
      "id": "989e62c9a284a275b12f7181",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1367.5854567411634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.700388380969,
        1393.470525101358
      ],
      "voteCount": 570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.42247731575864
      }
    },
    {
      "id": "270e19829db8ff4a428ff745",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1433.2451163754574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.502519315613,
        1439.987713435302
      ],
      "voteCount": 8751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.834726658142369
      }
    },
    {
      "id": "5d4ac69d695c5538bf83b691",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1421.4884489961291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.7155616868636,
        1434.2613363053947
      ],
      "voteCount": 2107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.469972432431106
      }
    },
    {
      "id": "9c3f144c42a42660cb5b14fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1422.1162704830408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.9024056482224,
        1430.3301353178592
      ],
      "voteCount": 5676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.56300891765812
      }
    },
    {
      "id": "564fd144e40890effdd3cd1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1425.8093551393338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.882420704414,
        1429.7362895742535
      ],
      "voteCount": 35661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.014311951773797
      }
    },
    {
      "id": "d9694472ced96734e07ac311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1410.2555248438573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.2411890282742,
        1421.2698606594406
      ],
      "voteCount": 2754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.580604952708324
      }
    },
    {
      "id": "dd49554f7163f658325c3b33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1414.7173648086616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.8454434921487,
        1435.5892861251743
      ],
      "voteCount": 881,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.40407896497734
      }
    },
    {
      "id": "55b2e60c592b0b70ab0b87d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1420.0519449228232,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.7795411165946,
        1445.3243487290517
      ],
      "voteCount": 536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.2635014345064
      }
    },
    {
      "id": "e7387d396c53122bbfd24642",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1344.8583217365626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.2810206033846,
        1373.4356228697407
      ],
      "voteCount": 420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.59166847160702
      }
    },
    {
      "id": "8da715234d1f1efb5fc98e45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1394.676086066207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.4337342967344,
        1410.9184378356795
      ],
      "voteCount": 1290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.67547026200266
      }
    },
    {
      "id": "30256b042e440a5abfe22139",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1350.7579398148023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.7630732971484,
        1366.752806332456
      ],
      "voteCount": 2009,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.59859362265271
      }
    },
    {
      "id": "b7c9a9551090d1ef4cc81257",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1404.5224301180506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.6791282116048,
        1426.365732024496
      ],
      "voteCount": 718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.2053762507642
      }
    },
    {
      "id": "14c7aaed0a70fd7731ec69f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1383.7107869197134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.4391624435716,
        1398.9824113958553
      ],
      "voteCount": 1499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.711965174249215
      }
    },
    {
      "id": "b8965dbdd65d01927e903970",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1367.4724953850948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.026727609943,
        1392.9182631602466
      ],
      "voteCount": 540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.5523984218986
      }
    },
    {
      "id": "11768563181646d69fb366ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1350.9621211823548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.6998337163882,
        1377.2244086483213
      ],
      "voteCount": 513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.54318271735045
      }
    },
    {
      "id": "06cc1c15853688bebc420d42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1402.0732242972088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.83515451611,
        1443.3112940783078
      ],
      "voteCount": 203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 442.69077937519273
      }
    },
    {
      "id": "716bec382def01beeae8066e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1403.6920338325806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.0802728938434,
        1430.303794771318
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.35335462805804
      }
    },
    {
      "id": "30479acc4d99e4b0c4337a9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1408.809492329939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.485367557298,
        1428.13361710258
      ],
      "voteCount": 928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.20833039181804
      }
    },
    {
      "id": "531ba0b982a5fa4dafb92401",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1354.2125580404868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.5090508106703,
        1377.916065270303
      ],
      "voteCount": 608,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.26116827472222
      }
    },
    {
      "id": "b033ea199b5e360de27b946d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1368.9049170656947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.9707650910268,
        1390.8390690403623
      ],
      "voteCount": 733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.24070810184728
      }
    },
    {
      "id": "3d08a349084c2ddc831fd044",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1379.9110674092476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.701335445725,
        1403.12079937277
      ],
      "voteCount": 663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.2310119573867
      }
    },
    {
      "id": "facfdc6655f79b675d572fe7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1366.160796366464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.6856286985203,
        1392.6359640344078
      ],
      "voteCount": 480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.4657078893481
      }
    },
    {
      "id": "17c799b94551c74847598bdb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1377.5152988566854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.2619426524154,
        1388.7686550609553
      ],
      "voteCount": 2808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.966128695165324
      }
    },
    {
      "id": "49bd7ec24667fb8ff3233f46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.6v",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1346.6211681152845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.932688870163,
        1380.309647360406
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 295.4381881526748
      }
    },
    {
      "id": "d851400139d87d76d0775751",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1433.6362893131504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.1782718784243,
        1461.0943067478768
      ],
      "voteCount": 443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.26468918115307
      }
    },
    {
      "id": "84da138946d1f5f259086961",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1423.4355435224636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.213629047149,
        1434.657457997778
      ],
      "voteCount": 2687,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.78217218231619
      }
    },
    {
      "id": "afcabff9c1d6a908ce14b453",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1312.3447017907172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.307155740897,
        1326.382247840537
      ],
      "voteCount": 1811,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.29631952301103
      }
    },
    {
      "id": "03752415f46f7973328c848d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1394.7513166806425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.6460777536731,
        1402.8565556076123
      ],
      "voteCount": 5290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.10154947109215
      }
    },
    {
      "id": "05a884e7d0122caf51b07838",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1331.242914841462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.6147892934466,
        1339.8710403894775
      ],
      "voteCount": 8140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.37923948872715
      }
    },
    {
      "id": "9f000fcc5cdc3f546f24578c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1389.6603859718662,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.3235447099082,
        1409.9972272338243
      ],
      "voteCount": 795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.66407550331239
      }
    },
    {
      "id": "9a4556105bc0373fbcd29506",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1369.7420948347865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.9131875678795,
        1409.5710021016935
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 412.9529764916852
      }
    },
    {
      "id": "69899cb95f544f89a228be2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1339.6661971432497,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.195088530726,
        1382.1373057557735
      ],
      "voteCount": 209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 469.55991225511855
      }
    },
    {
      "id": "c5c9285f7e041b23f517722b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1403.8642722172963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.3456211907783,
        1414.3829232438143
      ],
      "voteCount": 3074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.802083943119058
      }
    },
    {
      "id": "ad2567518d856b4a14bc419e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1386.7353725808118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.2354291259894,
        1394.2353160356342
      ],
      "voteCount": 6518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.642653859131988
      }
    },
    {
      "id": "a28026252ab7e13bfefd2018",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1369.625909457658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.0559179158577,
        1382.195900999458
      ],
      "voteCount": 2166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.1314281204185
      }
    },
    {
      "id": "c074e07cf321b280c588358a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1320.4375102678077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.327062383362,
        1333.5479581522532
      ],
      "voteCount": 2057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.74441917867666
      }
    },
    {
      "id": "23e8a22e307499950257fe28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1381.2261807479174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.282235770056,
        1401.1701257257787
      ],
      "voteCount": 825,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.54424187426021
      }
    },
    {
      "id": "37835bc27152e7f56f179dad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1383.8218918933453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.0514965252992,
        1397.5922872613912
      ],
      "voteCount": 1791,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.362442093818544
      }
    },
    {
      "id": "46c6cb7a2249ece1f4154f23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1388.0830952260978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.44126314692,
        1413.724927305276
      ],
      "voteCount": 481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.15985959156032
      }
    },
    {
      "id": "a3299b61919191b0e68a131d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1371.6248892087817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.4681433365718,
        1392.7816350809917
      ],
      "voteCount": 804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.52029002367142
      }
    },
    {
      "id": "927b4f3c9c37474e0082a610",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1423.9786119480864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.973187325932,
        1432.9840365702407
      ],
      "voteCount": 4258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.11116542195572
      }
    },
    {
      "id": "d87a13ac3d3cab4a4a7be0eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1333.4512114732493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.662428799664,
        1345.2399941468348
      ],
      "voteCount": 2554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.17776563850219
      }
    },
    {
      "id": "a8e0fb92d2c86f24497baca6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1350.7643432259933,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.3549754691803,
        1361.1737109828066
      ],
      "voteCount": 3171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.206715769766536
      }
    },
    {
      "id": "d9ed15038e7e5a74f2ffc9f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1297.692038798601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.1227615011676,
        1340.2613160960348
      ],
      "voteCount": 216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 471.73312384963907
      }
    },
    {
      "id": "e648d0859e25305537d597d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1373.0175248618734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4994937972288,
        1383.535555926518
      ],
      "voteCount": 3169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.79868889414226
      }
    },
    {
      "id": "61c73fd42fce16f2e7299829",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1365.9045038091606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.585167378403,
        1387.2238402399182
      ],
      "voteCount": 718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.31809920734808
      }
    },
    {
      "id": "a09302d548b780f65183fb28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1363.1188461628371,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.2309042573702,
        1376.0067880683043
      ],
      "voteCount": 2121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.238533669529176
      }
    },
    {
      "id": "94e781abb142ba36ca79c4ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1367.855226412471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.0441569533764,
        1373.666295871566
      ],
      "voteCount": 11736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.790548027356794
      }
    },
    {
      "id": "a71d27c6cd20abe18a7d71e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1349.8065984780294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.304254740958,
        1365.3089422151008
      ],
      "voteCount": 1391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.56025967210398
      }
    },
    {
      "id": "e01bcc4ede8e4fd40027bbee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7-flash",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1369.271822879637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.8272178495743,
        1402.7164279096996
      ],
      "voteCount": 337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 291.17625824628277
      }
    },
    {
      "id": "62f56d85d1285e2535cdb760",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1487.5673523967328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.4571764651052,
        1509.6775283283603
      ],
      "voteCount": 688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.25891452851411
      }
    },
    {
      "id": "0380b15f12e213883179a56b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1485.8352400940134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.7567693041412,
        1497.9137108838856
      ],
      "voteCount": 2411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.9776182516611
      }
    },
    {
      "id": "8dcc9a0a652ad8dd05ffb3cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1405.8477958057113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.4462656817313,
        1419.249325929691
      ],
      "voteCount": 1923,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.75333461767716
      }
    },
    {
      "id": "929f4d0be3a070243dbd93a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1462.8345711781292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.4634254022972,
        1471.205716953961
      ],
      "voteCount": 5588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.242049406523744
      }
    },
    {
      "id": "06fceec9e033e1b6ffcca60a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1442.2137333725525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.5888277890783,
        1450.8386389560267
      ],
      "voteCount": 8400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.364777756592296
      }
    },
    {
      "id": "3de620bb2645edd2076fab14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1445.8855548195622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.043936718432,
        1467.7271729206927
      ],
      "voteCount": 717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.186228082337
      }
    },
    {
      "id": "56d3b2b63f3d553221d43fde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1445.4000079989921,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.9134981949956,
        1481.886517802989
      ],
      "voteCount": 271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 346.55204176745394
      }
    },
    {
      "id": "b1f55de564bd26cb59350e76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1420.4352807560872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.0274372739818,
        1459.8431242381923
      ],
      "voteCount": 219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 404.26780564303795
      }
    },
    {
      "id": "3d619e201f82f718428dae94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1472.9435702336905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.26606943599,
        1483.6210710313912
      ],
      "voteCount": 3099,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.678574886896115
      }
    },
    {
      "id": "3dd7aa123cb37fb64172f3f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1463.0477745025394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.2159078790007,
        1470.8796411260778
      ],
      "voteCount": 6608,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.967406569209038
      }
    },
    {
      "id": "6276a6029e96ba6f2a2cd869",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1442.022006470618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.6441043397344,
        1454.3999086015017
      ],
      "voteCount": 2246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.883926475111714
      }
    },
    {
      "id": "88746422016df43a27175f31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1406.7574954750223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.8501169733447,
        1418.6648739767
      ],
      "voteCount": 2394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.90932778412406
      }
    },
    {
      "id": "9aedb1b10dfae6409cb26600",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1455.4243898440304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.6836156925704,
        1474.1651639954905
      ],
      "voteCount": 958,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.42792678240211
      }
    },
    {
      "id": "2b2dd5fd550e37561f551f82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1470.9459363513654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.1997415628996,
        1483.6921311398312
      ],
      "voteCount": 2085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.292652132648826
      }
    },
    {
      "id": "bcd0a34400778110f48a166d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1421.6821815657809,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.0468477615552,
        1445.3175153700067
      ],
      "voteCount": 541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.42105749717112
      }
    },
    {
      "id": "0262c1020264fc351dea9300",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1481.9934782936434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.7258129458796,
        1502.2611436414072
      ],
      "voteCount": 816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.9328809243153
      }
    },
    {
      "id": "9d701d99be0acdbb02f9edf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1474.7334485715119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.3253713590354,
        1484.1415257839885
      ],
      "voteCount": 4107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.041224953161983
      }
    },
    {
      "id": "3111296475376e1e4be177f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1416.9582724371687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.8044945876402,
        1428.1120502866972
      ],
      "voteCount": 2779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.38529062096102
      }
    },
    {
      "id": "b50521aca8d00ec13e6f60ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1428.2139468610583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.7853637805106,
        1438.6425299416062
      ],
      "voteCount": 3214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.310949080598622
      }
    },
    {
      "id": "1660ff68e80f48bd895f5a9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1408.6164644819935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.4276449011259,
        1455.805284062861
      ],
      "voteCount": 159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 579.6716292882988
      }
    },
    {
      "id": "16941b12437ee59d833b7128",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1452.6415325293224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.0282323455613,
        1463.2548327130835
      ],
      "voteCount": 3103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.322751081910564
      }
    },
    {
      "id": "d6ba51502aa5069a0a1a7f97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1429.0359674855695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.1511739081861,
        1449.9207610629526
      ],
      "voteCount": 711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.54400063335686
      }
    },
    {
      "id": "96087b0f5dc5c813a1325ed5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1459.8845135436766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.2904203668484,
        1473.4786067205052
      ],
      "voteCount": 1920,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.106560014328444
      }
    },
    {
      "id": "29964b8fcf086da2ccf69c17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1442.591607038939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.4895860090191,
        1448.6936280688587
      ],
      "voteCount": 12133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.692843887587296
      }
    },
    {
      "id": "b647a01eccfc3e4adb73c3ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1432.9947508969321,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.54042929347,
        1448.4490725003943
      ],
      "voteCount": 1357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.173269940215164
      }
    },
    {
      "id": "8adc3db5239420221258390a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-4.7",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1424.18072050183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.0450953822979,
        1457.3163456213622
      ],
      "voteCount": 315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 285.8210131389036
      }
    },
    {
      "id": "8b2f23240d90e37f652b532d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1519.4247123291134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.7102430243633,
        1541.1391816338637
      ],
      "voteCount": 843,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.74456116693274
      }
    },
    {
      "id": "f5fdf4b01d40fabfab2bcf9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1527.206202577125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1516.9253874422739,
        1537.4870177119763
      ],
      "voteCount": 3756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.514328480523794
      }
    },
    {
      "id": "3ddf5908adeee2b745575951",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1456.635916993618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.308684701939,
        1469.9631492852968
      ],
      "voteCount": 2209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.2363723904962
      }
    },
    {
      "id": "bc7c7cfb5708823d44e22e80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1487.3457748879832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.5955497114646,
        1495.0960000645016
      ],
      "voteCount": 6673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.636244742013796
      }
    },
    {
      "id": "74248e75a9d559ab9e237b5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1484.544848242308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.5516654625028,
        1492.5380310221135
      ],
      "voteCount": 10241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.631955185148087
      }
    },
    {
      "id": "33a5b5248595539e72895e9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1504.1177268056656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.7759202938132,
        1521.459533317518
      ],
      "voteCount": 1225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.28751188856559
      }
    },
    {
      "id": "da270e31809a61c67a925393",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1489.2443154103535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.2741434202874,
        1518.2144874004196
      ],
      "voteCount": 454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.47712140315434
      }
    },
    {
      "id": "3462926a9767a3d3f5ef85fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1467.6943480849566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.2240800786758,
        1507.1646160912376
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 405.54959175799104
      }
    },
    {
      "id": "146373f9b7662eb0c86ddfc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1505.7931216359955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.3072461430916,
        1515.2789971288994
      ],
      "voteCount": 4396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.42387047913637
      }
    },
    {
      "id": "18b6f8241c129a425a88142a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1498.5520241632962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.4206245783892,
        1505.6834237482033
      ],
      "voteCount": 8788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.238944477458329
      }
    },
    {
      "id": "473aac951f0dbeb06547442c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1456.4016344744568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.9369495845526,
        1467.866319364361
      ],
      "voteCount": 2800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.21590748721044
      }
    },
    {
      "id": "a834060f38dc6a88300b1b37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1451.831992645412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.768402450995,
        1463.895582839829
      ],
      "voteCount": 2625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.88409954959247
      }
    },
    {
      "id": "8349053ae5144930f3f19b79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1476.4352452775104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.2565876618528,
        1495.6139028931677
      ],
      "voteCount": 997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.75031911240268
      }
    },
    {
      "id": "e5faf061c35a8c0810737a45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1498.07361201727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.4595775797793,
        1510.6876464547609
      ],
      "voteCount": 2300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.42016671714623
      }
    },
    {
      "id": "065a7808cfc4871c64bf77a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1481.738633433045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.703594020683,
        1502.773672845407
      ],
      "voteCount": 802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.18355492866385
      }
    },
    {
      "id": "3aa20f82c540b827ef9a9ba7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1477.5461030956185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.2395816112275,
        1496.8526245800092
      ],
      "voteCount": 997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.03130743437046
      }
    },
    {
      "id": "f5999b2416f49d5885d9b408",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1512.4852465490017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.0291298030697,
        1520.9413632949336
      ],
      "voteCount": 5541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.614259258911012
      }
    },
    {
      "id": "3571bcce7809baf55616459d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1460.8148354061339,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.9714301450797,
        1471.6582406671878
      ],
      "voteCount": 3249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.60801719962431
      }
    },
    {
      "id": "fc8bb720c293ae22200e2496",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1468.0283022738524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.7968423732796,
        1477.2597621744255
      ],
      "voteCount": 4465,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.18424194392074
      }
    },
    {
      "id": "ac9b72f6b15258edc4d1ff58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1418.2852322206961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.5562734887653,
        1453.0141909526267
      ],
      "voteCount": 284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 313.96941393900283
      }
    },
    {
      "id": "fdb211676e321959580170a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1491.2854087962887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.4759799299259,
        1500.0948376626518
      ],
      "voteCount": 5378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.20223060401995
      }
    },
    {
      "id": "d8ff565063a410218e56ef82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1480.9311342976966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.7914018526096,
        1501.0708667427837
      ],
      "voteCount": 860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.5871849451189
      }
    },
    {
      "id": "ff22f670460139f8f67a628b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1483.5961297846861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.6446898435809,
        1496.5475697257916
      ],
      "voteCount": 2258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.66565005055828
      }
    },
    {
      "id": "e584e21172c3e26378ee7734",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1473.8519443543803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.0284291814085,
        1479.6754595273524
      ],
      "voteCount": 13957,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.828242225880897
      }
    },
    {
      "id": "785fcd4f9d106d007d006203",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1465.2252316698725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.2089181108213,
        1480.2415452289238
      ],
      "voteCount": 1591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.698969175205804
      }
    },
    {
      "id": "ddf8d5a9b420771b1709f008",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5.1",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1463.0985853250254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.2934484251862,
        1490.9037222248646
      ],
      "voteCount": 464,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.25834327676196
      }
    },
    {
      "id": "e627552d6c4290fd4a260a56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1524.4751643702352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1506.2292854016757,
        1542.7210433387947
      ],
      "voteCount": 1146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.66293584663961
      }
    },
    {
      "id": "71043669cb0cc86872c01b81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1494.5347151239573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.2455953745928,
        1502.8238348733216
      ],
      "voteCount": 5384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.886305548600717
      }
    },
    {
      "id": "c9e0f74e3e8fcc98219c37b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1449.0008687726192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.608311987592,
        1459.3934255576464
      ],
      "voteCount": 3516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.115682497541
      }
    },
    {
      "id": "f0fb763516478a0773e8053e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1470.7298276705951,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.4650350870115,
        1476.9946202541785
      ],
      "voteCount": 10197,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.216854571990671
      }
    },
    {
      "id": "d04a697c0ea810c40944e895",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1461.1074395460666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.5367894271099,
        1467.6780896650237
      ],
      "voteCount": 15320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.23881447151561
      }
    },
    {
      "id": "9eb92f6d844cdd9ce0798a32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1488.4203515149513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.3201802070769,
        1502.5205228228256
      ],
      "voteCount": 1732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.755033749256356
      }
    },
    {
      "id": "861315d8e1f029e4abc6452a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1488.7500144932142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.6662052771946,
        1513.833823709234
      ],
      "voteCount": 641,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.79128715272287
      }
    },
    {
      "id": "4066955291866401dabdc900",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1443.4644621776774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.8588689612277,
        1473.0700553941274
      ],
      "voteCount": 401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 228.16622294015133
      }
    },
    {
      "id": "ca760901e0be004d9cfe4542",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1485.5010777621485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.7915097738135,
        1493.2106457504835
      ],
      "voteCount": 6322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.472621558916323
      }
    },
    {
      "id": "6166f66bdb348136eba14899",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1478.080313770655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.2950978611912,
        1483.865529680119
      ],
      "voteCount": 13017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.712503421569183
      }
    },
    {
      "id": "5f6e274b62476b3f5efa629d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1449.129684807052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.998550965031,
        1458.2608186490727
      ],
      "voteCount": 4338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.704672399906908
      }
    },
    {
      "id": "993c7c8d27c17426aaad9cb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1435.5400822478086,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.1209100546964,
        1444.9592544409209
      ],
      "voteCount": 4111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.09560220340116
      }
    },
    {
      "id": "c2924275fb521159746fda95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1463.7898619331283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.0446299989255,
        1478.535093867331
      ],
      "voteCount": 1660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.59877534601439
      }
    },
    {
      "id": "05c789dc7bc39dafbad3f19f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1482.036601899884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.9300248699728,
        1492.1431789297953
      ],
      "voteCount": 3439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.589611923282884
      }
    },
    {
      "id": "e08b9221348e379a47309214",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1462.0717375355675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.9181825901626,
        1479.2252924809727
      ],
      "voteCount": 1159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.597058825652
      }
    },
    {
      "id": "3024ca42f8dec9b7875ef218",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1481.0004310102981,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.7366293618015,
        1496.264232658795
      ],
      "voteCount": 1554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.64978218940073
      }
    },
    {
      "id": "a4242499c67aadce0684598c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1485.3246469235837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.4219786908297,
        1492.2273151563377
      ],
      "voteCount": 8067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.403316280470177
      }
    },
    {
      "id": "9f4f90b5830149810d6036cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1446.170554045351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.6388434210335,
        1454.7022646696685
      ],
      "voteCount": 5042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.948553030158042
      }
    },
    {
      "id": "9aca2f22fc16cc8874f6942d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1447.278557092762,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.8073675049047,
        1454.7497466806192
      ],
      "voteCount": 6761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.530592793812803
      }
    },
    {
      "id": "48c8ed98042c5e231b675c7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1392.5449498790056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.7775016947985,
        1438.3123980632126
      ],
      "voteCount": 184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 545.2770447544673
      }
    },
    {
      "id": "6de0a27cbfff8c81d6b98b8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1424.9381610753226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.8119380495034,
        1454.064384101142
      ],
      "voteCount": 416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.83716300165224
      }
    },
    {
      "id": "3891505d858153ce6458e6b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1470.0833687556096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.7001825424716,
        1477.4665549687475
      ],
      "voteCount": 7224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.190296239598974
      }
    },
    {
      "id": "0bb385f2f22913f8c48e1e57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1440.1009580899315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.4827124225303,
        1455.7192037573325
      ],
      "voteCount": 1350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.49920931424134
      }
    },
    {
      "id": "d823fe45fbff4b9c06ea93ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1468.5538096437278,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.4572940155088,
        1478.650325271947
      ],
      "voteCount": 3501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.536696757418603
      }
    },
    {
      "id": "52d50df1d776e22f1175ec15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1457.0610622815716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.4055639434878,
        1461.7165606196552
      ],
      "voteCount": 21930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.642040117452989
      }
    },
    {
      "id": "56aa5a1411622b8cfe942531",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1447.767172737273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.6442406842527,
        1459.8901047902934
      ],
      "voteCount": 2289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.257726666348155
      }
    },
    {
      "id": "66a265f8e73e752abedac296",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "glm-5",
      "organization": "zai",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1439.5772058945995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.9479210050356,
        1461.2064907841634
      ],
      "voteCount": 781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.7834126748198
      }
    },
    {
      "id": "b4db75f34416c493eda4f269",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1207.7127384335472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.3358639887956,
        1218.0896128782988
      ],
      "voteCount": 7558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.030893540252027
      }
    },
    {
      "id": "26c699956805926db1e766bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1273.2881121024434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.1477386475258,
        1281.4284855573608
      ],
      "voteCount": 11130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.25013414917992
      }
    },
    {
      "id": "f0bfd317a2680ad06d4506a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1188.2599533477785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.4239676090829,
        1197.0959390864741
      ],
      "voteCount": 9694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.324217339995954
      }
    },
    {
      "id": "af2297a65b5b436e1b14a94e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1236.0913416833387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.5131083731733,
        1241.669574993504
      ],
      "voteCount": 39956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.100226584497456
      }
    },
    {
      "id": "8225c9a4e675f66f36b68fd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1110.1272678523223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.1794352518841,
        1117.075100452761
      ],
      "voteCount": 44422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.566157831412937
      }
    },
    {
      "id": "640388bc7de17aff050a0a16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1191.3242700241944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.4424770486544,
        1204.2060629997343
      ],
      "voteCount": 3207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.19728468016872
      }
    },
    {
      "id": "3f04cdc48f2c419c2b5c9f8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1235.000952115518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.0737745995311,
        1257.9281296315053
      ],
      "voteCount": 1284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.83746029447258
      }
    },
    {
      "id": "93f540eebb48f3e086c5ab58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1197.1754712546744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.2115741255066,
        1214.1393683838426
      ],
      "voteCount": 1885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.91263586081993
      }
    },
    {
      "id": "b1401948472ff3528e6b4d55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1238.9629444851732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.2455724443012,
        1246.6803165260453
      ],
      "voteCount": 12416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.503961905407346
      }
    },
    {
      "id": "23f04812e2497d118a542e9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1227.1454383511473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.4579435422397,
        1233.8329331600548
      ],
      "voteCount": 18544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.64208414216092
      }
    },
    {
      "id": "8eeffa0a1a9d120f0e269cdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1201.0422166193173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.332417542816,
        1210.7520156958187
      ],
      "voteCount": 6898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.54281107951351
      }
    },
    {
      "id": "d8def2333ad792bd05c36b44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1194.6339058994056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.0963998700495,
        1203.1714119287617
      ],
      "voteCount": 9653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.97430445138115
      }
    },
    {
      "id": "a2d53f9f841dde9b21eeb9d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1251.5322357314049,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.8589058407456,
        1264.205565622064
      ],
      "voteCount": 3573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.810493881189544
      }
    },
    {
      "id": "36355b632b4551b4a68228bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1223.8556600959068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.3470564078768,
        1232.364263783937
      ],
      "voteCount": 11407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.84605304889847
      }
    },
    {
      "id": "2c0e48fad842e571b81a12f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1195.1770937492552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.2691493897546,
        1204.0850381087557
      ],
      "voteCount": 7493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.656598551697673
      }
    },
    {
      "id": "b0bd44dc0bb921036cb8191a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1229.9584153175283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.2086413842933,
        1242.7081892507633
      ],
      "voteCount": 3837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.316407108907924
      }
    },
    {
      "id": "0d0d761bef5641fbe9e928ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1244.7669006237768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.7136151025215,
        1251.820186145032
      ],
      "voteCount": 18975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.950506296292943
      }
    },
    {
      "id": "bec44c2ba3ecc07ba974aff8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1223.0409307228092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.673718778058,
        1230.4081426675605
      ],
      "voteCount": 16149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.12895839114518
      }
    },
    {
      "id": "f6eda7ae78e895442224badc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1211.8709557371767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.4888229308222,
        1218.2530885435312
      ],
      "voteCount": 23523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.603164333956622
      }
    },
    {
      "id": "f2704b37da70181d27cee4bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1141.9817923482076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.310668520503,
        1163.652916175912
      ],
      "voteCount": 965,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.25501557526468
      }
    },
    {
      "id": "a10d5bd19acb3bce5424020c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1151.798790716034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.5300547894544,
        1174.0675266426138
      ],
      "voteCount": 1184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.0906978089469
      }
    },
    {
      "id": "a5efd681c43f91d6e9f4441c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1218.4868566304199,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.2667121147683,
        1227.7070011460714
      ],
      "voteCount": 6707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.129890975673227
      }
    },
    {
      "id": "c118024d662bd539a6c535b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1199.224916658281,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.7710541785445,
        1207.678779138017
      ],
      "voteCount": 8626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.604336051005486
      }
    },
    {
      "id": "542a159b9b2bb11bf69fff93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1199.3813668834894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.7072994317837,
        1208.055434335195
      ],
      "voteCount": 10274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.586164961972656
      }
    },
    {
      "id": "f379adaaa37efa7a0480c2d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1223.5058918152808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.8030123314593,
        1228.2087712991024
      ],
      "voteCount": 66207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.757467793278014
      }
    },
    {
      "id": "f3de074ba88c83b410616639",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1216.6421642932405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.2893629565356,
        1226.994965629945
      ],
      "voteCount": 5447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.90098775493507
      }
    },
    {
      "id": "37f64da5adb72696f2cec8dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-0125",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1225.4838365807868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.4417056363532,
        1250.5259675252203
      ],
      "voteCount": 895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.2474410137866
      }
    },
    {
      "id": "b1bb2a730b353122b1cd47e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1159.6128230813376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.9588419150327,
        1184.2668042476425
      ],
      "voteCount": 708,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.2260322755939
      }
    },
    {
      "id": "1aeb4ebdc1e342de69bc9238",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1260.675056609854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.0986325111712,
        1276.2514807085363
      ],
      "voteCount": 2121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.15959613961902
      }
    },
    {
      "id": "2993108172e66c9375b1f2bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1153.0340716676728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.9320238412406,
        1168.136119494105
      ],
      "voteCount": 2828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.37115538586895
      }
    },
    {
      "id": "ab5f913ae114602e040dde54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1219.1999830094467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.5958191095015,
        1228.804146909392
      ],
      "voteCount": 12878,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.01170193992761
      }
    },
    {
      "id": "7d8d609029cfbdb4942db25f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1078.987508680655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1066.614070332567,
        1091.3609470287429
      ],
      "voteCount": 11535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.85516536820925
      }
    },
    {
      "id": "870503e0880288444712db16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1208.5316475728637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.4639204659043,
        1236.599374679823
      ],
      "voteCount": 437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.0776389185373
      }
    },
    {
      "id": "ddad5235b61b038b179aecb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1192.3692396467163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.141885457436,
        1231.5965938359968
      ],
      "voteCount": 310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 400.5731646534241
      }
    },
    {
      "id": "4b65f6ffe467ed9c945ecaf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1172.3276512728316,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.699596126084,
        1206.9557064195792
      ],
      "voteCount": 325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 312.1476135020822
      }
    },
    {
      "id": "1506c246dfed7f0295d249e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1239.3086761721975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.5365006010088,
        1253.0808517433861
      ],
      "voteCount": 3150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.375205831146886
      }
    },
    {
      "id": "a67fcb0d13f950e30e427f36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1226.2893160673575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.547155236802,
        1239.031476897913
      ],
      "voteCount": 3846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.26588653172324
      }
    },
    {
      "id": "0dfca87e192ceeef5b84d492",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1153.1511826868891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.9944615587897,
        1172.307903814988
      ],
      "voteCount": 1382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.53140655909732
      }
    },
    {
      "id": "557c71032680833a79c32890",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1160.9637757451574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.891812172475,
        1176.0357393178397
      ],
      "voteCount": 2646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.13484864461378
      }
    },
    {
      "id": "6710da0d55f20d5c9095f160",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1206.5050807177852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.8393977492801,
        1229.1707636862902
      ],
      "voteCount": 944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.73387778134418
      }
    },
    {
      "id": "a79059f7476c8b10ba3ef8d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1200.7190409798059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.6850811899108,
        1215.7530007697012
      ],
      "voteCount": 3046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.837008936970626
      }
    },
    {
      "id": "02f5e16074089603b20bf356",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1201.664013313305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.2556647491733,
        1218.0723618774368
      ],
      "voteCount": 1746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.08636957180609
      }
    },
    {
      "id": "9c2d84cdbaa6590e8420b9a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1181.26305710889,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.3130880489007,
        1203.2130261688797
      ],
      "voteCount": 906,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.42139958367241
      }
    },
    {
      "id": "a608b3543b5c3203c592c832",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1227.5672219096373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.4470545005001,
        1240.6873893187749
      ],
      "voteCount": 4128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.81078696365822
      }
    },
    {
      "id": "df73887fe44a0a77d5378b19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1189.161961007013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.8537830366558,
        1202.47013897737
      ],
      "voteCount": 3932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.10425600207146
      }
    },
    {
      "id": "79c52343dcf2787b5e9ea987",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1193.7983345914333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.70991835521,
        1205.8867508276567
      ],
      "voteCount": 5238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.04018575260526
      }
    },
    {
      "id": "1e449220b0330b1bad621fef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1184.255027703706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.7964674717364,
        1204.7135879356756
      ],
      "voteCount": 933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.95670272719423
      }
    },
    {
      "id": "cc346503e51373025f9f223b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1202.2950896398302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.2089345701486,
        1217.381244709512
      ],
      "voteCount": 2134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.246261748383446
      }
    },
    {
      "id": "4c2fae5f64400d370d996dbf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1169.5559907360398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.7107359216975,
        1185.401245550382
      ],
      "voteCount": 2374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.35852962392885
      }
    },
    {
      "id": "3dfd097944154b94ec8e9c16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1201.9166997630944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.1674786834692,
        1210.6659208427197
      ],
      "voteCount": 16619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.927031128848217
      }
    },
    {
      "id": "d81d7df2a033cfdf085b0291",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1176.881590246961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.2191696222426,
        1205.5440108716793
      ],
      "voteCount": 400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 213.8599928867217
      }
    },
    {
      "id": "e1a6c468ac8bbf54935ad432",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-3.5-turbo-1106",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1207.5999593991733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.5314530101111,
        1247.6684657882356
      ],
      "voteCount": 260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 417.936330750571
      }
    },
    {
      "id": "849f327e3bcfec740a5f37cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1311.2882085650576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.569518025774,
        1321.0068991043413
      ],
      "voteCount": 11382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.587780373835606
      }
    },
    {
      "id": "40ee3bd7f13289782ed2f7f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1331.0954348049593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.510911559389,
        1338.6799580505294
      ],
      "voteCount": 15289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.974777954850678
      }
    },
    {
      "id": "1c3a04719eed54fe7378fe89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1279.839166185664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.7038945277995,
        1287.9744378435282
      ],
      "voteCount": 13940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.228518653049584
      }
    },
    {
      "id": "6e61793fee4db4bbafa21e1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1324.068666600235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.999858373751,
        1329.137474826719
      ],
      "voteCount": 54967,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.688296825795346
      }
    },
    {
      "id": "732a61ee8109c93f6b4c39eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1244.494692464797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.2588556379706,
        1250.7305292916235
      ],
      "voteCount": 63519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.122628601750707
      }
    },
    {
      "id": "19e406c258c2b912909cf6bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1277.3057264889756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.3299595060048,
        1289.2814934719463
      ],
      "voteCount": 4454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.33451314323889
      }
    },
    {
      "id": "5af5266eaddbf856646e74bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1341.2442303708235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.4270268192254,
        1363.0614339224219
      ],
      "voteCount": 1516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.9087526456584
      }
    },
    {
      "id": "2e328db2776a5e05c22e1bcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1294.7574722948825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.9902931203503,
        1309.524651469415
      ],
      "voteCount": 2668,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.76738732639484
      }
    },
    {
      "id": "ffb4409f2420e9faebcd1401",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1318.5386805418402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.283443976622,
        1325.7939171070584
      ],
      "voteCount": 16792,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.702725988812343
      }
    },
    {
      "id": "ffc4e120be56b42402e336d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1306.1613533884615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.9778003934648,
        1312.3449063834582
      ],
      "voteCount": 25575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.953595606948342
      }
    },
    {
      "id": "a33716687914307c680f3c3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1284.3731576110922,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.4851786514455,
        1293.2611365707387
      ],
      "voteCount": 9697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.564106938115337
      }
    },
    {
      "id": "2f69036d92a8bc912694aba8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1286.9329063815728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.041853638707,
        1294.8239591244387
      ],
      "voteCount": 13994,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.20965271194542
      }
    },
    {
      "id": "5a548d16015cd49f0414d303",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1327.315458278637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.649170589898,
        1338.9817459673757
      ],
      "voteCount": 5037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.42983923274909
      }
    },
    {
      "id": "51036f554d617f3a7a4d2905",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1316.9528014875832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.2171333599829,
        1324.6884696151837
      ],
      "voteCount": 16044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.577561591447841
      }
    },
    {
      "id": "c415d6ca0223b273dbd26a9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1298.4639594120638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.3506568674943,
        1306.5772619566333
      ],
      "voteCount": 10830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.13559385958068
      }
    },
    {
      "id": "1b1c714f5e63236e1a050022",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1313.4623034661768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.5778390288262,
        1325.346767903527
      ],
      "voteCount": 5155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.76741091217109
      }
    },
    {
      "id": "bc897765a0fc66ad7f3fa02d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1320.0707348676171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.6481399497902,
        1326.4933297854438
      ],
      "voteCount": 25603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.738036616787312
      }
    },
    {
      "id": "8a0640464fabf353933818dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1304.3210383016215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.6499712440223,
        1310.9921053592207
      ],
      "voteCount": 23492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.584957112450109
      }
    },
    {
      "id": "57b745d16db071e70eac78b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1288.806370336314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.0459048189955,
        1294.5668358536327
      ],
      "voteCount": 33252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.638114977950178
      }
    },
    {
      "id": "4fd13de16b3ee27707228e9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1251.9019053599343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.93832126389,
        1269.8654894559788
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.0020337683469
      }
    },
    {
      "id": "a1d318db107db4470dd1e52e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1244.6150781114013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.9777591173438,
        1265.2523971054588
      ],
      "voteCount": 1393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.86906176584496
      }
    },
    {
      "id": "76a7389243e9a50c023b3edd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1306.1390008802118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.5413690639355,
        1314.7366326964884
      ],
      "voteCount": 9653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.24250038814482
      }
    },
    {
      "id": "f3ac16fa2bf27a67540b6c12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1299.1611126550388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.3323758294423,
        1306.9898494806348
      ],
      "voteCount": 12374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.954647217426915
      }
    },
    {
      "id": "4f57b6e6b6f7e22433a8a1e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1291.2073274189236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.3900121752788,
        1299.0246426625683
      ],
      "voteCount": 14381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.908127737649083
      }
    },
    {
      "id": "83211944cb8c6110a9833531",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1312.5737967321675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.494858900126,
        1316.652734564209
      ],
      "voteCount": 93439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.331097797542311
      }
    },
    {
      "id": "dd08020d8e53ceb6b91ab005",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1292.5879703497683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.64730965399,
        1301.5286310455467
      ],
      "voteCount": 8356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.808608762488355
      }
    },
    {
      "id": "c11f5fae00d5b86d4cd21c5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0125-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1300.6866724011206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.3180808377022,
        1323.0552639645393
      ],
      "voteCount": 1219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.2510092873089
      }
    },
    {
      "id": "8c638a7a7931a6b052893e46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1285.3724372892661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.6002797008184,
        1297.1445948777136
      ],
      "voteCount": 5849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.07579848069375
      }
    },
    {
      "id": "e76c1a80a6d619ee2fcb1d1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1327.963354971941,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.556148289085,
        1337.3705616547968
      ],
      "voteCount": 8306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.036961140189703
      }
    },
    {
      "id": "0a90de239e9921401a3c04af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1253.7424535692064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.768094386163,
        1263.7168127522496
      ],
      "voteCount": 8231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.898453102351095
      }
    },
    {
      "id": "287de7a9bbdcd9d1e34c7ba8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1300.511470771275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.7161374412951,
        1306.3068041012548
      ],
      "voteCount": 35534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.743003627852366
      }
    },
    {
      "id": "732ed861f52aa1d349d2bfd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1201.0856412532708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.9586161641628,
        1208.2126663423787
      ],
      "voteCount": 37236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.222707568057935
      }
    },
    {
      "id": "1818a412273784164381a071",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1258.9981518915583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.5441316568167,
        1274.4521721262995
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.17084513029894
      }
    },
    {
      "id": "f680b9e55351c07a86bd2f8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1311.1610361525811,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.3151710628968,
        1337.0069012422655
      ],
      "voteCount": 839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.89454720575753
      }
    },
    {
      "id": "3b8eda8396c87753ddf76165",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1276.808904858054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.8464863907093,
        1295.7713233253985
      ],
      "voteCount": 1265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.60332387103826
      }
    },
    {
      "id": "1cebcda3ea68f15af564c5e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1313.5732107923068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.6720981598828,
        1322.4743234247308
      ],
      "voteCount": 9838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.62492656911538
      }
    },
    {
      "id": "0c22667f1ad0cf7a0e7bc882",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1304.1410696833736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.3536638814062,
        1311.9284754853409
      ],
      "voteCount": 13935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.786630016134108
      }
    },
    {
      "id": "b2a1b2a3cc9d0d79567909e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1246.621557128115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.4116416879506,
        1257.8314725682792
      ],
      "voteCount": 5128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.71210496873861
      }
    },
    {
      "id": "94904b2322e308c1444fe951",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1262.629122272901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.9229295625314,
        1272.3353149832706
      ],
      "voteCount": 8080,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.524583323220046
      }
    },
    {
      "id": "08bf2bdf3599e054f4e31183",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1296.458904449043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.1587131827905,
        1310.7590957152956
      ],
      "voteCount": 2897,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.23380512366261
      }
    },
    {
      "id": "69f02ad79f2fcb4120ecccba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1286.674826080467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.372293503936,
        1295.9773586569986
      ],
      "voteCount": 9610,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.52714824671483
      }
    },
    {
      "id": "1b5ad7009f3d066631b9fd50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1288.3466551964618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.318350037447,
        1298.3749603554766
      ],
      "voteCount": 6112,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.179352443025632
      }
    },
    {
      "id": "7bb24a08d3b24d423a9c4cfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1272.8510704590744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.2538918449393,
        1287.4482490732098
      ],
      "voteCount": 2913,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.46789213126745
      }
    },
    {
      "id": "b8665dff07f51294fa898a2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1304.234227370534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.373801536216,
        1312.0946532048522
      ],
      "voteCount": 14549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.08407044843737
      }
    },
    {
      "id": "2b202d1318efeec32092ad69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1281.8209364822844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.4596779363962,
        1290.1821950281724
      ],
      "voteCount": 12861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.198983181747366
      }
    },
    {
      "id": "2bc2a2f152e3e806bb94360f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1282.0182559080092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.7475778896592,
        1289.2889339263593
      ],
      "voteCount": 18087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.761115584981985
      }
    },
    {
      "id": "baa1deba5ee798c80c776022",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1217.5644896664976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.1321380542008,
        1242.9968412787941
      ],
      "voteCount": 619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.37470833921773
      }
    },
    {
      "id": "f1a8621e24dcbc6adb7e678d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1187.550138211474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.681570209769,
        1219.4187062131791
      ],
      "voteCount": 429,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.38019353694045
      }
    },
    {
      "id": "0e06e7f7d0530ab67d9c3fbe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1275.4536652994116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.83650075991,
        1287.0708298389131
      ],
      "voteCount": 4251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.13209908975804
      }
    },
    {
      "id": "2dafc4b7c3fce9c6e20c6232",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1282.6541588885357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.9897581792216,
        1292.3185595978498
      ],
      "voteCount": 7052,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.31384675192595
      }
    },
    {
      "id": "76261f6ea04d0920bf3fab22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1271.8540627662485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.9874761394096,
        1281.7206493930873
      ],
      "voteCount": 7992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.341813151943445
      }
    },
    {
      "id": "cea3b8c475ba8276d7cd5fe5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1286.2868029180083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.5106662431635,
        1291.062939592853
      ],
      "voteCount": 54173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.938234041169264
      }
    },
    {
      "id": "198c3076df5f64f0266c5677",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1266.0502759007654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.8032400923823,
        1278.2973117091483
      ],
      "voteCount": 3579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.04503291400983
      }
    },
    {
      "id": "5ec2056bffb69c0398d79cda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0314",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1277.840199889837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.9324825628619,
        1305.747917216812
      ],
      "voteCount": 647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.7460719367076
      }
    },
    {
      "id": "7e49879988ae69d7183d88bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1255.9751191094667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.583978929066,
        1266.3662592898672
      ],
      "voteCount": 8540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.10801814848727
      }
    },
    {
      "id": "6eac74e665068867281cab1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1312.7822920023266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.7646994473475,
        1320.7998845573054
      ],
      "voteCount": 13719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.733692427304725
      }
    },
    {
      "id": "6a1f8f0d9a6916cf1b00f4a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1264.9050032976304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.568330072712,
        1273.2416765225491
      ],
      "voteCount": 13932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.09211648571518
      }
    },
    {
      "id": "923a649c8b42dee54f02d3b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1292.0076352843666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.9773633293162,
        1297.0379072394169
      ],
      "voteCount": 57478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.5869861224214254
      }
    },
    {
      "id": "fdf87def4b8e865ef7073b2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1185.6982933221573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.6601525804417,
        1191.7364340638728
      ],
      "voteCount": 60653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.490963021745266
      }
    },
    {
      "id": "5d078667349b5289bf9d15ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1247.430213938212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.5817976134106,
        1260.2786302630138
      ],
      "voteCount": 3617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.97372684723939
      }
    },
    {
      "id": "600d5f565ec44c5abbf2c0b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1274.4719840309108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.4822704723829,
        1296.4616975894387
      ],
      "voteCount": 1545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.87600829695658
      }
    },
    {
      "id": "da03d9a8c6a1bc01b7dee36b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1253.309077244191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.4220942570478,
        1269.1960602313338
      ],
      "voteCount": 2215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.70322375294006
      }
    },
    {
      "id": "85c570600e1ad71cfa6a327a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1300.0912286920775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.4726816317016,
        1307.7097757524537
      ],
      "voteCount": 16244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.109431604079374
      }
    },
    {
      "id": "a344cce98bbfe6cd14cef0a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1287.448814817292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.930464170753,
        1293.967165463831
      ],
      "voteCount": 23040,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.060614504662574
      }
    },
    {
      "id": "cd9871c3b31aaed06eba90cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1233.4357156499127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.033125485288,
        1242.8383058145373
      ],
      "voteCount": 8676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.01435624602634
      }
    },
    {
      "id": "9c13bb50a20308ccab5437d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1267.2261954202274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.0823483128593,
        1275.3700425275956
      ],
      "voteCount": 13910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.26485921205467
      }
    },
    {
      "id": "3f525e6e3beba0ed2f898def",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1275.0666026756833,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.716136805369,
        1287.4170685459974
      ],
      "voteCount": 4695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.70731285523273
      }
    },
    {
      "id": "7f7099aae1b2f0f480ce769e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1276.4472744006407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.2602291349135,
        1284.6343196663681
      ],
      "voteCount": 15252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.448504152116925
      }
    },
    {
      "id": "9c9b808499142424477447eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1268.9256777305768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.21740596014,
        1277.6339495010134
      ],
      "voteCount": 9862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.740937171904978
      }
    },
    {
      "id": "1ef132bdc5c3cd2f007429a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1266.0704201052847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.5270597582703,
        1278.6137804522991
      ],
      "voteCount": 4768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.95732796808205
      }
    },
    {
      "id": "3acbe232c1b90325b8c593e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1285.2164270747198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.5015723323759,
        1291.9312818170642
      ],
      "voteCount": 23796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.737539386829704
      }
    },
    {
      "id": "80d2641e2767b01ab79c9797",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1283.005384217176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.1290851566755,
        1289.881683277677
      ],
      "voteCount": 22099,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.308732431211837
      }
    },
    {
      "id": "e3c65ca433d4ae2884f278cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1273.5812915716206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.5268987541385,
        1279.6356843891026
      ],
      "voteCount": 29706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.54212295363246
      }
    },
    {
      "id": "634df9b21b54cf3296108209",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1201.468310322764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.0445301877498,
        1220.8920904577785
      ],
      "voteCount": 1241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.21353093802215
      }
    },
    {
      "id": "c431dab22f7a5d590f812dac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1176.3843749446637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.350597602363,
        1198.4181522869644
      ],
      "voteCount": 1154,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.38098353540512
      }
    },
    {
      "id": "b8b98d27e4500ae019142153",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1276.4402492388822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.0469719343064,
        1285.833526543458
      ],
      "voteCount": 7523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.96878936859549
      }
    },
    {
      "id": "9c00d379687e843f0e8c4f16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1274.7724678824989,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.3904975454284,
        1283.1544382195693
      ],
      "voteCount": 11181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.289256766998836
      }
    },
    {
      "id": "3c0b2887229d8856ae2b8e4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1260.4188786683344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.0431294710515,
        1268.794627865617
      ],
      "voteCount": 13168,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.26211808854061
      }
    },
    {
      "id": "e45953afd6d7a60ff4d3eb33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1274.4461888159144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.3834774902293,
        1278.5089001415995
      ],
      "voteCount": 88723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.296707080896629
      }
    },
    {
      "id": "027ea2050e5a73430e4cb7f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1254.7768777431493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.6302623452314,
        1264.9234931410674
      ],
      "voteCount": 5975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.800704846463432
      }
    },
    {
      "id": "288828714d43ab73f086562e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-0613",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1262.492803022934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.9776273290877,
        1285.0079787167804
      ],
      "voteCount": 1364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.96370446401664
      }
    },
    {
      "id": "28b67ce25b301340970d4e43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1313.6462266379426,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.709298357625,
        1323.5831549182603
      ],
      "voteCount": 9150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.70443892727603
      }
    },
    {
      "id": "62968b1797f326f78f746ac9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1338.7479495895716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.3250013401575,
        1346.1708978389856
      ],
      "voteCount": 15605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.343551053222422
      }
    },
    {
      "id": "716fc562387da6f6cd47730e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1285.8136521808901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.890640267718,
        1293.7366640940622
      ],
      "voteCount": 15576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.341218455369106
      }
    },
    {
      "id": "4b8bd1ed0db5cfb9de7679d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1324.5591981232137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.6854260117543,
        1329.4329702346731
      ],
      "voteCount": 64698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.183498432022241
      }
    },
    {
      "id": "8a3ab0f4aee54e205480d50a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1244.8578575896722,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.8467455248197,
        1250.8689696545252
      ],
      "voteCount": 69044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.406183937614005
      }
    },
    {
      "id": "1f942d2421cc93042e1dee2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1286.20513336478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.2020727112636,
        1298.2081940182966
      ],
      "voteCount": 4240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.504883372916126
      }
    },
    {
      "id": "e95afe040bd1c75b19744451",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1342.9474920519924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.9458887829287,
        1363.9490953210561
      ],
      "voteCount": 1734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.81766705270836
      }
    },
    {
      "id": "265ac7f70567699c6d972702",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1298.8550460089468,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.72362665528,
        1313.9864653626137
      ],
      "voteCount": 2503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.60231837527576
      }
    },
    {
      "id": "2953415c95a2db62573c9176",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1323.9091300463608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.8236821648115,
        1330.9945779279103
      ],
      "voteCount": 18316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.068881908014665
      }
    },
    {
      "id": "155d4f3a11a33b38d985b3cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1311.4208584528387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.365389920647,
        1317.4763269850305
      ],
      "voteCount": 26242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.545514049722279
      }
    },
    {
      "id": "b205216edb4b01b31bbdbfac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1280.1758580375079,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.3666097002947,
        1288.9851063747208
      ],
      "voteCount": 9573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.20140261523546
      }
    },
    {
      "id": "a865e55bc29d739b094238ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1289.5990424398242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.8925106680804,
        1297.3055742115685
      ],
      "voteCount": 15221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.46043696445732
      }
    },
    {
      "id": "d702a3f2b2aaafaf148e6d3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1314.991403918737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.5589608402274,
        1326.4238469972465
      ],
      "voteCount": 5572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.023729224759855
      }
    },
    {
      "id": "ee6a354df3451e3a5308240c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1319.668727971707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.0341399872998,
        1327.3033159561141
      ],
      "voteCount": 17680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.173124693582746
      }
    },
    {
      "id": "c92970de392690c972287584",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1308.768089080259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.7471071384216,
        1316.789071022096
      ],
      "voteCount": 11549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.74784354440994
      }
    },
    {
      "id": "c8ef24521627ccc28a4854c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1302.8724055904058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.9917846390967,
        1314.7530265417147
      ],
      "voteCount": 5514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.743633285433766
      }
    },
    {
      "id": "850776f1d3cd7a966b3bb9ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1323.8917785448234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.5886168471195,
        1330.194940242527
      ],
      "voteCount": 26445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.342385338968725
      }
    },
    {
      "id": "43705feeb162dc4c0f077b9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1306.4247089765327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.9221151291385,
        1312.9273028239268
      ],
      "voteCount": 24682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.0072055221266
      }
    },
    {
      "id": "6efb92154246475ac41666c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1294.6897889196966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.0591706906694,
        1300.3204071487244
      ],
      "voteCount": 34416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.2530786143708
      }
    },
    {
      "id": "5df5fb88d9ebf4bb4fc4b5ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1263.1832121706698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.2676725187782,
        1281.098751822561
      ],
      "voteCount": 1422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.55329993111714
      }
    },
    {
      "id": "63d1cced7dce7835748eb303",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1253.758919113468,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.7275306286256,
        1274.7903075983104
      ],
      "voteCount": 1292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.14357494021982
      }
    },
    {
      "id": "ff942948882ee0b055ab378c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1299.705445198484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.2079848925218,
        1308.2029055044463
      ],
      "voteCount": 9140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.79672151174019
      }
    },
    {
      "id": "1ff798ff17436060208d6fa6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1303.10962965181,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.3230908654043,
        1310.896168438216
      ],
      "voteCount": 13306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.783114983710073
      }
    },
    {
      "id": "1da38b8d0442472bcf95f772",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1297.4553595498196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.6811626585536,
        1305.229556441086
      ],
      "voteCount": 14867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.733121224309524
      }
    },
    {
      "id": "5b66a37d59f6087fc0e0d13b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1312.220522713927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.3327209678591,
        1316.1083244599954
      ],
      "voteCount": 100105,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.934703747260088
      }
    },
    {
      "id": "82ef138c09d7b8d65e5c54c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1299.2939458444653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.0466933877112,
        1308.541198301219
      ],
      "voteCount": 7053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.260209464770405
      }
    },
    {
      "id": "77579684aa985de6f31d5d9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-1106-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1309.1462940340082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.2044693726768,
        1331.0881186953393
      ],
      "voteCount": 1472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.32834319999547
      }
    },
    {
      "id": "f34ccfd22264a0a29283a9ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1315.5419291128433,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.2288257971977,
        1324.8550324284888
      ],
      "voteCount": 10827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.578373846062743
      }
    },
    {
      "id": "c9a021dfcf375969adc8ab49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1346.920396404119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.8074603938103,
        1354.0333324144272
      ],
      "voteCount": 17104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.170480551344443
      }
    },
    {
      "id": "af39ad51b24fdd6421898071",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1322.2918489931749,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.5350486935126,
        1330.0486492928367
      ],
      "voteCount": 14396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.66278689874513
      }
    },
    {
      "id": "33d68902428468c0ec306a1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1340.9389531837069,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.0735886387283,
        1345.8043177286856
      ],
      "voteCount": 55116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.162182977991243
      }
    },
    {
      "id": "7a466472aba04dd134ebfd2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1266.6828794505286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.7439151966792,
        1272.621843704378
      ],
      "voteCount": 65114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.18174528345646
      }
    },
    {
      "id": "5481d9058e34cc2b6f3b5a43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1294.4034974899782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.335397722039,
        1305.4715972579174
      ],
      "voteCount": 5195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.88966436738203
      }
    },
    {
      "id": "4485dcf486a8335e79271fe6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1338.5449476476047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.1025140101917,
        1359.9873812850174
      ],
      "voteCount": 1402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.6883740671662
      }
    },
    {
      "id": "2bb7451ba3ddf765be9e093e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1311.9898665764085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.1223740480007,
        1325.8573591048162
      ],
      "voteCount": 3359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.06102056580048
      }
    },
    {
      "id": "2786d796e246da2811a1469d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1329.2636025239085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.3059107787722,
        1336.2212942690444
      ],
      "voteCount": 17922,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.601846506736319
      }
    },
    {
      "id": "0d982d2f2c181c5bc8217aea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1315.7167919619067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.7945614568307,
        1321.6390224669829
      ],
      "voteCount": 28310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.130076825583886
      }
    },
    {
      "id": "aa515243d080688f305531e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1293.8229247123145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.3138852876377,
        1302.3319641369915
      ],
      "voteCount": 10807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.847983360035844
      }
    },
    {
      "id": "2f05e94ba7f96a738bf18980",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1313.348939844282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.883032271805,
        1320.8148474167592
      ],
      "voteCount": 14793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.510054248271118
      }
    },
    {
      "id": "28398e5d34ff5a20aa9f6cc7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1337.7480872534716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.6344757140405,
        1348.8616987929022
      ],
      "voteCount": 5381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.15246270088962
      }
    },
    {
      "id": "66ccb0cea25457ec49f0f721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1327.114201565793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.7313003594486,
        1334.4971027721376
      ],
      "voteCount": 16354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.189200709119266
      }
    },
    {
      "id": "121bf5575d812547cc81d894",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1299.220112852926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.4583076832023,
        1306.9819180226496
      ],
      "voteCount": 11796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.683005416640238
      }
    },
    {
      "id": "17d8c14561f4a27e8eef7afe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1327.5934382518317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.018148916718,
        1339.1687275869454
      ],
      "voteCount": 5046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.879281399504336
      }
    },
    {
      "id": "f907549b5d06cd8e8616b536",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1336.3870845303338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.2361615065117,
        1342.5380075541557
      ],
      "voteCount": 27573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.84882457705161
      }
    },
    {
      "id": "dcc12ae9634413250763742a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1328.8177333391266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.391089539208,
        1335.2443771390454
      ],
      "voteCount": 24529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.751579662532881
      }
    },
    {
      "id": "d12dc0fa5d3cb54f7fa54ee2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1301.9295953292444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.4137140066828,
        1307.4454766518063
      ],
      "voteCount": 36297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.920154343627006
      }
    },
    {
      "id": "00b1724a05b29ded7f5dcaaf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1250.9813749734367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.1588788250583,
        1266.8038711218146
      ],
      "voteCount": 2112,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.17091450174746
      }
    },
    {
      "id": "295a6949230412fc7b0c132b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1263.1641667532108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.1350806890755,
        1281.193252817346
      ],
      "voteCount": 2668,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.61575653419663
      }
    },
    {
      "id": "3bd7ea105b8fd28fe636499c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1315.8354265710345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.875837860464,
        1323.7950152816047
      ],
      "voteCount": 11559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.492446072867814
      }
    },
    {
      "id": "d36f8f6014c8e1d9ec6b046c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1296.217925597844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.6931437445544,
        1303.7427074511338
      ],
      "voteCount": 13217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.739801878018719
      }
    },
    {
      "id": "2e1f446c2c6abf873c9bfc09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1312.2743102405002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.8416769643452,
        1319.7069435166552
      ],
      "voteCount": 15255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.381004716282318
      }
    },
    {
      "id": "11cec53733c234306123e42d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1323.750512376856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.8357849908346,
        1327.6652397628773
      ],
      "voteCount": 98114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.989393410729621
      }
    },
    {
      "id": "82b8c7f4c9490abd88e58e94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1311.7793302047216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.398695993525,
        1320.1599644159185
      ],
      "voteCount": 9938,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.283426442975944
      }
    },
    {
      "id": "b2c1c8db0bc047be7c2dc4a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4-turbo-2024-04-09",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1311.6949950654362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.580526628974,
        1332.8094635018983
      ],
      "voteCount": 1430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.05507130590614
      }
    },
    {
      "id": "65b57d073486a31e74578dc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1415.975365239204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.7483107070705,
        1428.2024197713376
      ],
      "voteCount": 2469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.91773139058534
      }
    },
    {
      "id": "f8b447f1afa0d74b2fa4c8c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1456.2283127741437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.620514746423,
        1462.8361108018642
      ],
      "voteCount": 9316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.366253502428393
      }
    },
    {
      "id": "fa7c1aee07d598efaee2aa41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1402.087775024013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.440939973706,
        1409.7346100743198
      ],
      "voteCount": 6704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.221843840053538
      }
    },
    {
      "id": "576ab2c3ee2c7b6df93598b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1421.7933192398793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.1275558263728,
        1426.4590826533858
      ],
      "voteCount": 25699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.666948221218246
      }
    },
    {
      "id": "b35fe90033e4502da83ec408",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1401.7889419563091,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.7181994592215,
        1406.8596844533965
      ],
      "voteCount": 36239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.69340234320763
      }
    },
    {
      "id": "cba58483932ec63e888e678a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1405.87893037381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.9446825845948,
        1417.8131781630252
      ],
      "voteCount": 2509,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.076089304181046
      }
    },
    {
      "id": "cd37e9c0a7cb557cedeb05f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1422.5437293210402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.2164437855117,
        1445.8710148565688
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.65510444226283
      }
    },
    {
      "id": "2b3033ed7185a0f901b476e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1408.8024764378636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.7614511800225,
        1425.8435016957046
      ],
      "voteCount": 1233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.59538065955458
      }
    },
    {
      "id": "cc102e19770dfab40ff21dd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1436.9008737527895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.8620222908137,
        1442.9397252147653
      ],
      "voteCount": 11915,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.493197423685727
      }
    },
    {
      "id": "a745b9cc8f79ef8085406332",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1430.715822106764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.823174240221,
        1435.6084699733074
      ],
      "voteCount": 22173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.231487636164097
      }
    },
    {
      "id": "95bb729fe3211c90ffde95d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1414.7939457927991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.7430845944175,
        1421.8448069911808
      ],
      "voteCount": 8284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.941605249294858
      }
    },
    {
      "id": "11dd3f21a3a20b6206e74ae4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1399.5524790037573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.8714155039206,
        1406.233542503594
      ],
      "voteCount": 9066,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.619702715122298
      }
    },
    {
      "id": "e696fdb48ac17b640501d40e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1438.153454990474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.623942039098,
        1448.6829679418502
      ],
      "voteCount": 3275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.861598722841734
      }
    },
    {
      "id": "594bec78ed53b4e22ef58178",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1424.0598776753434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.1562910064379,
        1430.9634643442491
      ],
      "voteCount": 8547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.406617152407717
      }
    },
    {
      "id": "58463dd1e9d5b9f51e8e72c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1372.9738914745035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4177501696395,
        1383.5300327793675
      ],
      "voteCount": 3065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.00776097038142
      }
    },
    {
      "id": "2997ca0cad487771d4c5cfb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1433.2694669697528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.577567109192,
        1444.9613668303136
      ],
      "voteCount": 2802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.585575358239154
      }
    },
    {
      "id": "170d946c5a0ef6ca27214fde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1442.0226860211724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.6536829472934,
        1447.3916890950513
      ],
      "voteCount": 16826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.503970588473744
      }
    },
    {
      "id": "990838d49189eb2cb087f384",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1403.6903005693573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.5408710848087,
        1409.839730053906
      ],
      "voteCount": 11398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.84404226376727
      }
    },
    {
      "id": "d5a35b08c52f99d0236a7ff6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1402.2239693323208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.5010961492528,
        1407.946842515389
      ],
      "voteCount": 13291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.52573956879311
      }
    },
    {
      "id": "e53bebde9ad8bbb6c7f414bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1341.603217139382,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.1038315200337,
        1361.1026027587302
      ],
      "voteCount": 1017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.97959532554368
      }
    },
    {
      "id": "882e5a14e2b652a000f2a0c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1380.4295974099107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.0717635041594,
        1399.787431315662
      ],
      "voteCount": 1004,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.54776792191286
      }
    },
    {
      "id": "64f30f107ae262c7c8356bae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1424.2489340824577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.841256646136,
        1430.6566115187795
      ],
      "voteCount": 9833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.688213005633388
      }
    },
    {
      "id": "c9db2f35494bd4dfb0d77de8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1373.467719863043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.2599695889714,
        1383.6754701371142
      ],
      "voteCount": 3227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.124634291661472
      }
    },
    {
      "id": "164ee55bc145608b319b2065",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1429.9797201760691,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.1617497006519,
        1436.7976906514862
      ],
      "voteCount": 8952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.100799090503216
      }
    },
    {
      "id": "6a682bea0f211d4a6e71814d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1413.4709361991618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.7790197178274,
        1417.1628526804964
      ],
      "voteCount": 50997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.548195605201482
      }
    },
    {
      "id": "d7652173af9a2d55b81dd5c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1408.1028546353136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.6868436583788,
        1418.5188656122484
      ],
      "voteCount": 3061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.242730102211606
      }
    },
    {
      "id": "6ddd75bfc5c9cd0a9856e906",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1402.6451137751044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.8065317007367,
        1422.4836958494718
      ],
      "voteCount": 986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.45309323667281
      }
    },
    {
      "id": "1cbc0568ab7f3ae078a72e1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1383.5612303324663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.2419636072073,
        1396.8804970577253
      ],
      "voteCount": 2052,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.18111878302901
      }
    },
    {
      "id": "48b861d47bdcdb643141ef1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1433.2090200742903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.7276859323151,
        1440.6903542162652
      ],
      "voteCount": 6918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.570079533943565
      }
    },
    {
      "id": "422cc39a88809162c7a7f698",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1349.143304903779,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.435090565504,
        1357.8515192420537
      ],
      "voteCount": 5157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.740676784772457
      }
    },
    {
      "id": "f413016f4c35058a0e9273a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1397.6464118506028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.3530997335954,
        1402.93972396761
      ],
      "voteCount": 19774,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.293883515584047
      }
    },
    {
      "id": "896041757eea4dfce5a5dab2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1358.956716282871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.0980397374299,
        1364.8153928283118
      ],
      "voteCount": 27948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.935170846865457
      }
    },
    {
      "id": "f0fdc7f3f14d59cf1bc9c620",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1382.8554568721343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.8058435479625,
        1395.9050701963058
      ],
      "voteCount": 2001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.330140152232005
      }
    },
    {
      "id": "dbbc810ef006890817c39faf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1408.716519935958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.9699471000185,
        1435.463092771898
      ],
      "voteCount": 532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.2259084008508
      }
    },
    {
      "id": "b29595125251eab80a4aa49f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1390.1862595094055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.30364904123,
        1409.068869977581
      ],
      "voteCount": 1016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.81707672410269
      }
    },
    {
      "id": "99dcf3a2e86449ea6f8a8185",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1412.9595978429995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.027128707597,
        1419.8920669784018
      ],
      "voteCount": 8751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.510645188856179
      }
    },
    {
      "id": "ff0254157ddf382494662395",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1402.3486124195183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.6767579791654,
        1408.0204668598712
      ],
      "voteCount": 16247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.374405217947663
      }
    },
    {
      "id": "dc96feca0cd5473fc2aedd32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1380.33861835524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.2525000196829,
        1388.424736690797
      ],
      "voteCount": 6066,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.020958127782357
      }
    },
    {
      "id": "c38687bb3209ac858cbfe833",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1348.0652935022936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.4995389130654,
        1355.631048091522
      ],
      "voteCount": 6797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.90075650325098
      }
    },
    {
      "id": "1bf9d72d6eb9d3fb302344f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1398.7872800302302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.7746532252984,
        1410.799906835162
      ],
      "voteCount": 2477,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.56468817970793
      }
    },
    {
      "id": "c4e7c11d929d1c843ff873eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1384.4773970642113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.598330933031,
        1392.3564631953914
      ],
      "voteCount": 6534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.160444767775274
      }
    },
    {
      "id": "eb30e380ed68441d89c4c605",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1364.3824720585396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.8226868676063,
        1375.942257249473
      ],
      "voteCount": 2481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.78590814006807
      }
    },
    {
      "id": "77dd3c2a5d52cd7ba0df28c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1398.3708881395492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.614978850014,
        1411.1267974290845
      ],
      "voteCount": 2320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.357143313969395
      }
    },
    {
      "id": "cf3cb0a432491785b7fbc3e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1418.508037524941,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.443087273441,
        1424.572987776441
      ],
      "voteCount": 12747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.575430395092303
      }
    },
    {
      "id": "ed9678741368b7c121b74c97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1359.9713576937481,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.0576994810654,
        1366.885015906431
      ],
      "voteCount": 8694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.442843230363726
      }
    },
    {
      "id": "d9c6347b365b7a378ef8d9ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1372.1957148578906,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.71849386709,
        1378.6729358486914
      ],
      "voteCount": 10065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.921473773884603
      }
    },
    {
      "id": "5d9b0a2b99b5569a0e8988a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1324.0607004929423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.495910663993,
        1344.6254903218914
      ],
      "voteCount": 909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.09113996761197
      }
    },
    {
      "id": "8629a19e6abd0f62798a6625",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1346.6570795945377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.4764988059592,
        1368.8376603831164
      ],
      "voteCount": 781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.07065937251534
      }
    },
    {
      "id": "3c433bec2063252d9f041b40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1388.919843942364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.4118091948444,
        1396.4278786898833
      ],
      "voteCount": 7047,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.674265272944814
      }
    },
    {
      "id": "28bbb2962a1a41691ebf4afb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1354.577183392223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.4989502871144,
        1365.6554164973318
      ],
      "voteCount": 2693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.948083907599834
      }
    },
    {
      "id": "9010349fb4d0787f4d65ad13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1392.2154121064864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.6465830745271,
        1399.7842411384456
      ],
      "voteCount": 7188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.912869196050966
      }
    },
    {
      "id": "a82c6e38a580dd8336acf73f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1382.4525803494744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.1543839537835,
        1386.7507767451655
      ],
      "voteCount": 39339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.8092386560044185
      }
    },
    {
      "id": "05df482f74b73390a18a38f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1360.6317058088944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.296357663623,
        1371.9670539541653
      ],
      "voteCount": 2632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.4482610830868
      }
    },
    {
      "id": "a9ce9767bc63af76b8975169",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-mini-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1356.1683249210803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.596431458056,
        1378.7402183841048
      ],
      "voteCount": 721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.6293989568433
      }
    },
    {
      "id": "114635d0da5f73c54ea3c27a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1321.1513005861966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.8632683070796,
        1357.4393328653136
      ],
      "voteCount": 246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 342.7919829822075
      }
    },
    {
      "id": "7fd7617536b025f3a265823e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1373.8734787520366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.5737293568034,
        1393.17322814727
      ],
      "voteCount": 807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.96324862634023
      }
    },
    {
      "id": "156a863ce86a8d418ebcfa2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1306.5327680111013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.1033260745426,
        1324.96220994766
      ],
      "voteCount": 1005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.41545515555374
      }
    },
    {
      "id": "4b06a2c9a7cf5c0dddfb0287",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1339.7550477197774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.85653620799,
        1349.653559231565
      ],
      "voteCount": 3528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.50607327121731
      }
    },
    {
      "id": "a0483f1d158d493fb63c6cac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1266.5654345811427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.284215700318,
        1278.8466534619674
      ],
      "voteCount": 3981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.263296637778936
      }
    },
    {
      "id": "5836dc09ba00a319bdf57068",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1313.0202859099793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.360403593032,
        1343.6801682269265
      ],
      "voteCount": 328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 244.70609410806946
      }
    },
    {
      "id": "936cea6ddfd6865c1280cc27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1320.9799822239543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.6480906903425,
        1358.3118737575662
      ],
      "voteCount": 222,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 362.79710144739477
      }
    },
    {
      "id": "74df415468a48a2fcaba7e1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1339.2091241659996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.0648810262403,
        1356.3533673057589
      ],
      "voteCount": 1062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.51391998576052
      }
    },
    {
      "id": "3c796b176e1b3ed8d1ae59e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1332.834038252469,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.2327545651697,
        1346.4353219397688
      ],
      "voteCount": 1669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.157464801086896
      }
    },
    {
      "id": "53e45d3bba67aa27cf4a6ea1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1322.176604242286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.0445876687527,
        1344.3086208158193
      ],
      "voteCount": 651,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.51045383395369
      }
    },
    {
      "id": "1d3c1b38c617adf9b50f4762",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1286.8485038441008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.5876822786713,
        1304.1093254095306
      ],
      "voteCount": 1061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.55802548464368
      }
    },
    {
      "id": "1c9c32bb30dcce183b7d1a17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1352.676135408793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.0979085353888,
        1381.2543622821972
      ],
      "voteCount": 382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.60544218984865
      }
    },
    {
      "id": "747ff677788272e92ca20706",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1349.3742603198534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.788035910622,
        1365.9604847290848
      ],
      "voteCount": 1162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.61415831698999
      }
    },
    {
      "id": "4981796e9d555b9e7b54692f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1280.3283508908817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.3473351667894,
        1304.3093666149744
      ],
      "voteCount": 534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.70591694518075
      }
    },
    {
      "id": "91d8c43df82d3026d2bcdcc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1343.4262391823145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.40269322735,
        1375.449785137279
      ],
      "voteCount": 302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 266.95782602308753
      }
    },
    {
      "id": "d22f6a3b153c60e023394700",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1362.0603046651852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.2674000096235,
        1376.8532093207466
      ],
      "voteCount": 1454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.965345292700896
      }
    },
    {
      "id": "b88c2dba5e0c3831512a6c20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1298.4822388770272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.1875479817368,
        1312.7769297723175
      ],
      "voteCount": 1583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.19286170428747
      }
    },
    {
      "id": "2f26e44ad0186f11863a21b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1300.579449415518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.1023402178853,
        1313.0565586131506
      ],
      "voteCount": 2015,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.525816153750576
      }
    },
    {
      "id": "530d4cc8a9350dd43d22caac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1232.738808528802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.5374981144296,
        1277.9401189431746
      ],
      "voteCount": 160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 531.870458214954
      }
    },
    {
      "id": "cf43a026ebb84b96a77d1c02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1324.836632039016,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.7540180573683,
        1344.9192460206636
      ],
      "voteCount": 730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.9891208421175
      }
    },
    {
      "id": "0cb8f98eb867613fa201d583",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1274.121056782388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.106914741138,
        1297.135198823638
      ],
      "voteCount": 582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.87749878810823
      }
    },
    {
      "id": "b1c594164b046eb46dcaf3fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1314.140430270024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.0591350204886,
        1332.221725519559
      ],
      "voteCount": 1000,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.10653196115419
      }
    },
    {
      "id": "0bef98f981d3fe0835d4bde7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1321.8652204589637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.1433073439978,
        1329.5871335739296
      ],
      "voteCount": 6103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.522213028515186
      }
    },
    {
      "id": "401fb4e20004b52a0262091f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.1-nano-2025-04-14",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1299.7147568026758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.9141102182357,
        1320.5154033871156
      ],
      "voteCount": 702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.63088283023549
      }
    },
    {
      "id": "a047493f1e0ce46cf3ed8a9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1456.6193395427792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.915943479474,
        1476.3227356060847
      ],
      "voteCount": 907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.06155878493246
      }
    },
    {
      "id": "8b1c28d0bd7bee8e1c1b231a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1459.040470076429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.0207475032028,
        1472.0601926496554
      ],
      "voteCount": 1939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.12729220748265
      }
    },
    {
      "id": "6759687ba661a26bd4201a3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1436.051386041585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.1280150652506,
        1447.9747570179193
      ],
      "voteCount": 2618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.008538181753536
      }
    },
    {
      "id": "3aa65d73c96e9a938d6b8619",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1447.4829820023385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.3992723784115,
        1454.5666916262653
      ],
      "voteCount": 8425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.062470373441785
      }
    },
    {
      "id": "1895368e7e24e09dfc320e38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1452.4210332179784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.8493722777919,
        1460.992694158165
      ],
      "voteCount": 10031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.12642428384646
      }
    },
    {
      "id": "cc1ff6718d7392d77df1da8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1429.1398463653709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.6344575147893,
        1452.6452352159522
      ],
      "voteCount": 608,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.82642917859064
      }
    },
    {
      "id": "4e2e1c1d1c5874a18fbb3449",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1446.4832358945803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.614676679425,
        1503.3517951097356
      ],
      "voteCount": 121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 841.876271010827
      }
    },
    {
      "id": "7636a4a9ba0630a6745e2ead",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1476.4626151448304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.281631645433,
        1508.643598644228
      ],
      "voteCount": 319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 269.5891710226284
      }
    },
    {
      "id": "7a2e419a9ff07a2f63816dd1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1444.3070617322019,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.0502686877583,
        1456.5638547766453
      ],
      "voteCount": 2260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.10727219696556
      }
    },
    {
      "id": "f9c4dbc81d9f001cebdb40b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1440.5411996675782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.5475227127483,
        1450.5348766224079
      ],
      "voteCount": 3445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.998867549867164
      }
    },
    {
      "id": "8e21cd974d9a03402e654139",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1426.0635580350126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.5098341621674,
        1441.6172819078583
      ],
      "voteCount": 1394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.97563962146289
      }
    },
    {
      "id": "f50d5c9cf1ddf2c6495acd2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1435.364479645642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.686270590414,
        1447.0426887008698
      ],
      "voteCount": 2627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.50228522636167
      }
    },
    {
      "id": "9cf8e253d56a1969613b0bdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1468.8173189857544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.2597206122714,
        1491.3749173592373
      ],
      "voteCount": 701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.46146011983507
      }
    },
    {
      "id": "faeb24cb571303e8634ad78a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1448.779592231561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9840385325103,
        1460.575145930612
      ],
      "voteCount": 2545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.219335820460905
      }
    },
    {
      "id": "72d3700dd4f00b281d8f2593",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1413.7531756167732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.1912151540303,
        1429.3151360795164
      ],
      "voteCount": 1283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.042355716368
      }
    },
    {
      "id": "f61f188d882ff6112545fb2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1450.176100001521,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.732997000258,
        1474.6192030027842
      ],
      "voteCount": 589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.53083144137463
      }
    },
    {
      "id": "5355054d2b9725cf32b25df2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1458.959158518131,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.7893059589721,
        1469.12901107729
      ],
      "voteCount": 3358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.923600096367498
      }
    },
    {
      "id": "56d3a2da8602df01aee3091e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1446.6463775698999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.035126942033,
        1456.2576281977665
      ],
      "voteCount": 4092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.047150560103596
      }
    },
    {
      "id": "4af50909de66e2c19b78d328",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1436.7691784245455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.467310190829,
        1445.071046658262
      ],
      "voteCount": 5501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.941365347640804
      }
    },
    {
      "id": "ebedaf17261cfa2ac9593770",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1440.1486612772408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.1878475272247,
        1478.1094750272566
      ],
      "voteCount": 271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 375.12399529067824
      }
    },
    {
      "id": "f48f37a17a4069bd7047ae4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1413.845644095658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.296919582494,
        1457.3943686088219
      ],
      "voteCount": 215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 493.69041690801214
      }
    },
    {
      "id": "44f9500ac9c5507337be7444",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1442.9284750337417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.2964432288318,
        1456.560506838652
      ],
      "voteCount": 1796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.375447923323314
      }
    },
    {
      "id": "87895d2223e7105224506a4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1409.048046899537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.8590312649196,
        1424.2370625341543
      ],
      "voteCount": 1393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.05692282989675
      }
    },
    {
      "id": "6c3a197406c54fe205405b64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1466.2948998460759,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.927921905217,
        1479.6618777869344
      ],
      "voteCount": 2052,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.51256400533745
      }
    },
    {
      "id": "45bab48fc072cad1820ce2ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1444.5390945160223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.848737975251,
        1450.2294510567936
      ],
      "voteCount": 14547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.429130461236738
      }
    },
    {
      "id": "69c3cc579739c851303b0987",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4.5-preview-2025-02-27",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1446.1641625433901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.679253697337,
        1461.6490713894434
      ],
      "voteCount": 1430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.41962055635199
      }
    },
    {
      "id": "25747f4250c9c0045a436b9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1337.4998029989279,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.024401481653,
        1345.9752045162024
      ],
      "voteCount": 11416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.699258336977593
      }
    },
    {
      "id": "059fa7373668ad7dc62bb9fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1368.948559203111,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.516183583382,
        1375.38093482284
      ],
      "voteCount": 19526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.770766535461089
      }
    },
    {
      "id": "b465162845e05a77e256d9d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1337.083999787017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.9551927072685,
        1344.212806866766
      ],
      "voteCount": 16599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.229320618122374
      }
    },
    {
      "id": "b71c69a8e05ea4ffdd7b0251",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1356.2086020215406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.6354594138284,
        1360.7817446292527
      ],
      "voteCount": 60226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.444190420006363
      }
    },
    {
      "id": "ab86e4c87b9bafb9b7130a99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1304.5275042816206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.0095206732112,
        1310.0454878900302
      ],
      "voteCount": 74322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.926192762668778
      }
    },
    {
      "id": "4f2c046440d9e4cfec51eb52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1309.328448129284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.18109476992,
        1319.475801488648
      ],
      "voteCount": 5887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.804603408761334
      }
    },
    {
      "id": "a5ef008dabab1d44fd1425da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1362.2867250725117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.6822185675085,
        1382.8912315775146
      ],
      "voteCount": 1359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.51678753594024
      }
    },
    {
      "id": "fd1af1ceeb14e1d452859dee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1329.2335689530664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.1839024934407,
        1342.2832354126922
      ],
      "voteCount": 3573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.330501160159145
      }
    },
    {
      "id": "93683a3db02b4ad7f0164ef9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1348.6682359614156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.2934430972712,
        1355.0430288255598
      ],
      "voteCount": 19579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.578789454106792
      }
    },
    {
      "id": "b1c24719f347dd7669e8b2c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1337.1234011420684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.7336856621696,
        1342.5131166219671
      ],
      "voteCount": 32416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.5619795265724274
      }
    },
    {
      "id": "b73d925d93e5fbbd00fe38ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1322.429118175197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.8615814204563,
        1329.9966549299374
      ],
      "voteCount": 13299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.90777728134035
      }
    },
    {
      "id": "911ee70a413a8c5d34b64d10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1337.3379668266707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.512232901572,
        1344.1637007517697
      ],
      "voteCount": 17607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.128372524849164
      }
    },
    {
      "id": "f99f302790fd2a576c6d4adb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1372.1750782052234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.153123977323,
        1382.197032433124
      ],
      "voteCount": 6743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.14620414647162
      }
    },
    {
      "id": "e19df588dab021ae0d70b16f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1354.2551634676124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.5414374382567,
        1360.9688894969686
      ],
      "voteCount": 19017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.733593746842926
      }
    },
    {
      "id": "13319ecf1467ec7e4d2cd43c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1309.8820552211055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.8703971822301,
        1316.8937132599813
      ],
      "voteCount": 13306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.798093315300546
      }
    },
    {
      "id": "d791a439a516922e65bd8bfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1353.1043239008127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.4883914721995,
        1363.7202563294259
      ],
      "voteCount": 5984,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.337297779106795
      }
    },
    {
      "id": "9e7e4a956990b39b080adbed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1360.0698805056215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.4910810879815,
        1365.6486799232616
      ],
      "voteCount": 31401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.10187077226987
      }
    },
    {
      "id": "bd3e0794a986ca6c23e90311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1344.1098898707564,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.269680064733,
        1349.9500996767797
      ],
      "voteCount": 29959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.8789317211029
      }
    },
    {
      "id": "7c85f8dcd8bd1a6fd18c9a75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1324.6078600197638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.6124685735515,
        1329.6032514659762
      ],
      "voteCount": 43766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.495952934979615
      }
    },
    {
      "id": "073250cb90ce493cc13df30f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1304.905407528737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.3302454622135,
        1319.4805695952602
      ],
      "voteCount": 2674,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.300696735578974
      }
    },
    {
      "id": "63adf9a1aa4b6fede0958b92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1293.72743808326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.8954185754865,
        1310.5594575910338
      ],
      "voteCount": 3517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.75241905076011
      }
    },
    {
      "id": "9514a15f3f46ceb78747d449",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1331.0282942208169,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.048605818581,
        1338.0079826230526
      ],
      "voteCount": 14922,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.681653628530029
      }
    },
    {
      "id": "9b4b8424fa4ef1fddc480886",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1304.7401907709161,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.9622704624123,
        1311.51811107942
      ],
      "voteCount": 15103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.959051457468627
      }
    },
    {
      "id": "43acd6381372f4879eb28d8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1340.1388956145656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.5121461195217,
        1346.76564510961
      ],
      "voteCount": 20434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.43154486871026
      }
    },
    {
      "id": "d9c3dfd4ea30734c70c2bdd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1345.530199621523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.0862064211442,
        1348.9741928219019
      ],
      "voteCount": 112881,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.0876523003081817
      }
    },
    {
      "id": "59f6cc1e1781f034a9879ce5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1331.0817194491742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.6292417418179,
        1338.5341971565308
      ],
      "voteCount": 13904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.457899087568267
      }
    },
    {
      "id": "fd4b4ae539084dd260a4708c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-05-13",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1338.61111437868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.664291383841,
        1358.557937373519
      ],
      "voteCount": 1712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.57412799639091
      }
    },
    {
      "id": "e8296c75f06703581b11b159",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1328.6378557378753,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.070976602232,
        1339.2047348735186
      ],
      "voteCount": 3778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.066805054835893
      }
    },
    {
      "id": "f5b1c179932a5dcfc155e51e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1360.378708818338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.4978974424293,
        1368.2595201942463
      ],
      "voteCount": 7318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.167604767249884
      }
    },
    {
      "id": "ab553379b9328b1e600ce3c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1326.2482757052467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.7785368997365,
        1334.7180145107568
      ],
      "voteCount": 6756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.674279429241178
      }
    },
    {
      "id": "32fece3f504095314085868f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1347.866758842973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.5475772259792,
        1353.1859404599668
      ],
      "voteCount": 25286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.365351132269196
      }
    },
    {
      "id": "d219188996bc3135d4010687",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1285.8576665787668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.3535322084876,
        1292.361800949046
      ],
      "voteCount": 28538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.012421551613354
      }
    },
    {
      "id": "04f1152ea213f6304fef7965",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1308.9283576436073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.2348798857497,
        1321.6218354014652
      ],
      "voteCount": 2349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.94353892881702
      }
    },
    {
      "id": "ef4c56e81de9a46a6ec1d01b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1330.5178930447926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.0537653232532,
        1358.982020766332
      ],
      "voteCount": 457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.91116806549715
      }
    },
    {
      "id": "cdebc1c953ba600ceac95f7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1312.9957749013406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.761969084409,
        1330.2295807182722
      ],
      "voteCount": 1202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.31543582758876
      }
    },
    {
      "id": "59159250b38f2525c2c7e864",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1338.9285494684013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.2351661326265,
        1346.6219328041761
      ],
      "voteCount": 8010,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.407726573126302
      }
    },
    {
      "id": "75bf71483c1e7551039a4f57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1326.5507878490605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.1051337944232,
        1332.9964419036978
      ],
      "voteCount": 12655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.815280894916805
      }
    },
    {
      "id": "cc5a8fe1d621c26b15f83857",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1303.26746485068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.1596879926747,
        1312.375241708685
      ],
      "voteCount": 5095,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.593775481426707
      }
    },
    {
      "id": "659df699cb4627b3adc57ee7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1324.1792315305877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.935183576997,
        1332.4232794841785
      ],
      "voteCount": 7043,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.69232206654842
      }
    },
    {
      "id": "ec5bce6dd5aff55bad0926cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1348.8230505049464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.3977504877626,
        1361.24835052213
      ],
      "voteCount": 2674,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.1899610859627
      }
    },
    {
      "id": "b667d41a502ff0408185bd61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1348.2635869882479,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.2334127856884,
        1356.2937611908073
      ],
      "voteCount": 7560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.786252497638536
      }
    },
    {
      "id": "08486fec6dd9042bcc29cf5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1312.4332154613098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.116745675571,
        1320.7496852470483
      ],
      "voteCount": 5805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.00453237309587
      }
    },
    {
      "id": "1028f9d47f46239b82d50038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1343.1444784779096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.3326727604842,
        1356.9562841953348
      ],
      "voteCount": 2174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.65977408067954
      }
    },
    {
      "id": "1aa7bf98afe37ff2aef23f7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1347.0718418897645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.360419898301,
        1353.7832638812283
      ],
      "voteCount": 11864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.725541584580206
      }
    },
    {
      "id": "275adbb2dc4eb87e95cc271b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1339.7893447095416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.9396774950178,
        1346.639011924065
      ],
      "voteCount": 12147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.213573837358204
      }
    },
    {
      "id": "ab169228bde7dab85173408c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1317.4483744932295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.6595046369328,
        1323.2372443495265
      ],
      "voteCount": 18305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.723512544926171
      }
    },
    {
      "id": "2c01c453185d6d14f40590e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1291.6899294456994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.2453539811154,
        1310.134504910283
      ],
      "voteCount": 1104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.56072131661075
      }
    },
    {
      "id": "a61434f1ac20c64062de961b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1288.285329552828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.927137722148,
        1312.6435213835077
      ],
      "voteCount": 712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.45213314898706
      }
    },
    {
      "id": "923da66fe05424e7ac991e10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1337.6387730384126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.2186265166029,
        1346.0589195602224
      ],
      "voteCount": 6160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.456235185136233
      }
    },
    {
      "id": "5e76dafc9a5a7f8ea230a5d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1308.3002360185365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.3270959174097,
        1316.2733761196632
      ],
      "voteCount": 6826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.548651447136233
      }
    },
    {
      "id": "cc5f0c73dddf0a9ac8a6dd53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1326.4355081004287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.5856475685973,
        1334.28536863226
      ],
      "voteCount": 8201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.040861882275575
      }
    },
    {
      "id": "0346e69a191aedfa83321104",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1334.7696899769544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.5759638877546,
        1338.963416066154
      ],
      "voteCount": 45499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.57829677009421
      }
    },
    {
      "id": "93fb85463d4d70d0cbf1b5a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1322.8861006465343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.0956394759082,
        1331.6765618171603
      ],
      "voteCount": 5517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.115328889122623
      }
    },
    {
      "id": "9f969d768b9ae8b72b7cb54e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-2024-08-06",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1324.9810452713443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.0504689156542,
        1351.9116216270345
      ],
      "voteCount": 546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.7970109018675
      }
    },
    {
      "id": "c625e1995d393b84774b6708",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1314.7999117023328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.7702213674766,
        1323.829602037189
      ],
      "voteCount": 5767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.225089568619467
      }
    },
    {
      "id": "7103915df9cc07e372f0807e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1348.8184956581981,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.2960113121962,
        1355.3409800042
      ],
      "voteCount": 10927,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.074647426821313
      }
    },
    {
      "id": "573604ff9fa474b7d5a41240",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1294.3131399518238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.3807994449458,
        1301.2454804587014
      ],
      "voteCount": 10484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.51018093553766
      }
    },
    {
      "id": "9e7aecbc81fdc36d05288828",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1328.7919105688409,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.5352345833887,
        1333.0485865542933
      ],
      "voteCount": 37771,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.716773312137634
      }
    },
    {
      "id": "1a68c51047e5a2df4445ea48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1261.1962096219881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.901957090921,
        1266.4904621530552
      ],
      "voteCount": 43354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.296475420149194
      }
    },
    {
      "id": "905378819c3193944799449f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1284.0234744189117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.2558787837102,
        1294.7910700541133
      ],
      "voteCount": 3547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.18153289542852
      }
    },
    {
      "id": "91c02ca277322884baab4c77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1340.2084736743109,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.0641188665988,
        1364.3528284820227
      ],
      "voteCount": 649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.75221088933785
      }
    },
    {
      "id": "d566a2271d39ab5e5c5f0c21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1300.2005413092384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.130856100044,
        1315.2702265184325
      ],
      "voteCount": 1637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.11697167774787
      }
    },
    {
      "id": "9c310b8a29cb3c9e18d27e3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1321.1817056711716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.8263304627021,
        1327.537080879641
      ],
      "voteCount": 11377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.514441498849937
      }
    },
    {
      "id": "b5e59c581200d141f384b42b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1311.1188370448785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.810280394548,
        1316.4273936952093
      ],
      "voteCount": 18259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.3359562148518975
      }
    },
    {
      "id": "5b016929074a1d63279073ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1311.3719522519827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.6221827575964,
        1319.121721746369
      ],
      "voteCount": 7766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.634406099209455
      }
    },
    {
      "id": "4aaa2cde52bc0c78073a66e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1284.2878531736471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.7854401881032,
        1290.790266159191
      ],
      "voteCount": 11285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.006593226198158
      }
    },
    {
      "id": "7f36dacde90250280113faf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1347.3733135697084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.5901642442532,
        1358.1564628951642
      ],
      "voteCount": 3866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.26878974953101
      }
    },
    {
      "id": "7595e7271dcb65c114cf9806",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1326.9236759161104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.3126324405057,
        1333.534719391715
      ],
      "voteCount": 11642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.377421411076773
      }
    },
    {
      "id": "5d1874707a1e1ad2e7d36b34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1286.2546734815687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.1098211344383,
        1293.3995258286993
      ],
      "voteCount": 7968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.288939812993364
      }
    },
    {
      "id": "2b8caaf85ed44b9e3cb9dcb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1334.4138711361527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.1352492858243,
        1345.6924929864813
      ],
      "voteCount": 3438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.11432369323694
      }
    },
    {
      "id": "2abbbfb5fd990a78f6738810",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1338.7146920489054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.191938433988,
        1344.2374456638227
      ],
      "voteCount": 17799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.93990223890267
      }
    },
    {
      "id": "55d3ca7bf4892a1cf2dd5d40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1313.3512587163286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.7889704258532,
        1318.9135470068036
      ],
      "voteCount": 18538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.053984819435668
      }
    },
    {
      "id": "9f0136e7bcee1c68622facf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1293.0738686928266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.275830403045,
        1297.8719069826084
      ],
      "voteCount": 26705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.9928200469560995
      }
    },
    {
      "id": "9825a103160fd2d1476510e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1250.252852912238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.5703841673796,
        1264.9353216570967
      ],
      "voteCount": 1790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.11797457841618
      }
    },
    {
      "id": "9a7719e47aaf6db74193f0ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1237.1308455801343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.9757061824114,
        1257.2859849778574
      ],
      "voteCount": 1087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.74879573178404
      }
    },
    {
      "id": "253d0330f6154a4d69faac90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1325.7219326396212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.6245531460104,
        1332.819312133232
      ],
      "voteCount": 8980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.112933921083533
      }
    },
    {
      "id": "aab26d22f3444df83a2f59fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1275.6921143676414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.7917306100796,
        1282.592498125203
      ],
      "voteCount": 9322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.395107750502417
      }
    },
    {
      "id": "9c6a6a33a7888056d84087bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1311.3057797781914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.6520442539836,
        1317.9595153023993
      ],
      "voteCount": 12285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.524839518676725
      }
    },
    {
      "id": "181cb322b0f32a7f91be22cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1317.5640338101641,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.0520277840442,
        1321.0760398362843
      ],
      "voteCount": 68709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.2108078996080454
      }
    },
    {
      "id": "0133a34d6645b8f4cc4a82be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1307.731084252795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.2648366741055,
        1315.1973318314845
      ],
      "voteCount": 8253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.511375888239758
      }
    },
    {
      "id": "f5042ef02be5d50649225792",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-4o-mini-2024-07-18",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1309.3709696032624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.7010387370642,
        1333.040900469461
      ],
      "voteCount": 740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.84709959467358
      }
    },
    {
      "id": "09a80e76251aa3f3663f21d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1448.7278978892482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.7897155131193,
        1463.6660802653769
      ],
      "voteCount": 1655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.08972661645367
      }
    },
    {
      "id": "e7bb2cbe9427991d80d10449",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1463.5372072245843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.6588808241706,
        1471.415533624998
      ],
      "voteCount": 5991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.1574104444624
      }
    },
    {
      "id": "97b393af01cea52aa1dfb6c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1391.7119269098257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.14386921346,
        1401.2799846061914
      ],
      "voteCount": 4023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.831500571556475
      }
    },
    {
      "id": "fa65876e5c1efdca1f971d9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1432.369226335627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.7897507154814,
        1437.9487019557728
      ],
      "voteCount": 15008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.103834935857714
      }
    },
    {
      "id": "4d9802534d1797213ec5a7b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1419.4551274770427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.5612110619315,
        1425.3490438921538
      ],
      "voteCount": 22718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.042984014609331
      }
    },
    {
      "id": "8ccb7ac54ae8999488101ee0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1447.6904602126426,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.9568787795772,
        1463.424041645708
      ],
      "voteCount": 1450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.44051498804565
      }
    },
    {
      "id": "8f9fb07ca29ef0efad06ba3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1446.856925802614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.4160677027417,
        1477.2977839024861
      ],
      "voteCount": 393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 241.2223806395297
      }
    },
    {
      "id": "1d3e26fe6a6ec614d3f79c7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1423.0307926490004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.5655031674903,
        1446.4960821305108
      ],
      "voteCount": 661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.33612207030788
      }
    },
    {
      "id": "1e5eb2f4ff7347e02b350e37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1448.0609415796773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.9149604541692,
        1455.2069227051854
      ],
      "voteCount": 7751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.293139046819709
      }
    },
    {
      "id": "3193e85a08aca3a8973f6717",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1448.5434099385936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.9715294437447,
        1454.1152904334429
      ],
      "voteCount": 15220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.081787075689396
      }
    },
    {
      "id": "d42aaf0185c84de4d30cb627",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1440.011528411595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.7209647730124,
        1448.3020920501779
      ],
      "voteCount": 5614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.892537354589912
      }
    },
    {
      "id": "13a7d1a0a811f92297c66b18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1391.4269814300978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.2944999708154,
        1399.55946288938
      ],
      "voteCount": 5613,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.216702761275336
      }
    },
    {
      "id": "8a44747dce3fa27086ae3531",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1457.7520214874608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.0742677306625,
        1471.429775244259
      ],
      "voteCount": 1952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.700495453391774
      }
    },
    {
      "id": "606b8f5472bf9f9ce58cb031",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1447.7863628629436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.1849329115953,
        1456.3877928142917
      ],
      "voteCount": 5034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.259505479895285
      }
    },
    {
      "id": "fd3ac3b2a079d288808fb7f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1408.4564940586652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.6756393788846,
        1423.2373487384457
      ],
      "voteCount": 1568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.872577648850545
      }
    },
    {
      "id": "1002379b26d092d8befc5046",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1457.116255556973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.3485338884614,
        1471.8839772254848
      ],
      "voteCount": 1695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.77155826942454
      }
    },
    {
      "id": "b29771723c2486aa4a00212f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1454.6744913941423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.4081979283421,
        1460.9407848599424
      ],
      "voteCount": 10752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.221750546433082
      }
    },
    {
      "id": "4f665f34ec3efb7beb852345",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1406.9902466783012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.4437292207288,
        1414.5367641358737
      ],
      "voteCount": 6781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.82507776229568
      }
    },
    {
      "id": "1c7f4ed7af8bfdedaf51d9a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1416.761701825502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.7857760019604,
        1423.737627649044
      ],
      "voteCount": 8144,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.667984577474595
      }
    },
    {
      "id": "802a183cb0d59070aef36d16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1425.9127879354953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.8485227669637,
        1454.9770531040267
      ],
      "voteCount": 466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 219.8986242507931
      }
    },
    {
      "id": "3b5efd7e6c73a3fbc6b893a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1375.1483549511825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.9456954344855,
        1397.3510144678792
      ],
      "voteCount": 783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.32575139391832
      }
    },
    {
      "id": "f01d0d21d9edf3eef72edb6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1436.2012591344564,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.6112724031327,
        1443.7912458657804
      ],
      "voteCount": 6738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.996359786895708
      }
    },
    {
      "id": "85d193bb8cdb6759f5e69f36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1412.9463158625601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.2633807875723,
        1426.6292509375482
      ],
      "voteCount": 1787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.73739925513696
      }
    },
    {
      "id": "8517a0eac95594129fa811e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1449.5592208229775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.301188273981,
        1457.8172533719737
      ],
      "voteCount": 5803,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.75239687925628
      }
    },
    {
      "id": "36a441ae3c0be11044113ffc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1426.7250409963585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.4431688365285,
        1431.0069131561884
      ],
      "voteCount": 31595,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.772777751607813
      }
    },
    {
      "id": "3a5b742ee74772d4565878b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1429.1928596006728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.7061085296345,
        1443.6796106717109
      ],
      "voteCount": 1594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.63183816097807
      }
    },
    {
      "id": "2874615c8e8c59e5f3bf79eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-chat",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1413.6387333949974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.580757970838,
        1435.6967088191566
      ],
      "voteCount": 770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.65872589645471
      }
    },
    {
      "id": "bc4574b4821391388161ba4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1454.836379177838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.9695292962047,
        1470.7032290594711
      ],
      "voteCount": 1595,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.5368017509547
      }
    },
    {
      "id": "a46563d9cf5f6222036c7e95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1467.130703784959,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.0633340852328,
        1475.1980734846854
      ],
      "voteCount": 6360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.942119363992678
      }
    },
    {
      "id": "c90db39f157c16a9a72bc0ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1375.2107593998637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.5010376233845,
        1384.9204811763432
      ],
      "voteCount": 4255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.542420308855544
      }
    },
    {
      "id": "314894f0373df23d6babfd10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1438.3509362700734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.6113152667697,
        1444.0905572733768
      ],
      "voteCount": 15150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.57571323792319
      }
    },
    {
      "id": "24e01230ca729648ecfde3d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1426.8311022386297,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.738342673856,
        1432.9238618034033
      ],
      "voteCount": 23611,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.66344319875666
      }
    },
    {
      "id": "f48661ab70c307c2cf4de4e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1458.5708403250685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.7608161298208,
        1474.380864520316
      ],
      "voteCount": 1590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.06821411381122
      }
    },
    {
      "id": "b6a578e788b6f4671bf53352",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1442.3933912001007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.7569643640757,
        1473.029818036126
      ],
      "voteCount": 444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 244.33182629028562
      }
    },
    {
      "id": "097e657843337142f02c900c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1443.069373543953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.6683937467326,
        1466.4703533411732
      ],
      "voteCount": 702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.5515360258286
      }
    },
    {
      "id": "0dda9c0def7931278a76ae20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1452.365405264547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.9272071225905,
        1459.8036034065037
      ],
      "voteCount": 7690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.402547100325235
      }
    },
    {
      "id": "6b6b3fa4e5b21965d48e79fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1446.125894365297,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.220699758713,
        1452.031088971881
      ],
      "voteCount": 14989,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.077625185977913
      }
    },
    {
      "id": "cc1c21b67880dc1fed54976a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1413.184077662604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.5456877925383,
        1421.82246753267
      ],
      "voteCount": 5545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.42537536658331
      }
    },
    {
      "id": "07f5ffbb7adc56cebd68df39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1397.3991580904553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.0247078799202,
        1405.7736083009904
      ],
      "voteCount": 5833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.256454019741238
      }
    },
    {
      "id": "d1a6b7178e3e05df3e8b6c97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1454.2936589572032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.9645941803706,
        1468.6227237340358
      ],
      "voteCount": 1869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.44899085539726
      }
    },
    {
      "id": "e5c91136d3bd1196e068bc01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1442.8470940900968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.943092409539,
        1451.7510957706545
      ],
      "voteCount": 5091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.638317271626978
      }
    },
    {
      "id": "ed5ace31a8f56a631d8b6d59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1442.015231425677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.6819636221778,
        1456.3484992291762
      ],
      "voteCount": 1749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.48035095940559
      }
    },
    {
      "id": "3f00c3a780db881207572fa6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1455.6327340248436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.6637138177787,
        1470.6017542319087
      ],
      "voteCount": 1778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.32981073555587
      }
    },
    {
      "id": "9ebfe07ba8d2ed5c4206ecd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1452.024512966364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.495705426736,
        1458.5533205059921
      ],
      "voteCount": 10928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.096130371066083
      }
    },
    {
      "id": "b60621cd7b2260a353cf8b66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1397.3470169721352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.6643244640538,
        1405.0297094802168
      ],
      "voteCount": 7026,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.364934762743555
      }
    },
    {
      "id": "a339810c510a3cc692540bc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1409.7051087560449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.505594941801,
        1416.904622570289
      ],
      "voteCount": 8266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.493050838463313
      }
    },
    {
      "id": "c100a4cdf80ecfab28730d2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1429.5185909716715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.309956603407,
        1452.7272253399362
      ],
      "voteCount": 817,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.2177491368931
      }
    },
    {
      "id": "ddd185001ce0efd1aca9f67d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1400.070200846304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.9705885873932,
        1423.1698131052146
      ],
      "voteCount": 806,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.9035029186136
      }
    },
    {
      "id": "7a5e9e9f90415108ed2eb54e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1410.888131993146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.0855301161248,
        1418.6907338701674
      ],
      "voteCount": 6805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.848301099397005
      }
    },
    {
      "id": "7f0818374cf3c4b4c64edaf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1433.9772101181272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.3572135300699,
        1447.5972067061846
      ],
      "voteCount": 1887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.290067840731126
      }
    },
    {
      "id": "4e051f8a67170cb355ad7af5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1420.196719578281,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.252770925427,
        1429.140668231135
      ],
      "voteCount": 5020,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.82391644391811
      }
    },
    {
      "id": "bde5968fef1f55c68d16500b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1433.720226939256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.2069938160803,
        1438.2334600624315
      ],
      "voteCount": 31947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.302483815367152
      }
    },
    {
      "id": "ca15481b1192404513c7a2ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1427.3225833420092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.527730775211,
        1442.1174359088077
      ],
      "voteCount": 1658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.98034853169326
      }
    },
    {
      "id": "fe05038b822e6b1f6ca0fc01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1404.7718310713894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.2300832349815,
        1427.3135789077976
      ],
      "voteCount": 817,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.27537225777007
      }
    },
    {
      "id": "640140fcc45ea5fff4ec78e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1409.0166277401877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.0495195548037,
        1425.9837359255716
      ],
      "voteCount": 1343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.94099861846323
      }
    },
    {
      "id": "6bed0fedacc36f3cc5c4b419",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1430.046263583068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.5698273798498,
        1438.5226997862858
      ],
      "voteCount": 5502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.703824265970262
      }
    },
    {
      "id": "e993c2ea29ec88684caab16d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1325.6476647963214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.3036812575135,
        1335.9916483351294
      ],
      "voteCount": 3561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.853479744394374
      }
    },
    {
      "id": "9bb35958b789f24c583418df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1397.6464374263232,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.5953033930907,
        1403.697571459556
      ],
      "voteCount": 12748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.531853599703545
      }
    },
    {
      "id": "22d850015d65593a91c848fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1366.4173518350844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.1462213871812,
        1372.688482282988
      ],
      "voteCount": 19693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.23753707387499
      }
    },
    {
      "id": "f26bb1b5cdb711d22329fa4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1403.2450746209124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.0940437821782,
        1421.3961054596466
      ],
      "voteCount": 1143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.76427234722912
      }
    },
    {
      "id": "2c8fe8683816ea90823746fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1402.911391832157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.2631748476285,
        1435.5596088166856
      ],
      "voteCount": 368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.47429349672325
      }
    },
    {
      "id": "419481aa9defb73da4476288",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1388.8130263304652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.3068983576827,
        1414.3191543032474
      ],
      "voteCount": 554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.3529970071103
      }
    },
    {
      "id": "3b5151f78371708fc9c36323",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1409.606920456738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.6966302891883,
        1417.5172106242874
      ],
      "voteCount": 6487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.288783364733064
      }
    },
    {
      "id": "24a6d37183533b902c9996c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1402.949436912673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.823401997796,
        1409.0754718275502
      ],
      "voteCount": 12811,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.76928441250679
      }
    },
    {
      "id": "be729680b12f91058b26b943",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1379.3787624228885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.2549945016672,
        1388.50253034411
      ],
      "voteCount": 4843,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.669668989258877
      }
    },
    {
      "id": "0ea60666560f4652a6ec0fc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1349.1904151904205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.171615450754,
        1358.2092149300872
      ],
      "voteCount": 4862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.173921820021974
      }
    },
    {
      "id": "05b2778fde65bac49167d72e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1393.392430366917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.5247088050817,
        1408.2601519287527
      ],
      "voteCount": 1710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.54302070074671
      }
    },
    {
      "id": "391e89c3e850f59f638ac451",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1395.8647080996827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.266299718146,
        1405.4631164812197
      ],
      "voteCount": 4212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.982931422419856
      }
    },
    {
      "id": "80e4566eee6d7222e45e93ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1409.270584434565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.71580268174,
        1425.82536618739
      ],
      "voteCount": 1283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.34289645571465
      }
    },
    {
      "id": "3384eb8fbb16e0204e810b54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1400.705463294287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.3725496187599,
        1417.0383769698142
      ],
      "voteCount": 1427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.44342802665214
      }
    },
    {
      "id": "5297079f920ce57f48cf0a03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1415.3065631915185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.3544999529286,
        1422.2586264301085
      ],
      "voteCount": 9028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.581465929816043
      }
    },
    {
      "id": "b31629430cd80b22e8a7aeff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1353.0665318702258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.054921465643,
        1361.0781422748091
      ],
      "voteCount": 6135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.708730789732773
      }
    },
    {
      "id": "0a4a93f8e85ff71264406e38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1374.408900759264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.815056428386,
        1382.0027450901423
      ],
      "voteCount": 6917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.011607416161445
      }
    },
    {
      "id": "b8b02e71810e25ac2cfce6f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1368.5195004858736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.672202773349,
        1399.366798198398
      ],
      "voteCount": 404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 247.70687923011042
      }
    },
    {
      "id": "d39f2fe3bdb366cb36801b8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1324.3368117476462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.825631236699,
        1349.8479922585934
      ],
      "voteCount": 639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.42009831164367
      }
    },
    {
      "id": "6af374d359dd90560ec17e9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1369.3989871532076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.0881631578404,
        1377.7098111485748
      ],
      "voteCount": 5775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.980095246599753
      }
    },
    {
      "id": "b526c7cfda318fedaf8d21b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1405.6747345811123,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.2378142004554,
        1421.111654961769
      ],
      "voteCount": 1460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.03333732357402
      }
    },
    {
      "id": "a15da3e1f4a8a9f5d04bba7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1372.1900023317128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.8283003669576,
        1381.5517042964682
      ],
      "voteCount": 4471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.81463052650071
      }
    },
    {
      "id": "5ebae006fb47ad7d5bed56b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1390.1684764620559,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.5278830561235,
        1394.809069867988
      ],
      "voteCount": 27039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.60597110742687
      }
    },
    {
      "id": "4bee73dcafdd6b78989d245b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1374.0749320510406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.6439028834045,
        1389.5059612186767
      ],
      "voteCount": 1398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.98599862367101
      }
    },
    {
      "id": "2a664a3ccb13b6b9e9a10479",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1373.8592152657566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.5229638209341,
        1397.1954667105786
      ],
      "voteCount": 741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.76401646225787
      }
    },
    {
      "id": "8ac721366ebae8288e42118e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1378.8326347944408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.78809378397,
        1408.8771758049118
      ],
      "voteCount": 384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 234.98219990465898
      }
    },
    {
      "id": "b9f274271912c1e916da1ff7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1382.119896828571,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.5540462581184,
        1396.6857473990235
      ],
      "voteCount": 1684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.23006043897014
      }
    },
    {
      "id": "2475a862559e9df33b2c21ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1248.3024195173834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.230033542445,
        1268.3748054923221
      ],
      "voteCount": 915,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.88220687319762
      }
    },
    {
      "id": "c94696fbb11f0aa68517ef0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1343.8763961050138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.4582759388836,
        1353.294516271144
      ],
      "voteCount": 4012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.090443397657186
      }
    },
    {
      "id": "545add97204f86d65136bdcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1292.4829559973793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.887558585609,
        1302.0783534091497
      ],
      "voteCount": 5991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.96788714584526
      }
    },
    {
      "id": "0e27d4b60f57add6df802e4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1353.7579922838818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.2595827462144,
        1387.2564018215494
      ],
      "voteCount": 324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.11388015101187
      }
    },
    {
      "id": "69a54f6d1dc5e815f3858796",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1351.517278932194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.8982364979868,
        1393.136321366401
      ],
      "voteCount": 202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 450.9080466538354
      }
    },
    {
      "id": "c3c65e016a28c0e8794bc6b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1367.1707777976576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.7875065852982,
        1380.554049010017
      ],
      "voteCount": 1975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.62602326456884
      }
    },
    {
      "id": "43b2c7742d7e31982dead634",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1354.374740219063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.612109656424,
        1364.137370781702
      ],
      "voteCount": 3813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.810614912527065
      }
    },
    {
      "id": "5d00b087862c28e7294a09f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1335.2690406552124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.737716079585,
        1350.8003652308394
      ],
      "voteCount": 1536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.794384720201705
      }
    },
    {
      "id": "2a898dd0318a1b0a18ab197f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1277.2747011989622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.0911500581653,
        1293.4582523397594
      ],
      "voteCount": 1373,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.17913187455913
      }
    },
    {
      "id": "d2d390d1ed1eeb72f2a1cc23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1327.4985966446313,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.2426577532328,
        1354.7545355360298
      ],
      "voteCount": 471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.38648141942414
      }
    },
    {
      "id": "8f0f1c20a5c9d44f2eeb878f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1345.6951761980163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.199342166044,
        1362.191010229988
      ],
      "voteCount": 1321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.83573015138981
      }
    },
    {
      "id": "c2a99065b433f8a82443945e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1353.5191872121989,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.029800829253,
        1382.0085735951448
      ],
      "voteCount": 439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.28565327953223
      }
    },
    {
      "id": "45b591f87cf52035c0695b99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1358.9125315087408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.409329500333,
        1386.4157335171485
      ],
      "voteCount": 480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.9111621450645
      }
    },
    {
      "id": "def40f61586c0e047bef2b1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1371.6175616650844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.488269055918,
        1382.746854274251
      ],
      "voteCount": 2886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.24325959534021
      }
    },
    {
      "id": "5efaf7afbf610a4fc6458ca2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1290.1528060447636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.9364853365964,
        1304.3691267529302
      ],
      "voteCount": 1738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.61120420937837
      }
    },
    {
      "id": "bf3202b576d545d7076c9e36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1325.7635050751328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.6432723159946,
        1338.8837378342714
      ],
      "voteCount": 2028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.811233359222044
      }
    },
    {
      "id": "e4fffce34da3028eb951de93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1274.12361662476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.6012188887505,
        1316.6460143607696
      ],
      "voteCount": 216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 470.6947005337604
      }
    },
    {
      "id": "d31a3b92ae70218ed8bf8169",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1328.8008159549593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.1260355247255,
        1343.4755963851928
      ],
      "voteCount": 1620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.05921883516534
      }
    },
    {
      "id": "b044b9e31d793888f0fe0197",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1344.7632837388724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.1547228441354,
        1371.3718446336093
      ],
      "voteCount": 494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.3090205925965
      }
    },
    {
      "id": "450696dcf95c140bf353e3f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1322.595854785434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.95485030805,
        1338.2368592628181
      ],
      "voteCount": 1456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.68440545129681
      }
    },
    {
      "id": "9179cccc92dcecdbcdd17657",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1337.2534708731218,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.375204502689,
        1344.1317372435547
      ],
      "voteCount": 8270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.31577649817901
      }
    },
    {
      "id": "72862a1490d470f8685b4e67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1312.824405310994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.2951252678786,
        1339.3536853541095
      ],
      "voteCount": 483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.2123504265173
      }
    },
    {
      "id": "ecdc1e7be1771b04c4c912e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1381.323109500217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.6358152578882,
        1424.0104037425458
      ],
      "voteCount": 206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 474.3523684062036
      }
    },
    {
      "id": "8e26556bf07ea49248920c80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1496.2425106873645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.4628928767315,
        1510.0221284979975
      ],
      "voteCount": 2018,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.42858322058127
      }
    },
    {
      "id": "f1f3ba556f901dfd2d02105c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1490.362508402332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.2296521772303,
        1497.495364627434
      ],
      "voteCount": 8210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.244353331055516
      }
    },
    {
      "id": "835093f375ac79015bbbc29c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1430.2769446305742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.9280726036516,
        1438.625816657497
      ],
      "voteCount": 6061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.145102518458444
      }
    },
    {
      "id": "b552a0bcbf180f917b0d45f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1463.3210375565384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.07421703478,
        1468.5678580782967
      ],
      "voteCount": 18789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.166320627789404
      }
    },
    {
      "id": "ae5bfa4b6865219e99284e38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1458.29019256545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.943536204779,
        1463.6368489261213
      ],
      "voteCount": 29411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.441634955217034
      }
    },
    {
      "id": "fb38663cb45c0bf34ff121e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1481.696978209707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.9653900791218,
        1494.428566340292
      ],
      "voteCount": 2331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.19577610819394
      }
    },
    {
      "id": "818ef971a125993ae468b5d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1472.349903330836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.4582017534892,
        1494.241604908183
      ],
      "voteCount": 862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.75640643858685
      }
    },
    {
      "id": "25d3c193f98ce0358f1e6235",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1451.0709672100475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.750751319875,
        1474.39118310022
      ],
      "voteCount": 662,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.5692565112493
      }
    },
    {
      "id": "720f8746009001c45abd7d54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1479.0326107060605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.4206486254795,
        1485.6445727866417
      ],
      "voteCount": 10364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.380583417823008
      }
    },
    {
      "id": "2e193eb46f8cc70ffd76127d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1474.2732868511246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.2773850603212,
        1479.2691886419277
      ],
      "voteCount": 21751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.497280295937383
      }
    },
    {
      "id": "7d7f2770202823a7445d561f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1445.7653720867952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.230682006843,
        1453.3000621667475
      ],
      "voteCount": 7591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.778644585515528
      }
    },
    {
      "id": "382a6a6e1935dfe6a52b9389",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1420.3298287935165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.6893029194177,
        1427.9703546676153
      ],
      "voteCount": 7343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.196736020776621
      }
    },
    {
      "id": "04c79f3cec024fcb435a3ad9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1458.2170471806946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.8466495151383,
        1469.587444846251
      ],
      "voteCount": 2949,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.65542860343024
      }
    },
    {
      "id": "bbdd3442c4ad2361c601015a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1466.6188441859827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.6815706911905,
        1474.556117680775
      ],
      "voteCount": 6638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.400100449273907
      }
    },
    {
      "id": "9484cb793ea2eddd3735adf2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1461.1565684007571,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.0070001118072,
        1475.306136689707
      ],
      "voteCount": 1721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.11829466584777
      }
    },
    {
      "id": "6e0f57378e5bfc96edbe6afa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1468.4042519004859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.880485660476,
        1480.9280181404956
      ],
      "voteCount": 2495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.82946821907292
      }
    },
    {
      "id": "16ecbeeb56b94943ce7b9261",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1480.595669026499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.7514520670752,
        1486.4398859859232
      ],
      "voteCount": 13953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.891120135096779
      }
    },
    {
      "id": "f519f26ece58a43f0372f0fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1436.7090774719682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.7271243363325,
        1443.6910306076038
      ],
      "voteCount": 9079,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.689884719212806
      }
    },
    {
      "id": "08faf04145de0560ec22f1fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1448.6939201020045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.199769754234,
        1455.188070449775
      ],
      "voteCount": 10757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.978638769275493
      }
    },
    {
      "id": "87234451aefcdbfaa10a00db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1457.5029896035658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.8550270042033,
        1489.1509522029285
      ],
      "voteCount": 369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 260.7325975473226
      }
    },
    {
      "id": "1cca7ab611cd539d10db00aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1392.4577503959654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.3537466553435,
        1417.5617541365873
      ],
      "voteCount": 618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.0551241664193
      }
    },
    {
      "id": "c08a43d905558802c7239b58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1459.2071547011076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.5772743815367,
        1465.8370350206787
      ],
      "voteCount": 10271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.44234914482141
      }
    },
    {
      "id": "df80ffafc46bc45ec0992501",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1455.2995738211582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.4349211196952,
        1467.1642265226214
      ],
      "voteCount": 2500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.64492847560942
      }
    },
    {
      "id": "977a79efec1efe85dbbe6ee3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1462.9789919207967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.2801459717384,
        1470.6778378698552
      ],
      "voteCount": 7121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.429614558935492
      }
    },
    {
      "id": "faeea21301d1b5fc3c56d9f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1454.8072906701968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.0096333974777,
        1458.604947942916
      ],
      "voteCount": 40856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.75435516407034
      }
    },
    {
      "id": "88332a5c565ed778391ce009",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1454.9741230858979,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.546919746414,
        1464.4013264253815
      ],
      "voteCount": 4125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.13500338080322
      }
    },
    {
      "id": "9e3d398e635210502decf6e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1447.0639949209565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.2135528283377,
        1466.9144370135753
      ],
      "voteCount": 965,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.57562807902485
      }
    },
    {
      "id": "9cbe385083febcc94506b0df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1478.2123431197722,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.5151666348072,
        1491.909519604737
      ],
      "voteCount": 2026,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.838905326693975
      }
    },
    {
      "id": "fbae87921b8a3e1bce016292",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1473.899625545411,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.0756875353331,
        1480.723563555489
      ],
      "voteCount": 9130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.121991185882854
      }
    },
    {
      "id": "17074cbc47f756aeb8fc5c88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1410.6371102591163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.5207297790562,
        1418.7534907391766
      ],
      "voteCount": 6450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.14859775203838
      }
    },
    {
      "id": "30cb7d89d9dfbb6a8b13254b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1442.0300378786044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9910139761703,
        1447.0690617810385
      ],
      "voteCount": 20125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.60992687270668
      }
    },
    {
      "id": "2ba30b33a402188ccb81e42a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1436.3696604200118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.2115927159775,
        1441.5277281240462
      ],
      "voteCount": 31067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.925926758885451
      }
    },
    {
      "id": "4d9aa3b54f3553573e5db857",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1456.3343618151416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.7091418932425,
        1467.9595817370405
      ],
      "voteCount": 2726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.180837421575525
      }
    },
    {
      "id": "59253faf1092e4ddea7d912a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1459.5744899526283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.172277516393,
        1481.9767023888633
      ],
      "voteCount": 834,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.6428483196715
      }
    },
    {
      "id": "aafb2180048b9c90d4273ce2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1444.2297871187936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.6337738769673,
        1466.82580036062
      ],
      "voteCount": 707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.91299952879123
      }
    },
    {
      "id": "f0ab2aa747c49f232d162d03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1457.517512931567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.2245412534307,
        1463.810484609703
      ],
      "voteCount": 11318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.308972291591019
      }
    },
    {
      "id": "cc1a82ab749fb3b480609aea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1455.318591957945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.5460923010376,
        1460.0910916148525
      ],
      "voteCount": 23606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.929193579398239
      }
    },
    {
      "id": "9208eb4b87705de0d0e11802",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1441.5763873477572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.2893676001113,
        1448.863407095403
      ],
      "voteCount": 8122,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.823044650778579
      }
    },
    {
      "id": "a1077556916025a0fe0d95ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1406.294303947445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.0118518518275,
        1413.5767560430627
      ],
      "voteCount": 7951,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.80572095144378
      }
    },
    {
      "id": "1c3948fb8f6936cb02d7a487",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1449.1258224643746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.1606885564072,
        1460.0909563723421
      ],
      "voteCount": 3060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.299089026270476
      }
    },
    {
      "id": "a41b8835587907ba8e3e35d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1455.404427920171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.7370037828873,
        1463.0718520574549
      ],
      "voteCount": 6940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.303923755293344
      }
    },
    {
      "id": "4033f8a49403b1995b2c6f4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1437.3716660218142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.2320577221867,
        1450.5112743214418
      ],
      "voteCount": 2029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.94368268054064
      }
    },
    {
      "id": "3d8eaa4603900b5c0bc809e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1461.979815694905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.9437609609038,
        1474.0158704289063
      ],
      "voteCount": 2646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.711354025057204
      }
    },
    {
      "id": "06daf41ec3cca213fc861505",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1465.6237237435223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.0156626479327,
        1471.2317848391117
      ],
      "voteCount": 15185,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.187084834136535
      }
    },
    {
      "id": "2afee3f8db49a073b3b66df0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1424.9514178807347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.2169464269841,
        1431.6858893344854
      ],
      "voteCount": 9764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.806219428167115
      }
    },
    {
      "id": "f9438206569705d51de418e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1427.6617837314866,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.5308555843867,
        1433.7927118785867
      ],
      "voteCount": 11869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.784897274549333
      }
    },
    {
      "id": "c5f59db29de0c795f1dacffc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1429.0732965227971,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.2282655455394,
        1460.9183275000546
      ],
      "voteCount": 383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.98981357797106
      }
    },
    {
      "id": "e2967b2b5bedb62269113cff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1396.0223708793599,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.3323285419185,
        1419.712413216801
      ],
      "voteCount": 671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.09504673757064
      }
    },
    {
      "id": "aec61d7e41ea2b9ce0befa01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1443.678125240453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.3761230071143,
        1449.9801274737918
      ],
      "voteCount": 11470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.338580732678436
      }
    },
    {
      "id": "2535fb39371d5f2d789affe2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1423.7921285025675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.6920677814726,
        1434.8921892236624
      ],
      "voteCount": 2867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.07410355364188
      }
    },
    {
      "id": "64c93bfbb6b4645406f98c17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1448.714428873555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.3154132045124,
        1456.1134445425978
      ],
      "voteCount": 8049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.25120909166646
      }
    },
    {
      "id": "8afb190dda17f4b9109d7f48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1438.807447321132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.131286715241,
        1442.483607927023
      ],
      "voteCount": 43501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.517975183673371
      }
    },
    {
      "id": "ad046468669c0c727272ee7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1444.6601336697595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.4221427297418,
        1453.8981246097771
      ],
      "voteCount": 4287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.215642700141828
      }
    },
    {
      "id": "4470e460d61b621539b6162b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.1",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1438.1818575839504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.9225023965903,
        1457.4412127713106
      ],
      "voteCount": 1054,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.5577869102013
      }
    },
    {
      "id": "7f74e2ae7b8173e56fb2dfde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1506.2344660420413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.9337807975626,
        1521.5351512865197
      ],
      "voteCount": 1649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.943245750660545
      }
    },
    {
      "id": "9a8457583bf1824dd088ffb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1517.5089527813695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1510.284714266976,
        1524.7331912957634
      ],
      "voteCount": 8304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.585886130472495
      }
    },
    {
      "id": "7de63f221dd6a74ab6c59b9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1431.8910127448341,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.9359348212126,
        1440.8460906684554
      ],
      "voteCount": 5046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.875772554458944
      }
    },
    {
      "id": "a34bf8e9e20456c6d3498d7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1479.5891111885815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.9195223396969,
        1485.258700037466
      ],
      "voteCount": 15065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.367716332720551
      }
    },
    {
      "id": "f2639c85ded1007bd92955dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1487.486149022747,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.7740620480556,
        1493.1982359974384
      ],
      "voteCount": 23945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.493632010492952
      }
    },
    {
      "id": "0aba4ef93f69249f0ead9f07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1494.254216271424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.1495881742055,
        1506.3588443686426
      ],
      "voteCount": 2657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.14228609783617
      }
    },
    {
      "id": "d1359149bfc1f5fc8690e4ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1486.8434631849466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.1421905149882,
        1509.5447358549047
      ],
      "voteCount": 850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.1541859200961
      }
    },
    {
      "id": "ecfd11de320e2ea14246d408",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1477.5757199494353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.248059009709,
        1503.9033808891613
      ],
      "voteCount": 539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.43815199141824
      }
    },
    {
      "id": "9d32d9fde5a252b5cc9c575c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1497.7948965788137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.0294855711436,
        1504.5603075864838
      ],
      "voteCount": 9693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.914949043871976
      }
    },
    {
      "id": "1fceb612ec0aceee97317f4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1497.319997019372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.0728392576143,
        1502.5671547811296
      ],
      "voteCount": 19903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.167241889579516
      }
    },
    {
      "id": "5bd185e2049b7b2e722d9e73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1485.0938367160672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.8908185070368,
        1493.2968549250977
      ],
      "voteCount": 6158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.516654708152526
      }
    },
    {
      "id": "8ad833f68bdcdde23ecd75dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1435.745265086512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.596945119113,
        1443.8935850539112
      ],
      "voteCount": 6192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.283829240454864
      }
    },
    {
      "id": "c5c12b495c47b011010671d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1479.8573370840238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.1312262185654,
        1492.583447949482
      ],
      "voteCount": 2400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.15947777117481
      }
    },
    {
      "id": "a566e4d71fb822681583951e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1487.3520347997503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.5810607375872,
        1496.1230088619131
      ],
      "voteCount": 5084,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.02624252659171
      }
    },
    {
      "id": "9e23fc04ac00bb072723b014",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1458.3557726384943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.4321253690725,
        1473.2794199079162
      ],
      "voteCount": 1709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.9767370204107
      }
    },
    {
      "id": "e179c94dc15a023f2d8da172",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1504.7055492490235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.6097538863892,
        1517.801344611658
      ],
      "voteCount": 2292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.644460395128405
      }
    },
    {
      "id": "5e9d4013b5f84e9eaeb784a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1509.1611023262483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.9906259490033,
        1515.331578703493
      ],
      "voteCount": 12286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.911541552137729
      }
    },
    {
      "id": "3fa54396e4acf816dc0a7a5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1451.1944447160388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.8157709018194,
        1458.5731185302582
      ],
      "voteCount": 7518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.172956108067487
      }
    },
    {
      "id": "dca5dcd87dc08cf7169b3f3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1456.1921068292154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.592138168704,
        1462.7920754897268
      ],
      "voteCount": 10042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.33933444374703
      }
    },
    {
      "id": "94d7e124850a100a14a06850",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1460.263862651544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.9246247146277,
        1500.6031005884604
      ],
      "voteCount": 225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 423.6031656945141
      }
    },
    {
      "id": "8f991b42cac697e31d16896a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1426.916933588622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.8447934887272,
        1454.9890736885166
      ],
      "voteCount": 483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.14213130253566
      }
    },
    {
      "id": "eb1489a2e108a0ae7bd8da93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1472.2509681060658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.7488505522397,
        1478.7530856598921
      ],
      "voteCount": 11474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.00559309812835
      }
    },
    {
      "id": "cf4251159b8ff784078b7872",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1456.5523208318725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.9676799645194,
        1470.1369616992258
      ],
      "voteCount": 1985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.03968390883752
      }
    },
    {
      "id": "da5ff2a4ce77ef2dfa4563d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1496.4388549726095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.140669838038,
        1504.7370401071807
      ],
      "voteCount": 6006,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.925449612180923
      }
    },
    {
      "id": "c1c8034688f352aaea0b717f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1476.3326167679527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.0925852202645,
        1480.572648315641
      ],
      "voteCount": 32280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.679958412815351
      }
    },
    {
      "id": "ff4ca5017bb5a7f320a06740",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1478.7841521682133,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.2810858119194,
        1489.2872185245071
      ],
      "voteCount": 3521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.71679953731191
      }
    },
    {
      "id": "b6e6487a1c4121c02e2abe3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-chat-latest-20260210",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1473.876867283041,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.2315295005296,
        1494.5222050655523
      ],
      "voteCount": 954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.95523655176707
      }
    },
    {
      "id": "8849f4b20a3f570302b4a29a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1473.726359797982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.8739491956417,
        1486.5787704003221
      ],
      "voteCount": 2391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.00045008976559
      }
    },
    {
      "id": "425965b6d8ec4e5c8c42d384",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1491.205419654681,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.8159273170663,
        1497.5949119922957
      ],
      "voteCount": 11036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.627632427688077
      }
    },
    {
      "id": "10df27411706fff8eed1f995",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1387.0339864320433,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.2862357584872,
        1394.7817371055994
      ],
      "voteCount": 7126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.626261610880173
      }
    },
    {
      "id": "8e3d43923d845cdfc3c6f037",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1445.7627896493052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.825280402953,
        1450.7002988956574
      ],
      "voteCount": 21301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.346286318750195
      }
    },
    {
      "id": "cdcbc31acc7599dea36dd332",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1434.9524010377208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.8947487916134,
        1440.0100532838283
      ],
      "voteCount": 33730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.658888572423402
      }
    },
    {
      "id": "a61879664bcdbea78ebb0702",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1479.215666047213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.6512301539271,
        1489.7801019404992
      ],
      "voteCount": 3480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.05336512840258
      }
    },
    {
      "id": "0c463d09da006ae9c388673f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1475.9517991032174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.5491955073162,
        1495.3544026991183
      ],
      "voteCount": 1233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.99949547074655
      }
    },
    {
      "id": "67647ffe3c1fa96769a4542c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1462.6773712442757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.2477112191839,
        1485.1070312693676
      ],
      "voteCount": 773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.96317631495583
      }
    },
    {
      "id": "c724d1fcb4348e676962742a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1462.3972167734134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.4263902337598,
        1468.3680433130671
      ],
      "voteCount": 13048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.280528890373432
      }
    },
    {
      "id": "3b92854cca0f9d0acd60c40a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1460.597192028605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.9695936861747,
        1465.2247903710354
      ],
      "voteCount": 27018,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.574618242294576
      }
    },
    {
      "id": "fb60f859d53697313d16cc75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1445.0316820303294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.075640215886,
        1451.9877238447725
      ],
      "voteCount": 8999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.595870470775711
      }
    },
    {
      "id": "e0acdabff5a5bf1da137198a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1390.9732951801982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.8999856178038,
        1398.0466047425923
      ],
      "voteCount": 8582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.024142780324764
      }
    },
    {
      "id": "a0065a5cf6fb725e5f2eecae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1448.3728661831813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.659030079405,
        1459.0867022869572
      ],
      "voteCount": 3420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.880909679472666
      }
    },
    {
      "id": "9abcea272cd141418b7d0f69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1450.8518280263436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.4195103832467,
        1458.2841456694405
      ],
      "voteCount": 7535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.379783339160843
      }
    },
    {
      "id": "2f7063b6c163fd9beae548e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1463.2089565736137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.2453032530361,
        1476.1726098941915
      ],
      "voteCount": 2289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.74804345442933
      }
    },
    {
      "id": "5166568d4850f92eeedd40eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1455.0286439346842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.6824459776715,
        1466.3748418916966
      ],
      "voteCount": 3195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.51232281502277
      }
    },
    {
      "id": "b7d80005f7344c2c357b8b4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1474.0422535705607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.6295825482252,
        1479.454924592896
      ],
      "voteCount": 16828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.626531732737895
      }
    },
    {
      "id": "7b1361dd2e39deead286d581",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1408.861192707065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.381400403854,
        1415.3409850102757
      ],
      "voteCount": 10576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.930146658493673
      }
    },
    {
      "id": "45a7a70c498fef10ce0ef426",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1427.3369818776089,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.51549044433,
        1433.1584733108875
      ],
      "voteCount": 13729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.822107456982682
      }
    },
    {
      "id": "375ee0f07e4444160fca796d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1438.1429825888627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.912463163987,
        1471.3735020137383
      ],
      "voteCount": 365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 287.46043437932775
      }
    },
    {
      "id": "76bd60c7a21493818d8fe98f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1382.6812176373228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.22023788131,
        1406.1421973933357
      ],
      "voteCount": 719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.28347557623675
      }
    },
    {
      "id": "87011a7eef2a83621fa9a417",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1435.4361031065275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.6017103831418,
        1441.270495829913
      ],
      "voteCount": 14850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.861252987359437
      }
    },
    {
      "id": "3e63394c06df883e1b5d49f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1460.136409191935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.9117368048842,
        1471.3610815789857
      ],
      "voteCount": 2889,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.79828733758352
      }
    },
    {
      "id": "97b0287b0b4356c45e24e4f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1443.948566883926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.760422845745,
        1451.136710922107
      ],
      "voteCount": 8477,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.45046689952587
      }
    },
    {
      "id": "bdee1c1e944b897b5c6ecba0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1438.2108268775576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.513877563383,
        1441.9077761917322
      ],
      "voteCount": 46111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.557876023022388
      }
    },
    {
      "id": "d002739298577d761fafe289",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1430.528604783629,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.8122080312014,
        1439.2450015360564
      ],
      "voteCount": 5158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.777791691126474
      }
    },
    {
      "id": "1135841e6a2517254970f0cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1429.6994989064128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.4810693296574,
        1447.917928483168
      ],
      "voteCount": 1249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.4023777777257
      }
    },
    {
      "id": "5609360f521b90a8d2deea45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1473.8441036510396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.3914742570664,
        1487.296733045013
      ],
      "voteCount": 2213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.11054993917491
      }
    },
    {
      "id": "6a034f8bc980cd1a22cb93a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1482.5588232106281,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.2783176009661,
        1488.8393288202903
      ],
      "voteCount": 11360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.268169607990028
      }
    },
    {
      "id": "5e5c7f75e087491f914a0ac0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1390.9984682899506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.3021579577103,
        1398.6947786221908
      ],
      "voteCount": 7249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.419452737864892
      }
    },
    {
      "id": "f0b0a1b9f42b9b6be1a6ccf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1437.8738949601752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.97309152865,
        1442.7746983917002
      ],
      "voteCount": 21924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.252279510342004
      }
    },
    {
      "id": "dee0c49ff8795916bd44ffde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1431.8322962426093,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.7726722652417,
        1436.891920219977
      ],
      "voteCount": 34038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.66408153445403
      }
    },
    {
      "id": "63326c6a292dcff3cdb597ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1461.5157451635769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.2140068152166,
        1471.8174835119369
      ],
      "voteCount": 3710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.626435151762458
      }
    },
    {
      "id": "75927b3fe5fe39b9fd68546a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1473.4972838763106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.9641490585766,
        1493.0304186940446
      ],
      "voteCount": 1244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.3225161629691
      }
    },
    {
      "id": "929ee4571097fec90af9134e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1436.019849443664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.8232752664323,
        1459.216423620896
      ],
      "voteCount": 690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.07206081740333
      }
    },
    {
      "id": "c3f17fdf39c0458214028cf2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1456.9637535379302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.091210649608,
        1462.8362964262521
      ],
      "voteCount": 13675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.977516507374663
      }
    },
    {
      "id": "64201f0663070dabc33169bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1459.497922567847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.8852978368711,
        1464.1105472988224
      ],
      "voteCount": 27760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.5386008029531855
      }
    },
    {
      "id": "69c20539f15b14fc9e6b4477",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1443.2536853546349,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.3085898238353,
        1450.1987808854346
      ],
      "voteCount": 8976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.556259010793616
      }
    },
    {
      "id": "45b909ba86b50c626bc08ced",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1400.2648639786712,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.262494948601,
        1407.2672330087416
      ],
      "voteCount": 8823,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.764206079509032
      }
    },
    {
      "id": "334e427f9f72932167e9e3f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1451.0402876371495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.372923913529,
        1461.7076513607703
      ],
      "voteCount": 3506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.622248766278897
      }
    },
    {
      "id": "2918d4c062e404c8aa022838",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1455.2493058393468,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.8316372099516,
        1462.666974468742
      ],
      "voteCount": 7473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.323154422249267
      }
    },
    {
      "id": "34e53f3cc73e423e7ca071c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1435.2883494428904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.4467223396246,
        1448.129976546156
      ],
      "voteCount": 2275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.92832341998946
      }
    },
    {
      "id": "8f61e5947b6ab132bb7b64e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1462.1420709155511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.9145651757333,
        1473.3695766553687
      ],
      "voteCount": 3174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.81484743727183
      }
    },
    {
      "id": "a0bfb35adb20d6fb59676144",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1470.9453874616577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.5964812319455,
        1476.2942936913698
      ],
      "voteCount": 17258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.4478991418899545
      }
    },
    {
      "id": "8eefacd726f8b5af504661bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1411.1729371051579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.738225626873,
        1417.6076485834428
      ],
      "voteCount": 10669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.77859056713523
      }
    },
    {
      "id": "c05999e33daa2e04ccb457a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1423.4707123514088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.74157333678,
        1429.1998513660374
      ],
      "voteCount": 14174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.544419029594167
      }
    },
    {
      "id": "88d7420c32c3e7101e054ef9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1403.806908076952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.9519084001986,
        1438.6619077537052
      ],
      "voteCount": 325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 316.2525121763408
      }
    },
    {
      "id": "656259e671302da958da4a16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1386.8366367964456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.9304855405878,
        1409.7427880523035
      ],
      "voteCount": 724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.58659114857528
      }
    },
    {
      "id": "5fa23e8ed6db40702ebcee36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1440.5873726425357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.8342487157324,
        1446.3404965693387
      ],
      "voteCount": 15663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.616110821975115
      }
    },
    {
      "id": "1bde966588a1ce91672301ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1432.7682442002883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.4248349219222,
        1444.1116534786545
      ],
      "voteCount": 2794,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.495851462302404
      }
    },
    {
      "id": "63a5d29a890e0807e0c4d01b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1447.0010033094984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.0527826422694,
        1453.9492239767271
      ],
      "voteCount": 8818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.567561620192592
      }
    },
    {
      "id": "220f5f2a9af655cdd00115a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1434.9768543292814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.275217552125,
        1438.6784911064376
      ],
      "voteCount": 46492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.5669039991219678
      }
    },
    {
      "id": "49217297246f0e98fefa6355",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1442.096213190725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.3104701611996,
        1450.8819562202502
      ],
      "voteCount": 5037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.09374151429916
      }
    },
    {
      "id": "f113c8d59d1786609188238c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.2",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1420.182521523206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.1810552746201,
        1438.183987771792
      ],
      "voteCount": 1299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.35669942712696
      }
    },
    {
      "id": "2134e423e67f561d3d1f8b15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1488.1244024623934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.1179429995823,
        1504.1308619252043
      ],
      "voteCount": 1561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.69516881306
      }
    },
    {
      "id": "bbf9e4b77fb1c985c80965be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1496.62533546369,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.1062690319736,
        1504.1444018954062
      ],
      "voteCount": 7910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.717419252290236
      }
    },
    {
      "id": "e29b4ad9dd1974bbfc31c56a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1406.2430990237033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.0945146597714,
        1415.3916833876349
      ],
      "voteCount": 4847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.787711328076323
      }
    },
    {
      "id": "eded659fb2640f65c97eb851",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1450.201925557216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.28003525938,
        1456.1238158550523
      ],
      "voteCount": 14396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.129027886668634
      }
    },
    {
      "id": "734548fc535f2e91be8359c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1451.3647545893348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.4083676145424,
        1457.3211415641272
      ],
      "voteCount": 23174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.235695981524259
      }
    },
    {
      "id": "aecb9a59af16d905d4e5272b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1469.0772604274975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.718614503173,
        1481.435906351822
      ],
      "voteCount": 2557,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.75992876977552
      }
    },
    {
      "id": "3a2cede21ca7f4c600ad6908",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1470.051374233632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.5040906962681,
        1492.598657770996
      ],
      "voteCount": 875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.34034741583315
      }
    },
    {
      "id": "a909aeff26b440153f7544d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1441.3447622332124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.6705883210298,
        1468.018936145395
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.21910219742912
      }
    },
    {
      "id": "cd6348fa61dd9bec62bf0b65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1467.9502191876973,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.872566219304,
        1475.0278721560903
      ],
      "voteCount": 9176,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.040142789283667
      }
    },
    {
      "id": "0b2599bcba8e6ba573d77795",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1471.5911997313558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.0862568011244,
        1477.0961426615872
      ],
      "voteCount": 18848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.888773010361006
      }
    },
    {
      "id": "3a67bb9830c0d2e6e392e436",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1457.9707035039244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.605611844356,
        1466.3357951634925
      ],
      "voteCount": 6014,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.21567319582356
      }
    },
    {
      "id": "060fe492bfe479189f422eae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1414.8051909273977,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.35216294722,
        1423.2582189075756
      ],
      "voteCount": 5942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.60066328154913
      }
    },
    {
      "id": "6ef6bca9b0afef233841dae2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1464.1449413106684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.2339699508225,
        1477.0559126705145
      ],
      "voteCount": 2371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.3931975417209
      }
    },
    {
      "id": "1ed37c97677383c54d786310",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1459.9059427056884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.8341541720622,
        1468.9777312393144
      ],
      "voteCount": 4844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.423462033612882
      }
    },
    {
      "id": "7e26b7c7c6951312d6ceb9bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1426.186555725103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.1149607533105,
        1441.2581506968959
      ],
      "voteCount": 1691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.13195626882245
      }
    },
    {
      "id": "5c3b63f691ef54640dbbbb39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1482.2246846516102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.1010600434138,
        1495.3483092598067
      ],
      "voteCount": 2310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.83440559848031
      }
    },
    {
      "id": "e076c14ac9f538bac53b7b06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1488.3123652018082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.89536904313,
        1494.7293613604863
      ],
      "voteCount": 11726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.71932347124575
      }
    },
    {
      "id": "96141cea44fe65951f6fccff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1424.755375076102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.1214703246767,
        1432.3892798275274
      ],
      "voteCount": 7111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.170409074775563
      }
    },
    {
      "id": "6bcb8f704fc65feebb736866",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1432.3042881698805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.4427671442643,
        1439.1658091954969
      ],
      "voteCount": 9648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.255883241895106
      }
    },
    {
      "id": "f19f9d4308135af218d8de11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1422.197997583191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.8180381162606,
        1465.577957050121
      ],
      "voteCount": 221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 489.8714189554889
      }
    },
    {
      "id": "4768e16e875d5e442311be3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1422.2701192332668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.1626436561824,
        1450.3775948103512
      ],
      "voteCount": 512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.65889683900042
      }
    },
    {
      "id": "0088e41f8976e78ab401b576",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1454.503177832936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.8022453473511,
        1461.2041103185206
      ],
      "voteCount": 11016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.688917745121488
      }
    },
    {
      "id": "ff9c9602a38d38d92366421b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1427.6072080315214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.9230340097863,
        1441.2913820532563
      ],
      "voteCount": 1944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.74622569123073
      }
    },
    {
      "id": "98e4a8fab31853f23e5334b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1466.6031686535969,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.0885836676155,
        1475.1177536395783
      ],
      "voteCount": 5741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.872558803168424
      }
    },
    {
      "id": "b49cf34bdb4661e7cd6e5ace",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1448.536889311787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.0855275111678,
        1452.988251112406
      ],
      "voteCount": 30882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.158098213436319
      }
    },
    {
      "id": "ce9e10cd4e6e08db0040da5f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1456.9707329121493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.1316251575272,
        1467.8098406667714
      ],
      "voteCount": 3309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.583760597251075
      }
    },
    {
      "id": "b0853e5b4bbdb4f5dd40f31d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.3-chat-latest",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1434.1709034814348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.2605774827068,
        1454.0812294801628
      ],
      "voteCount": 1076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.19545252966972
      }
    },
    {
      "id": "df4074f2d03ceffb1a61aea4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1507.865526874996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.6593967374547,
        1524.0716570125373
      ],
      "voteCount": 1545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.369509161488
      }
    },
    {
      "id": "5eb3253806fa907819913cdc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1521.3140925246491,
      "unit": "Arena rating",
      "confidenceInterval": [
        1513.5681320686,
        1529.0600529806984
      ],
      "voteCount": 7181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.619041147455466
      }
    },
    {
      "id": "868bbc5e8926944fbcd8007f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1445.5309376774132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.8696699392892,
        1455.1922054155375
      ],
      "voteCount": 4460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.298085353639692
      }
    },
    {
      "id": "226594a2abac670dc41f7c39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1482.703690856325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.6244560957846,
        1488.7829256168652
      ],
      "voteCount": 13071,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.620588687472296
      }
    },
    {
      "id": "5f8c5fe7f4cde1bc658c9079",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1492.2378529631544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.0150074462958,
        1498.460698480013
      ],
      "voteCount": 21183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.08049497187903
      }
    },
    {
      "id": "7f33cf7553d6aff850f7d5e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1527.359315580999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1514.6273926321282,
        1540.0912385298698
      ],
      "voteCount": 2446,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.19799548617636
      }
    },
    {
      "id": "0c5ea32479868f16d2d34d86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1508.5971573691804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.2878062086866,
        1530.906508529674
      ],
      "voteCount": 905,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.56201600315296
      }
    },
    {
      "id": "9b9cc87611484b80d18841f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1483.1335563823288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.6593445313474,
        1510.6077682333105
      ],
      "voteCount": 488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.49626666991543
      }
    },
    {
      "id": "0b57b88b6f12abed7243b55d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1500.5128907008407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.2735390755283,
        1507.752242326153
      ],
      "voteCount": 8468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.642788951058956
      }
    },
    {
      "id": "ff771aad567d0b1fe8a15f23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1503.2383466791366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.5759822388848,
        1508.9007111193887
      ],
      "voteCount": 17428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.346404985915402
      }
    },
    {
      "id": "bfc452e6b280203decb9ba39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1481.9810591120458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.213364111337,
        1490.7487541127546
      ],
      "voteCount": 5487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.011271554269424
      }
    },
    {
      "id": "ff33dea0ede80ded87ed9df3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1448.8759687455888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.0432694085773,
        1457.7086680826003
      ],
      "voteCount": 5430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.309101625081713
      }
    },
    {
      "id": "29c4332ec3a25c8a312d12e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1484.663673930352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.1069844099222,
        1498.2203634507814
      ],
      "voteCount": 2161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.84219728277988
      }
    },
    {
      "id": "96e71052e3a7edbc6325c928",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1491.3285200272471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.0207347874182,
        1500.636305267076
      ],
      "voteCount": 4591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.55259528074893
      }
    },
    {
      "id": "8fa9a8cfe792ceeab4c89a6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1514.148959607339,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.5874991767544,
        1529.710420037924
      ],
      "voteCount": 1554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.03830446603657
      }
    },
    {
      "id": "797f40a0171415a7caac2aa2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1476.4679826948484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.3690478846408,
        1490.566917505056
      ],
      "voteCount": 2012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.74595695563455
      }
    },
    {
      "id": "612ee49d166ce6d59a6de643",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1507.4226526296025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.8664714919971,
        1513.978833767208
      ],
      "voteCount": 10750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.18937182862379
      }
    },
    {
      "id": "62e72fbcd5c879b3c5a78e6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1471.7071528551153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.7331441096917,
        1479.681161600539
      ],
      "voteCount": 6710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.55225747300985
      }
    },
    {
      "id": "b6afaf69ec154b8b9585528d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1478.5450790950292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.4676622864367,
        1485.622495903622
      ],
      "voteCount": 8922,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.039272583819699
      }
    },
    {
      "id": "004bcb48f89f5b4559a8fae8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1498.8933174097863,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.624865909703,
        1540.1617689098698
      ],
      "voteCount": 241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 443.3433153155596
      }
    },
    {
      "id": "96653cda9160fbec8714feb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1428.418644901527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.7050478690553,
        1457.1322419339986
      ],
      "voteCount": 496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 214.6243635625338
      }
    },
    {
      "id": "dc849841f0f754734f05ea8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1487.7653426940797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.902041097688,
        1494.6286442904714
      ],
      "voteCount": 10627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.262244892298725
      }
    },
    {
      "id": "bc38d0cbaa74daf5e4f61382",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1514.759509961718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.1128217651346,
        1529.4061981583018
      ],
      "voteCount": 1682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.844793642530526
      }
    },
    {
      "id": "bb7c8a8d88f1c39fd8552abc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1496.8199128943058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.929203758156,
        1505.7106220304556
      ],
      "voteCount": 5201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.576742491107357
      }
    },
    {
      "id": "a725aad10a775d20431df295",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1480.4254903832507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.7491167061185,
        1485.1018640603831
      ],
      "voteCount": 28246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.692751579262197
      }
    },
    {
      "id": "92b4060d0ce68beb7c9131eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1493.7550112728566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.4973834945365,
        1505.0126390511766
      ],
      "voteCount": 3164,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.99116015834426
      }
    },
    {
      "id": "5f9435f506316fb8a1b75e7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1461.2962026935813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.3978440514306,
        1482.194561335732
      ],
      "voteCount": 929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.69154644668039
      }
    },
    {
      "id": "1d03af176fb3bcd200c99e5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1487.7457694324507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.2232876587882,
        1504.2682512061135
      ],
      "voteCount": 1449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.06477427023115
      }
    },
    {
      "id": "ebf8500d2d567e3e971412ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1498.6683373209896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.8144564017393,
        1506.5222182402401
      ],
      "voteCount": 6903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.057297077212787
      }
    },
    {
      "id": "342ddeaa8b58fa576489c186",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1404.981233373829,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.0432954956852,
        1414.9191712519723
      ],
      "voteCount": 4166,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.70966236519345
      }
    },
    {
      "id": "b37da8a9337d2367b7a45d4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1452.977484477617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.8065978597376,
        1459.1483710954965
      ],
      "voteCount": 12480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.91285952242535
      }
    },
    {
      "id": "b2fe914f75225939c9275a53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1453.8426062384717,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.6454078089182,
        1460.0398046680252
      ],
      "voteCount": 19842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.997573882184799
      }
    },
    {
      "id": "d14b4e6d3e9c3996bbc40ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1488.0550318753992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.2277812696389,
        1500.8822824811596
      ],
      "voteCount": 2331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.832258728534384
      }
    },
    {
      "id": "bf7075bc9e412c378186d575",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1463.9096878707815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.4443813760192,
        1487.3749943655434
      ],
      "voteCount": 810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.33632991896232
      }
    },
    {
      "id": "55c90a698119bd1476aa8087",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1441.4447950505087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.0692256365098,
        1471.8203644645073
      ],
      "voteCount": 377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 240.18875648338533
      }
    },
    {
      "id": "84e3a7797898982b6b077fe3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1470.3297266996544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.0212558543046,
        1477.638197545004
      ],
      "voteCount": 8321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.904547358306907
      }
    },
    {
      "id": "b5ec7a92fb370ba8fd16751d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1474.0262926270348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.3448351753498,
        1479.70775007872
      ],
      "voteCount": 16739,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.402786618828022
      }
    },
    {
      "id": "2dc568bd5d41de9705512e89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1462.3408827314095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.5093396982156,
        1471.1724257646033
      ],
      "voteCount": 5292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.303784574492003
      }
    },
    {
      "id": "dc243b28f7dfc89e252bfec8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1412.168854988901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.262506708149,
        1421.0752032696532
      ],
      "voteCount": 5243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.649196932878926
      }
    },
    {
      "id": "b72b7873bedc229eb0cab03e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1462.658350408155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.6551006685443,
        1476.6616001477657
      ],
      "voteCount": 1999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.045973007326644
      }
    },
    {
      "id": "9a30b17e8f542699a4654402",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1470.1262750084136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.61904886234,
        1479.633501154487
      ],
      "voteCount": 4338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.52943327302215
      }
    },
    {
      "id": "8aff4925345507c870988111",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1460.086410425203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.8611337914595,
        1476.3116870589467
      ],
      "voteCount": 1436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.53115291079422
      }
    },
    {
      "id": "d8f643f19c23712c3e3fe3d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1457.7723314779873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.1602044368992,
        1472.3844585190757
      ],
      "voteCount": 1914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.58155550560354
      }
    },
    {
      "id": "9235bb8e4b9e19c04f21d602",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1486.9010756547252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.2246565453524,
        1493.5774947640978
      ],
      "voteCount": 10161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.603553286545717
      }
    },
    {
      "id": "a46fb120cce528558d5f1ddf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1425.6773379775707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.569912069194,
        1433.7847638859473
      ],
      "voteCount": 6241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.110779505359606
      }
    },
    {
      "id": "fb54141e555e7550ee9f7e48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1435.521593593057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.381666594246,
        1442.6615205918679
      ],
      "voteCount": 8553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.270624501745452
      }
    },
    {
      "id": "93a8567a2796f1c77a7009c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1417.1087150098606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.8313236686586,
        1466.3861063510624
      ],
      "voteCount": 157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 632.1195698656967
      }
    },
    {
      "id": "92a34250579e73834604258e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1390.2948553702377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.40916755723,
        1420.1805431832454
      ],
      "voteCount": 427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.50394648124148
      }
    },
    {
      "id": "da5e5fcc789f48b0e4ce055c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1448.0780817345171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.1505959780136,
        1455.0055674910207
      ],
      "voteCount": 10171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.4926651948044
      }
    },
    {
      "id": "f29829614ad51d68cbd83c74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1439.3348299832276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.1964082846293,
        1454.4732516818258
      ],
      "voteCount": 1586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.65749529580501
      }
    },
    {
      "id": "45804e35909a404bb468e900",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1472.9514922416256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.9024006230331,
        1482.000583860218
      ],
      "voteCount": 4970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.316396437872708
      }
    },
    {
      "id": "ffa64fea19b6131570d2b81f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1451.4141701947265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.7022402723903,
        1456.1261001170626
      ],
      "voteCount": 26397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.779648989962473
      }
    },
    {
      "id": "bea32714e8bdbc1ab708a923",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1455.346787389857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.6172834729614,
        1467.0762913067524
      ],
      "voteCount": 2807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.81484757699632
      }
    },
    {
      "id": "72035ef54a14d766053066e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1439.2437537368796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.8757993928884,
        1462.6117080808708
      ],
      "voteCount": 736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.14945824258223
      }
    },
    {
      "id": "74df46e18013e60ea82c2e75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1437.3399665940585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.5714959511856,
        1454.1084372369314
      ],
      "voteCount": 1390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.19656953919454
      }
    },
    {
      "id": "e0481d903c7fc52b7bbacc79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1460.1022037838522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.2326311819577,
        1467.9717763857466
      ],
      "voteCount": 6894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.121524615301606
      }
    },
    {
      "id": "a254bd39965f2a9c44a57344",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1336.6596813531182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.5003423110354,
        1346.8190203952008
      ],
      "voteCount": 4015,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.867962039832065
      }
    },
    {
      "id": "380ea3dfd875040ab783f66d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1415.4744017872024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.2817139227868,
        1421.667089651618
      ],
      "voteCount": 12206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.983025922206819
      }
    },
    {
      "id": "760a2088b94d5405d7d0c719",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1388.8904661959427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.4872890157942,
        1395.2936433760915
      ],
      "voteCount": 19127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.673205132254433
      }
    },
    {
      "id": "3ca2cda716895cc722bfe7f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1436.6873466244137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.7275400237033,
        1449.647153225124
      ],
      "voteCount": 2326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.72208449119
      }
    },
    {
      "id": "d5cf0c1f445c9ad048ee9b47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1424.488481555258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.7979030925703,
        1448.1790600179456
      ],
      "voteCount": 775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.10165931580693
      }
    },
    {
      "id": "ca980ce11ab7dc5982db8b3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1392.1457367275618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.4610167358876,
        1424.830456719236
      ],
      "voteCount": 356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.0951119869407
      }
    },
    {
      "id": "7a0c2bdd337cdcb8fe8934f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1432.6455473123217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.3147980826197,
        1439.9762965420236
      ],
      "voteCount": 8205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.989446920340653
      }
    },
    {
      "id": "82c39199de55e89ce35a89eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1422.286096835274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.5228904517185,
        1428.04930321883
      ],
      "voteCount": 16238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.64633707395978
      }
    },
    {
      "id": "41074a850ed548e487c95504",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1401.5552148824868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.5249589560874,
        1410.585470808886
      ],
      "voteCount": 5057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.22774859826142
      }
    },
    {
      "id": "995180cafac38bad934dcb80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1352.6311144619094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.4339510850898,
        1361.828277838729
      ],
      "voteCount": 4978,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.019711294113765
      }
    },
    {
      "id": "ec7aa82022d20a8e1dc8e83d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1395.5395778543857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.328394560102,
        1409.7507611486697
      ],
      "voteCount": 1971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.57318639881656
      }
    },
    {
      "id": "518d82799ce243682b70dbb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1417.390988753008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.6334373470802,
        1427.148540158936
      ],
      "voteCount": 4225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.784805430276688
      }
    },
    {
      "id": "9cb84e06e485a99b108d8c2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1445.7774837910185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.1686562217096,
        1462.3863113603272
      ],
      "voteCount": 1377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.8094781443432
      }
    },
    {
      "id": "acc5aaa78076d2512d8cbdc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1423.2699879274182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.5713636018963,
        1437.9686122529401
      ],
      "voteCount": 1862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.241539255595704
      }
    },
    {
      "id": "a276a482bfe4bca8d6657a6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1449.6909620667993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.9246138018311,
        1456.4573103317675
      ],
      "voteCount": 9891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.91825058652227
      }
    },
    {
      "id": "e3054c8790339ad4df8dfc46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1361.823947432354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.500114328689,
        1370.1477805360194
      ],
      "voteCount": 5967,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.03642854751558
      }
    },
    {
      "id": "bd2b570c3d2ef77847b0f026",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1385.331129622272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.0926890672695,
        1392.569570177275
      ],
      "voteCount": 8312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.639355285042603
      }
    },
    {
      "id": "6b8ff30918e27e7c51ae9980",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1389.0690433395196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.287526741544,
        1437.850559937495
      ],
      "voteCount": 169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 619.4616349339335
      }
    },
    {
      "id": "049b52acd6fc1056668e1ee5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1313.4451159085143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.3750622448274,
        1343.5151695722013
      ],
      "voteCount": 411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 235.38144479540108
      }
    },
    {
      "id": "f41c9d81bd7a3132e267a2f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1402.4835972451613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.4548140194586,
        1409.5123804708637
      ],
      "voteCount": 10020,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.860685468701911
      }
    },
    {
      "id": "1a9ff5843e447681f951eee2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1436.7295835379552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.2496060765563,
        1452.2095609993542
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.37987009375785
      }
    },
    {
      "id": "53b7c79980eade209c3def24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1413.9599955865635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.7459571114152,
        1423.174034061712
      ],
      "voteCount": 4851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.100589641664957
      }
    },
    {
      "id": "a6d5db0bf83180cb7fcb8e9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1402.8103935001786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.0737726458897,
        1407.5470143544676
      ],
      "voteCount": 25617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.8403794403376645
      }
    },
    {
      "id": "01cbf78f85bf8db013bfc530",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1392.6338621475145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.747931194938,
        1404.519793100091
      ],
      "voteCount": 2748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.77648549773773
      }
    },
    {
      "id": "6c78992e5ef38a898759d48c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4-nano-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1385.6998292420865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.6135848453523,
        1408.7860736388204
      ],
      "voteCount": 754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.74278112121638
      }
    },
    {
      "id": "860733f87d4b86f2bf05c05e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1508.27199962491,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.5053401103512,
        1524.0386591394686
      ],
      "voteCount": 1662,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.71175765541697
      }
    },
    {
      "id": "45b5e7356066951459d136a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1513.306352832743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1505.7635964296085,
        1520.8491092358774
      ],
      "voteCount": 7884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.81030431734413
      }
    },
    {
      "id": "7699be5b155566145fb0ac76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1441.1737543727916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.7206932233285,
        1450.626815522255
      ],
      "voteCount": 4580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.262091113433506
      }
    },
    {
      "id": "c569110f8f353ba37ea02ecd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1475.8632752411256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.8923359087046,
        1481.834214573547
      ],
      "voteCount": 14049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.280879524047961
      }
    },
    {
      "id": "47d65a2943cb714434640fa9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1476.8626628783052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.8085311914517,
        1482.9167945651586
      ],
      "voteCount": 22464,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.541299853147965
      }
    },
    {
      "id": "1e6c606625bb1490142f343e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1500.2414427824995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.639465404999,
        1512.8434201599998
      ],
      "voteCount": 2533,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.3410220532663
      }
    },
    {
      "id": "cf977785baac2b72cd394508",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1472.549438886483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.2999394126757,
        1494.7989383602899
      ],
      "voteCount": 900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.86776871539908
      }
    },
    {
      "id": "614cca2f8eab669ae39e167f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1452.542974523301,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.3369711885805,
        1481.7489778580214
      ],
      "voteCount": 431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 222.04862022536827
      }
    },
    {
      "id": "c945db00e16b34e67d26b292",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1494.0461853020436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.037738961461,
        1501.0546316426262
      ],
      "voteCount": 9328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.786371636791559
      }
    },
    {
      "id": "7198bcf8caa26204c35198d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1491.6003274312461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.9866959121669,
        1497.2139589503254
      ],
      "voteCount": 18711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.20335718874278
      }
    },
    {
      "id": "34491c17a2e6fa7c7639336b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1479.0073160397646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.5050598142807,
        1487.5095722652488
      ],
      "voteCount": 5907,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.817945030248186
      }
    },
    {
      "id": "e4ae666d79534063b0c465a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1437.2442341550855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.708990700757,
        1445.779477609414
      ],
      "voteCount": 5812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.964248798453465
      }
    },
    {
      "id": "7540056a3a6121952cdbb22f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1480.6207123443282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.1496822156728,
        1494.0917424729837
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.23951529808488
      }
    },
    {
      "id": "bfe9d4d2175f10d137d73c19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1476.294484388337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.2190376698052,
        1485.3699311068688
      ],
      "voteCount": 4788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.44074347412298
      }
    },
    {
      "id": "c9e855cea973944126eafa7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1465.6468018138742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.2503035276309,
        1481.0433001001177
      ],
      "voteCount": 1602,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.70888991476011
      }
    },
    {
      "id": "4bce48db8faa07088b789b5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1470.9459470762063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.1834245220075,
        1484.7084696304048
      ],
      "voteCount": 2066,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.306015213408465
      }
    },
    {
      "id": "61af5253717b3e32afabe410",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1500.5192496206994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.0550820204685,
        1506.9834172209303
      ],
      "voteCount": 11491,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.877498553095066
      }
    },
    {
      "id": "fc06a9738b155e0d5f1750ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1462.938180804796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.0828356434447,
        1470.7935259661472
      ],
      "voteCount": 6954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.063284935282493
      }
    },
    {
      "id": "22dc223d1c3a13e81e7c25f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1464.805627073144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.8764083799258,
        1471.7348457663622
      ],
      "voteCount": 9588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.49891615127855
      }
    },
    {
      "id": "c7d88d528bef2e41e92360d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1479.4691497141616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.6589455070603,
        1520.279353921263
      ],
      "voteCount": 229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 433.5521595216211
      }
    },
    {
      "id": "2ef8a1e8f4e49b89a64d57fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1425.3575716544024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.9663781822715,
        1452.7487651265333
      ],
      "voteCount": 530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 195.31056165067378
      }
    },
    {
      "id": "9a56515e7250208ee22d48c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1483.4802360412693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.7120020501902,
        1490.2484700323485
      ],
      "voteCount": 11342,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.924894550795035
      }
    },
    {
      "id": "9561cdca70a5f8fdd46105c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1455.2654569395042,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.0740861332515,
        1469.456827745757
      ],
      "voteCount": 1763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.42669901227041
      }
    },
    {
      "id": "a289d2975e8484850243c07b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1483.442422678057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.770045478935,
        1492.1147998771792
      ],
      "voteCount": 5551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.57853247799854
      }
    },
    {
      "id": "bfaca8f8df6fa93deab3ac63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1469.3380990658372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.7280042114319,
        1473.9481939202426
      ],
      "voteCount": 29672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.532526979626684
      }
    },
    {
      "id": "c97861bc79c5a7f725bad8cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1473.2404488716895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.0981432223273,
        1484.3827545210518
      ],
      "voteCount": 3251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.318705205169394
      }
    },
    {
      "id": "b2dafab3772383137c8e5151",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.4",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1468.0470498484592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.2662155267262,
        1489.827884170192
      ],
      "voteCount": 843,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.49598574248343
      }
    },
    {
      "id": "f2f2de0fd973db9917354abd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1534.0962834228364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1512.6322443794097,
        1555.5603224662632
      ],
      "voteCount": 812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.92969170355556
      }
    },
    {
      "id": "2da2b45208ee4b258b901917",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1522.243814657764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1512.6756997507448,
        1531.8119295647834
      ],
      "voteCount": 4494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.831785565615732
      }
    },
    {
      "id": "6c8d7ee2ec6a0e81d498b26a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1450.8153011003524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.7131649477594,
        1462.9174372529455
      ],
      "voteCount": 2766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.12658323106398
      }
    },
    {
      "id": "6f44a8ffbf4b9ffa0de9caf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1486.533327584459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.2165137338336,
        1493.8501414350842
      ],
      "voteCount": 7959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.936311027545402
      }
    },
    {
      "id": "aa1b06900ddf863e9d085c6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1493.874631998634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.5132020234878,
        1501.23606197378
      ],
      "voteCount": 12531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.106789583959872
      }
    },
    {
      "id": "745059e325a828dd43e18235",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1528.764255380059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1512.8011800125737,
        1544.7273307475443
      ],
      "voteCount": 1516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.33411604343897
      }
    },
    {
      "id": "579ba55716f60e5ea7875cfd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1511.5825562217296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.8134257597399,
        1538.3516866837197
      ],
      "voteCount": 587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.54016068862998
      }
    },
    {
      "id": "7e642eb29e9163c809530e1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1448.2418537969206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.8321342792758,
        1487.6515733145654
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 404.3062974130218
      }
    },
    {
      "id": "f583cb1823f711eef12a0bd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1501.7461994188586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.8840524546863,
        1510.6083463830312
      ],
      "voteCount": 5267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.44474572823903
      }
    },
    {
      "id": "e9d22444474391fdfaf68a75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1500.418185398871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.6859074931976,
        1507.1504633045442
      ],
      "voteCount": 10459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.798529651042173
      }
    },
    {
      "id": "c0f81285cf9836e78ec25742",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1492.390870384985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.2824753348823,
        1503.4992654350876
      ],
      "voteCount": 3238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.12228644087095
      }
    },
    {
      "id": "1ff7d20eda6bd3e687879046",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1448.6754351116551,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.9130369470258,
        1459.4378332762847
      ],
      "voteCount": 3512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.15240294391289
      }
    },
    {
      "id": "6321f6057f3e74519daef1d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1483.5077986283436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.7543416364165,
        1501.2612556202705
      ],
      "voteCount": 1266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.0483180676785
      }
    },
    {
      "id": "4a622c1bca3944740145017f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1496.1153344576962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.2021105769484,
        1508.028558338444
      ],
      "voteCount": 2706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.94557454794615
      }
    },
    {
      "id": "bd5b381d0d802ea6be3b9e85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1510.0905534892884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.607236046931,
        1529.573870931646
      ],
      "voteCount": 987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.81653722662658
      }
    },
    {
      "id": "473ed5dcfbb00c9e825cd23a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1473.6359508416579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.055917333521,
        1491.2159843497948
      ],
      "voteCount": 1229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.45318004772352
      }
    },
    {
      "id": "508d26f12ab693388bd2a6e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1510.865517696786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.7865529774074,
        1518.9444824161644
      ],
      "voteCount": 6421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.990855293137912
      }
    },
    {
      "id": "14bcbcbdad471829a03224c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1475.1419769792492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.155445800531,
        1485.1285081579676
      ],
      "voteCount": 4027,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.961700915875575
      }
    },
    {
      "id": "ce7efa301cd7e35b3e4b0aa7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1480.9155079157506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.132090486615,
        1489.6989253448864
      ],
      "voteCount": 5379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.08310523045141
      }
    },
    {
      "id": "a5024b8b805ecc44cd275a8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1456.3114130896877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.3766175201554,
        1496.2462086592202
      ],
      "voteCount": 219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 415.151631611706
      }
    },
    {
      "id": "aec168f286ed9745646ac4b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1492.2663035558699,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.0431047193574,
        1500.4895023923823
      ],
      "voteCount": 6782,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.60294780215847
      }
    },
    {
      "id": "92352ff8482f179c55312da3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1498.7798196000283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.2039605102796,
        1517.3556786897768
      ],
      "voteCount": 1003,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.82591172481794
      }
    },
    {
      "id": "a14d02303adcb8bdaca73755",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1480.324834988874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.3136816427152,
        1492.3359883350329
      ],
      "voteCount": 2795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.55547343831041
      }
    },
    {
      "id": "69a6459556dbf83d0c2c97e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1482.3262161584726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.7084212230689,
        1487.9440110938763
      ],
      "voteCount": 16573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.21552993519888
      }
    },
    {
      "id": "8dbe0917bab451d475a5c0ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1487.2897167972642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.6809027182712,
        1501.8985308762572
      ],
      "voteCount": 1797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.55635469652611
      }
    },
    {
      "id": "28e87c8e3d47f6ca390ca960",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1476.150460960076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.8599555267128,
        1504.440966393439
      ],
      "voteCount": 456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.34603077445695
      }
    },
    {
      "id": "6770f3628e431f2487618291",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1508.2973526367923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.7219252286257,
        1525.8727800449592
      ],
      "voteCount": 1365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.41102690355658
      }
    },
    {
      "id": "83ac3bb8fd09996b0dbfeb43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1514.5908602020627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1506.453146511206,
        1522.7285738929193
      ],
      "voteCount": 7212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.23886346447685
      }
    },
    {
      "id": "2844386795e173b9212d41ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1455.7112342992793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.5770610088994,
        1465.8454075896595
      ],
      "voteCount": 4055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.735017365328734
      }
    },
    {
      "id": "a9df50e1825cc1eac60a1c9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1475.0105459028534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.3876447138487,
        1481.633447091858
      ],
      "voteCount": 11950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.418271601150016
      }
    },
    {
      "id": "8f5db8a62326c941fa6271b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1485.4090236529485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.6791168397074,
        1492.1389304661893
      ],
      "voteCount": 19353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.790220285824358
      }
    },
    {
      "id": "09a5c649228b3ced215177ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1475.4071012822703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.9942104926756,
        1488.8199920718653
      ],
      "voteCount": 2384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.83263513445419
      }
    },
    {
      "id": "362a463bd469323995b4b87b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1488.111853733846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.0056025013373,
        1510.2181049663545
      ],
      "voteCount": 982,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.21373997873236
      }
    },
    {
      "id": "e0b47d14615a636ef0dcff17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1457.027618570918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.8845501231624,
        1487.170687018674
      ],
      "voteCount": 404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.52591837022848
      }
    },
    {
      "id": "be1efdd25c61bd316f58f823",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1489.9244407080778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.3270947347714,
        1497.521786681384
      ],
      "voteCount": 8399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.025454790033088
      }
    },
    {
      "id": "e835a48126a8a431aaa6cc6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1490.3216462888404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.1363177803626,
        1496.506974797318
      ],
      "voteCount": 16721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.959312475689735
      }
    },
    {
      "id": "926c2949b16fea9246273886",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1474.6756332855455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.3774309306436,
        1483.9738356404473
      ],
      "voteCount": 5172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.506180872473415
      }
    },
    {
      "id": "b696170983fa6ad14f56248c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1453.8090946463146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.630046765513,
        1462.9881425271165
      ],
      "voteCount": 5325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.933053022504154
      }
    },
    {
      "id": "00dbee3d1be8348f890f0fa1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1474.5635462489583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.3254682230222,
        1488.8016242748945
      ],
      "voteCount": 2057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.77236470180799
      }
    },
    {
      "id": "a7c9a8566be1dee073918047",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1490.5804242433853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.3084521413416,
        1500.8523963454288
      ],
      "voteCount": 4017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.467015993183416
      }
    },
    {
      "id": "b69d9ecc62a5d8e8eb67c8a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1458.7350838552247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.3603013990762,
        1475.109866311373
      ],
      "voteCount": 1462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.79991534511265
      }
    },
    {
      "id": "1c644bfebb1313802d514888",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1488.4762429099374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.5672687095037,
        1503.385217110371
      ],
      "voteCount": 1877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.86278653093351
      }
    },
    {
      "id": "f4c514d4b75925dbe2205dcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1503.2035670113262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.0744135657585,
        1510.332720456894
      ],
      "voteCount": 10158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.230606189673177
      }
    },
    {
      "id": "c990f1eb66bc4aa03d727846",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1462.6213831779755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.1980770248608,
        1471.0446893310902
      ],
      "voteCount": 6098,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.470089062748446
      }
    },
    {
      "id": "657188a9583329babf8e787c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1455.1219562922722,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.7229226236504,
        1462.5209899608938
      ],
      "voteCount": 8690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.251278429558687
      }
    },
    {
      "id": "ebd5ceebd845b8919a5810f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1470.1217901713599,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.306128941228,
        1513.9374514014914
      ],
      "voteCount": 202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 499.76122578525093
      }
    },
    {
      "id": "ea28701ebf7d1d703ff7ce2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1455.9217152580911,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.4742937476647,
        1487.3691367685174
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 257.4387402845374
      }
    },
    {
      "id": "d17f8dd8c92868f41e4701ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1472.8584218863618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.7323787665387,
        1479.9844650061852
      ],
      "voteCount": 11142,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.219064140951753
      }
    },
    {
      "id": "049c6569fd91c4a7340598c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1466.2231931448364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.9968108418027,
        1482.44957544787
      ],
      "voteCount": 1409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.54049332139668
      }
    },
    {
      "id": "250adf64304b565a25d80e2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1481.6693916257507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.9381977473286,
        1491.400585504173
      ],
      "voteCount": 4629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.651086662522083
      }
    },
    {
      "id": "8e203ffe5d02f85caf5e0c82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1473.7456147880832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.5396825129574,
        1478.951547063209
      ],
      "voteCount": 24925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.055062182939227
      }
    },
    {
      "id": "3ee5547025e3c5658ba443ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1477.5528352041695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.3089112105922,
        1489.796759197747
      ],
      "voteCount": 2735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.02519375006843
      }
    },
    {
      "id": "d55df10e79658689d40d28ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5-instant",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1478.8858129246964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.7176459796688,
        1503.0539798697241
      ],
      "voteCount": 727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.05168680610464
      }
    },
    {
      "id": "0457eb8177b204e425969510",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1548.8770872035757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1526.3505258698297,
        1571.403648537322
      ],
      "voteCount": 808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.0972029660687
      }
    },
    {
      "id": "efd6b25d319c734ada4819e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1507.8416690274778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.4986804734829,
        1517.1846575814725
      ],
      "voteCount": 4672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.723511872582353
      }
    },
    {
      "id": "e4bdd13455003c380a4aebaf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1448.8981873456441,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.943854182721,
        1460.852520508567
      ],
      "voteCount": 2852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.200992654227754
      }
    },
    {
      "id": "c9eceb2facba841d6f56b624",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1479.0115785498394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.7892721778749,
        1486.2338849218038
      ],
      "voteCount": 8208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.578619937176315
      }
    },
    {
      "id": "be81547c91444cee1ce621fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1486.1503951029222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.7665655480823,
        1493.534224657762
      ],
      "voteCount": 12749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.192769320139506
      }
    },
    {
      "id": "037ddcf4e10904e294a02fb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1511.0227399813768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.6461321413265,
        1526.3993478214272
      ],
      "voteCount": 1637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.54955179865185
      }
    },
    {
      "id": "34eb2dd039ae1013cc9e6c93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1528.9774992066448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1501.3769608417067,
        1556.5780375715829
      ],
      "voteCount": 581,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.3074018470838
      }
    },
    {
      "id": "576d1178ac738c9faceade0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1456.426193970491,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.0385845536346,
        1496.8138033873477
      ],
      "voteCount": 226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 424.6196745937856
      }
    },
    {
      "id": "3bca0da8705215b42d42d4a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1492.317809602727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.71781045754,
        1500.917808747914
      ],
      "voteCount": 5578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.253098562137655
      }
    },
    {
      "id": "5a4ec723d8ccd9363d933cc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1494.140152430987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.4767626681012,
        1500.8035421938725
      ],
      "voteCount": 10924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.558307717094374
      }
    },
    {
      "id": "65ce2b9934e3ea6dcda967ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1489.7912643798816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.5094988610988,
        1501.0730298986641
      ],
      "voteCount": 3224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.13278604865918
      }
    },
    {
      "id": "15b702c8769a89dddac52fbf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1443.0432081052145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.4439598717745,
        1453.6424563386543
      ],
      "voteCount": 3620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.245156165380514
      }
    },
    {
      "id": "2ba5d2d759af95a107938042",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1472.6590924318823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.9807868379621,
        1490.3373980258025
      ],
      "voteCount": 1246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.35515783442932
      }
    },
    {
      "id": "d3b64e08021f422a26fa9bd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1495.9872908592945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.40960143464,
        1507.564980283949
      ],
      "voteCount": 2810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.89374705558707
      }
    },
    {
      "id": "64fb3780924d4ca0dc6c1e33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1508.9777607402286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.0499566106546,
        1528.9055648698027
      ],
      "voteCount": 982,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.37671076607049
      }
    },
    {
      "id": "b1c4196059735557f6db3741",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1474.9001780599526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.2463355770433,
        1492.5540205428622
      ],
      "voteCount": 1222,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.13015626575584
      }
    },
    {
      "id": "2b133468ac208b5ae4728d2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1501.2637720831344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.272081239015,
        1509.2554629272538
      ],
      "voteCount": 6579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.625747021919228
      }
    },
    {
      "id": "abf65b35e2e00f1f0419cb8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1470.407671694073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.4098751875808,
        1480.4054682005656
      ],
      "voteCount": 4052,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.020306256249157
      }
    },
    {
      "id": "1e0d786a96b898c92f308651",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1473.1515132758286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.533640685001,
        1481.7693858666562
      ],
      "voteCount": 5613,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.33320945460961
      }
    },
    {
      "id": "3e5a5401c00cbf6318cc13d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1406.7283569652623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.1089005300887,
        1446.347813400436
      ],
      "voteCount": 221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 408.6211518818237
      }
    },
    {
      "id": "87e2c0593bcaf32de85a5807",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1479.5965152096094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.5362123526052,
        1487.6568180666138
      ],
      "voteCount": 7030,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.912450498400506
      }
    },
    {
      "id": "81508ad0fb368cd9b17c36c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1496.9444340123762,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.751791446385,
        1516.1370765783672
      ],
      "voteCount": 1000,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.8900110243377
      }
    },
    {
      "id": "910cb6bb852d4d66a9b12e58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1478.7217865853645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.9511333793712,
        1490.4924397913578
      ],
      "voteCount": 2891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.06657870426541
      }
    },
    {
      "id": "f706155a8232fc7ba0c98d3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1476.4054606925872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.7809580886496,
        1482.0299632965248
      ],
      "voteCount": 16852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.235160395649954
      }
    },
    {
      "id": "76c95033f59fa37152502253",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1478.4400377323661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.5446832634032,
        1493.3353922013291
      ],
      "voteCount": 1710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.75711653104889
      }
    },
    {
      "id": "5c74f1df973bc4b82c6361f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-5.5",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1465.3634869526345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4647038207004,
        1492.2622700845684
      ],
      "voteCount": 526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.35150075826587
      }
    },
    {
      "id": "ba8f75350a32ad993d71ec46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1373.5584563674538,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.6116636637025,
        1388.5052490712048
      ],
      "voteCount": 1626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.15671143613629
      }
    },
    {
      "id": "14a93489fbaecd7884e257ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1390.6291497637376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.9511099324986,
        1398.307189594976
      ],
      "voteCount": 6494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.346330235927397
      }
    },
    {
      "id": "fb3ab6f7512cb680d523fd31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1278.4391249061746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.6418730515745,
        1288.2363767607744
      ],
      "voteCount": 3953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.986899087758214
      }
    },
    {
      "id": "5a30da1bb473e595aa0d3bdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1361.3291908070385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.6742105204162,
        1366.9841710936607
      ],
      "voteCount": 14697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.324650486897015
      }
    },
    {
      "id": "e7e1a8f31b69bb729501d861",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1314.3820894039923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.25592658003,
        1320.5082522279545
      ],
      "voteCount": 21778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.769692374032987
      }
    },
    {
      "id": "2a90e7fd0b54d016911cff09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1360.7124158748295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.240682375556,
        1377.1841493741028
      ],
      "voteCount": 1316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.62889832619909
      }
    },
    {
      "id": "e46d1796e715ced40e59d16c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1357.0288255639816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.0311462370157,
        1387.0265048909478
      ],
      "voteCount": 405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 234.24974912028028
      }
    },
    {
      "id": "7d05c4963c5de8be24d47570",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1325.6182560657435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.581212511694,
        1349.655299619793
      ],
      "voteCount": 619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.4062622529597
      }
    },
    {
      "id": "dcb8ee2a1b77ae8c53774ed6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1366.635467750928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.4425362951088,
        1373.828399206747
      ],
      "voteCount": 7638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.468389313298431
      }
    },
    {
      "id": "2ee97743fc5157a917bac402",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1362.391560406398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.7392800459645,
        1368.0438407668316
      ],
      "voteCount": 14759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.31670330574291
      }
    },
    {
      "id": "2801f20467a791bfa35f30ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1349.6228449982932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.1930787855488,
        1358.0526112110374
      ],
      "voteCount": 5390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.49843034076466
      }
    },
    {
      "id": "1ad876aa9608e3aca5362fd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1286.9586523343946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.7648605752909,
        1295.1524440934986
      ],
      "voteCount": 5508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.47727270428642
      }
    },
    {
      "id": "d4a1c8e0622157461b1852bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1343.4993494353437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.8067288122033,
        1357.191970058484
      ],
      "voteCount": 1924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.806421799771115
      }
    },
    {
      "id": "f3c79ce62242d877f16100e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1361.132178253861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.2819100166826,
        1369.9824464910396
      ],
      "voteCount": 4835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.389974623197496
      }
    },
    {
      "id": "0d67d25ca7579c2512c18da5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1384.5484494234238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.8073689284133,
        1399.2895299184345
      ],
      "voteCount": 1550,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.56690968279512
      }
    },
    {
      "id": "d829cbda95bb0701edd40997",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1368.7098359442748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.6298815498253,
        1383.7897903387238
      ],
      "voteCount": 1636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.19756924469068
      }
    },
    {
      "id": "f169d024485639f2d917102b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1385.8467915955907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.4593607474696,
        1392.2342224437116
      ],
      "voteCount": 10473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.620775789588157
      }
    },
    {
      "id": "be9c5c4353ad19dffc389d84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1310.3170642333744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.6983746402261,
        1317.9357538265224
      ],
      "voteCount": 6667,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.109996963667756
      }
    },
    {
      "id": "c31652f891dcd881913279fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1325.6507270002808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.6024303835736,
        1332.6990236169881
      ],
      "voteCount": 7814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.93219256431065
      }
    },
    {
      "id": "b6ac3d1b674ed580508bc1e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1319.2649504036447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.2014225669063,
        1346.3284782403828
      ],
      "voteCount": 502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.66572704729873
      }
    },
    {
      "id": "ef192f33ff3dd07a06c51e92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1263.2284032746754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.4549099510978,
        1288.001896598253
      ],
      "voteCount": 658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.7637772783535
      }
    },
    {
      "id": "e198122bdbe865640be60fca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1324.962983457113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.1458778027306,
        1332.7800891114953
      ],
      "voteCount": 6453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.907274726619256
      }
    },
    {
      "id": "1242d991cd7f86c6f3acdf89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1382.570305056142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.9243309111,
        1396.2162792011839
      ],
      "voteCount": 1795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.47445177962496
      }
    },
    {
      "id": "9b71f8da3be73104a9748c60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1328.0629298236545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.3890042348949,
        1336.736855412414
      ],
      "voteCount": 5007,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.585524310199617
      }
    },
    {
      "id": "ae7bd5eb5fe74a2fa85f0abd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1353.1103031084817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.764852020303,
        1357.455754196661
      ],
      "voteCount": 30639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.915566205742954
      }
    },
    {
      "id": "d65cb0e1590a0c4145620117",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1334.6101555024402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.3144805737197,
        1348.9058304311607
      ],
      "voteCount": 1606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.200185452129766
      }
    },
    {
      "id": "0b1ed0e5fe70585866df275f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-120b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1364.9695855970513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.19368831176,
        1387.7454828823427
      ],
      "voteCount": 759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.0376305885814
      }
    },
    {
      "id": "6d984240b46dd438b3e4c4ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1348.4857288345052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.3906137000563,
        1375.5808439689545
      ],
      "voteCount": 488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.1110592138002
      }
    },
    {
      "id": "9c60ba4c209eafd178032583",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1369.5771723989965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.6697632343535,
        1382.4845815636395
      ],
      "voteCount": 2167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.36925608730264
      }
    },
    {
      "id": "95529c82c190f4f3a20ff250",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1238.4282336758527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.1897526126481,
        1256.6667147390572
      ],
      "voteCount": 1242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.59267403854712
      }
    },
    {
      "id": "1f4e64be4ec77c11cb93a8ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1330.884883663136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.2588012149554,
        1339.5109661113165
      ],
      "voteCount": 5063,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.370062748548047
      }
    },
    {
      "id": "a2d0723fb138ed7ef19fc313",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1262.3903604255488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.3805646406568,
        1271.4001562104409
      ],
      "voteCount": 7784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.131664785304448
      }
    },
    {
      "id": "299b0c21deab11374389c2b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1318.3521965075715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.4666582660457,
        1346.2377347490972
      ],
      "voteCount": 489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.42394343279383
      }
    },
    {
      "id": "da6e97d7f07ee65751103973",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1269.9475581143863,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.7986083626624,
        1311.0965078661102
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 440.77943945366695
      }
    },
    {
      "id": "35bcad012bb996a6e09eac0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1338.4716142030359,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.2206708321237,
        1350.7225575739483
      ],
      "voteCount": 2446,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.069952453683044
      }
    },
    {
      "id": "cb62660004c49aef56581c38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1322.972385702053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.127069796632,
        1331.8177016074746
      ],
      "voteCount": 4797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.36716183060925
      }
    },
    {
      "id": "88e05de946b640fd7c512a71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1322.1833589032049,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.2593043849802,
        1336.1074134214293
      ],
      "voteCount": 1849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.47022583765664
      }
    },
    {
      "id": "aaad80a4a023056acad87039",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1256.6863345083375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.6951846715324,
        1271.6774843451426
      ],
      "voteCount": 1745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.502403362724706
      }
    },
    {
      "id": "cc982a6d385294eb9536b0dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1323.3342307451217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.9125267540808,
        1346.7559347361625
      ],
      "voteCount": 694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.80413859670506
      }
    },
    {
      "id": "d098ddaae58ec7fc04fd10e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1329.3198638657195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.1996736379879,
        1344.4400540934514
      ],
      "voteCount": 1688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.51388865376076
      }
    },
    {
      "id": "8d99fbd302e4f631fff3f4c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1329.776209350022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.7850663349395,
        1353.7673523651047
      ],
      "voteCount": 583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.83238661039104
      }
    },
    {
      "id": "05991f2f24fea84ea68aeca1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1354.4560125891512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.5627805130698,
        1380.3492446652326
      ],
      "voteCount": 561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.53251450569053
      }
    },
    {
      "id": "729510358537119fdc5d9138",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1358.9571125863663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.0813433164258,
        1368.8328818563068
      ],
      "voteCount": 3707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.389005381938844
      }
    },
    {
      "id": "57870b0a51b25b00d431de93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1273.691133530512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.5736436563948,
        1286.808623404629
      ],
      "voteCount": 2182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.792499055470266
      }
    },
    {
      "id": "6b11b5154ae31080e8a9f2a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1281.043741284039,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.9203923169873,
        1293.1670902510905
      ],
      "voteCount": 2554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.26035811841776
      }
    },
    {
      "id": "03bbeb8613e1d052739fc239",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1261.929990930143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.6004970968102,
        1302.259484763476
      ],
      "voteCount": 233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 423.39854434752027
      }
    },
    {
      "id": "0a7ba6e01994cf6069a62cf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1291.7374288565784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.6508004357838,
        1333.8240572773734
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 461.09677976711635
      }
    },
    {
      "id": "3354efb7f6c937f1ea4347ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1301.1102111935809,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.6895638001806,
        1314.530858586981
      ],
      "voteCount": 2093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.88681692686502
      }
    },
    {
      "id": "41f3fdcbafa8c22202ee671f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1336.251638165617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.2627006829764,
        1358.2405756482576
      ],
      "voteCount": 680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.86712345080154
      }
    },
    {
      "id": "a363584771866f58e7dafe39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1292.3867241975713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.1634895059708,
        1306.6099588891716
      ],
      "voteCount": 1839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.66239065287931
      }
    },
    {
      "id": "bf0e619d7f15cfe4812efffe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1317.5667534700315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.2061724800717,
        1323.9273344599915
      ],
      "voteCount": 10633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.531673621462675
      }
    },
    {
      "id": "6677fb33fb1e740850b0fbda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1302.2846060933366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.7666658089393,
        1325.8025463777337
      ],
      "voteCount": 607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.98007138354043
      }
    },
    {
      "id": "bc89c4d30d78b12b09fd112f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt-oss-20b",
      "organization": "openai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1304.0795281497024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.1625807557562,
        1344.9964755436486
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 435.82312402256895
      }
    },
    {
      "id": "f704bef607a3d0b5d2db2903",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1062.221035668419,
      "unit": "Arena rating",
      "confidenceInterval": [
        1024.7017181323004,
        1099.7403532045378
      ],
      "voteCount": 250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 366.44911583921044
      }
    },
    {
      "id": "4da72029957d6bf288ba053c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1093.8695109818918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.8328057199788,
        1110.906216243805
      ],
      "voteCount": 1388,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.55705780775546
      }
    },
    {
      "id": "fd94c10074d019894bbdd784",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 884.6882836822896,
      "unit": "Arena rating",
      "confidenceInterval": [
        860.8871350757483,
        908.4894322888308
      ],
      "voteCount": 1196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.46863143213375
      }
    },
    {
      "id": "b333c08512af2e18a4c95c09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1081.28118545882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1047.7099175374433,
        1114.8524533801965
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 293.38594592697217
      }
    },
    {
      "id": "df62bb8aa4696f41cd1c03e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1062.6317069052316,
      "unit": "Arena rating",
      "confidenceInterval": [
        1032.5123378358387,
        1092.7510759746242
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.15413713438465
      }
    },
    {
      "id": "db4f0f833d1fccef7299eb57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1048.341883455542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1011.1508366258754,
        1085.532930285209
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 360.06476415554596
      }
    },
    {
      "id": "3b2df819f421f979b54f1e3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1060.0350522601884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1023.7952459271635,
        1096.2748585932131
      ],
      "voteCount": 305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 341.8814633597566
      }
    },
    {
      "id": "65219e07fee3233e19a9b913",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1073.966246565512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1044.6862239217703,
        1103.2462692092536
      ],
      "voteCount": 422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.17556064888606
      }
    },
    {
      "id": "5d4c17979043ea8374472bfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1058.973247072792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1027.536008406959,
        1090.410485738625
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 257.2720471734657
      }
    },
    {
      "id": "12fec742d91e15fc604889c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1034.6875586342396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1009.5720549562254,
        1059.8030623122538
      ],
      "voteCount": 483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.2054631959757
      }
    },
    {
      "id": "58e7b23f36ea01d9b5059a75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 997.4388825392368,
      "unit": "Arena rating",
      "confidenceInterval": [
        960.2852968007729,
        1034.5924682777006
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 359.3397710758114
      }
    },
    {
      "id": "dc250e53a3125383dda1f853",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1026.9944922126515,
      "unit": "Arena rating",
      "confidenceInterval": [
        989.3735752775401,
        1064.615409147763
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 368.43643446445196
      }
    },
    {
      "id": "fea91ed796c9fcc054287b38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "gpt4all-13b-snoozy",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1065.430672185259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.2004732449382,
        1080.6608711255801
      ],
      "voteCount": 1743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.383039514097504
      }
    },
    {
      "id": "0b8aa33396e0fc86572006df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1178.5607292303832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.9973526022106,
        1202.124105858556
      ],
      "voteCount": 759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.53694391569405
      }
    },
    {
      "id": "d552e4ed47f0ee3a64007847",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1208.0327433310217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.5238132477307,
        1225.5416734143128
      ],
      "voteCount": 1134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.80370139856866
      }
    },
    {
      "id": "9c57172b929413b65ea03579",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1098.9638580786207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1077.3084845906985,
        1120.619231566543
      ],
      "voteCount": 916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.07737289154834
      }
    },
    {
      "id": "371070adebd94630557f7429",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1199.9845529302304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.5436889634082,
        1211.4254168970529
      ],
      "voteCount": 3330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.07386995851793
      }
    },
    {
      "id": "fd2baaac5bdc1d446f853f64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 978.7682648893567,
      "unit": "Arena rating",
      "confidenceInterval": [
        961.56503673934,
        995.9714930393732
      ],
      "voteCount": 4814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.0413201326588
      }
    },
    {
      "id": "2a1a7e16db54f90c11118677",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1172.2095787964133,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.5970298821449,
        1200.8221277106818
      ],
      "voteCount": 407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 213.11642102243832
      }
    },
    {
      "id": "5127ffcfb05c78d21a383a83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1191.7095952930363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.3729864285285,
        1211.0462041575438
      ],
      "voteCount": 974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.33397124152862
      }
    },
    {
      "id": "83303a959fcbf748106d31bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1175.9050990844544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.2029655953984,
        1190.6072325735106
      ],
      "voteCount": 1740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.26839677822464
      }
    },
    {
      "id": "c185b048ab49ad5469701494",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1138.1501564913272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.2462591700269,
        1160.0540538126274
      ],
      "voteCount": 873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.89544734345918
      }
    },
    {
      "id": "01a7a9dd29d99735465c8efd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1105.5384797136571,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.670939814845,
        1126.406019612469
      ],
      "voteCount": 941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.35647256784294
      }
    },
    {
      "id": "42e43f767fd403234fd7cc83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1180.9115715129888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.8586665418065,
        1212.9644764841707
      ],
      "voteCount": 435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 267.4475414280216
      }
    },
    {
      "id": "d45ebf0894ad7bf944d4015c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1181.4585582634895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.4196054871877,
        1200.4975110397916
      ],
      "voteCount": 1206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.36043433956621
      }
    },
    {
      "id": "2567e7a96a788e988c77b60b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1187.9662163803846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.1785925334361,
        1208.753840227333
      ],
      "voteCount": 751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.48989651388207
      }
    },
    {
      "id": "ffd82999c5b5aa3b770c8da0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1132.0415369038262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1094.8325235272973,
        1169.2505502803551
      ],
      "voteCount": 380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 360.4127340884891
      }
    },
    {
      "id": "2375d5f5c2b542b278c8d175",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1185.5007974933615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.045425964581,
        1199.9561690221417
      ],
      "voteCount": 1929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.39542001840713
      }
    },
    {
      "id": "2969eceeb1c50a4bb87791d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1104.9318198078167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.3251992475657,
        1120.5384403680675
      ],
      "voteCount": 1820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.404715937482024
      }
    },
    {
      "id": "2468efa3f0518739a07010ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1129.5817877283228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.1769435205254,
        1141.98663193612
      ],
      "voteCount": 2698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.05774030187786
      }
    },
    {
      "id": "203d35921e28464bf8b60f80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1145.9157387739356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.1756925555082,
        1170.655784992363
      ],
      "voteCount": 647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.33266903517767
      }
    },
    {
      "id": "7a0551f8c5edabb6c6438757",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1168.020475566605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.2622758309772,
        1186.7786753022324
      ],
      "voteCount": 908,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.59802922425219
      }
    },
    {
      "id": "0b7505fcfb57a8852cb6522b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1115.2675867245057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.18601809875,
        1134.3491553502615
      ],
      "voteCount": 1162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.78333055608151
      }
    },
    {
      "id": "2e7b40890635f6929e8548fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1155.3283571694437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.9411399961512,
        1163.7155743427365
      ],
      "voteCount": 6837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.312160873109267
      }
    },
    {
      "id": "52880067455215a4ced0d1ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1107.1794273006244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.548694370533,
        1126.8101602307156
      ],
      "voteCount": 1056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.31753387452453
      }
    },
    {
      "id": "a8c8f7a8a70cf55f2e6eab99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1164.2276038350951,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.2941712891236,
        1188.1610363810664
      ],
      "voteCount": 701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.11241280182742
      }
    },
    {
      "id": "7827a4b1df9b23385613e5a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1238.9694612976746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.0564283891838,
        1256.8824942061651
      ],
      "voteCount": 1108,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.52992000124843
      }
    },
    {
      "id": "215495403453d6bad629f535",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1135.5653061462558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.227053662547,
        1156.903558629965
      ],
      "voteCount": 895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.52815305624956
      }
    },
    {
      "id": "82aab2ee381787e4108c6dd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1236.7024574983393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.209907132468,
        1248.1950078642103
      ],
      "voteCount": 3296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.38243648495477
      }
    },
    {
      "id": "3392dbf6a421116b57371ca0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1030.1309084119162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1013.884131775463,
        1046.3776850483691
      ],
      "voteCount": 4661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.71289356346715
      }
    },
    {
      "id": "b1448f4c8fe79c6a5d11e6df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1199.5007120879613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.482248045203,
        1230.5191761307196
      ],
      "voteCount": 345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.46347142621008
      }
    },
    {
      "id": "3abcaa61db64fb2fe86f13b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1234.7625314097286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.1839670579748,
        1254.341095761482
      ],
      "voteCount": 900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.78505561761905
      }
    },
    {
      "id": "eac0dcd6e8a7fbc8e55cd300",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1201.5471841359301,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.7393452341926,
        1216.3550230376677
      ],
      "voteCount": 1666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.08042261408205
      }
    },
    {
      "id": "744b9e622236e9bd53a9d34a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1151.5615123035077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.7120843762557,
        1174.4109402307597
      ],
      "voteCount": 813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.91096012538895
      }
    },
    {
      "id": "415bf062170a4c9abf2b0ddf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1140.2066122971937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.5322795325944,
        1160.8809450617932
      ],
      "voteCount": 934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.26711367015365
      }
    },
    {
      "id": "3fb86ffd157ff1b261bd17d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1193.5524201293788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.516291697545,
        1227.5885485612127
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 301.56721513910827
      }
    },
    {
      "id": "6b3bd9d4430e92c1e6753ea8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1217.6261766789517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.9133556082838,
        1237.338997749619
      ],
      "voteCount": 1128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.15826635203602
      }
    },
    {
      "id": "a4ea45f4f425d5445c5bf885",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1213.4630697337043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.366934497698,
        1234.5592049697102
      ],
      "voteCount": 675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.85362297738847
      }
    },
    {
      "id": "470b275d5c525c26fc0f5694",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1196.6090161310324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.8758582076016,
        1232.342174054463
      ],
      "voteCount": 356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 332.3889789739074
      }
    },
    {
      "id": "881091b356413782173aef21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1218.2365182269077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.397174265948,
        1233.0758621878672
      ],
      "voteCount": 1825,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.323568849783136
      }
    },
    {
      "id": "11d842a535f7d1ee970f6405",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1142.4997508767694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.9365274029265,
        1158.0629743506124
      ],
      "voteCount": 1751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.05258918616023
      }
    },
    {
      "id": "0c2f0e9858a45ee81a4c08c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1169.2339280686579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.9033372018189,
        1181.5645189354964
      ],
      "voteCount": 2597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.5796175937903
      }
    },
    {
      "id": "3498e0359316c5bb1fef6ec4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1201.2593351119226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.2372641900984,
        1225.2814060337469
      ],
      "voteCount": 603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.21894501758237
      }
    },
    {
      "id": "730e4c931f49ed2c9d95ecf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1196.4305828056026,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.6892493505195,
        1215.1719162606855
      ],
      "voteCount": 873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.4333840525578
      }
    },
    {
      "id": "a7893b61f095eff5f121b467",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1135.5025684184202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.6219161313147,
        1155.3832207055257
      ],
      "voteCount": 1148,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.88808335823073
      }
    },
    {
      "id": "017c419ad1f7fc50811d5f58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1181.483355376808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.8020895713018,
        1190.1646211823145
      ],
      "voteCount": 6638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.618686416697003
      }
    },
    {
      "id": "bae45456faa34ce2a449b6aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.0-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1135.750642469804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.8035045594029,
        1155.6977803802054
      ],
      "voteCount": 954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.57739842820195
      }
    },
    {
      "id": "14d453f015090fdcb5708023",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1206.6739913690292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.94850741861,
        1245.3994753194484
      ],
      "voteCount": 231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 390.38895825601713
      }
    },
    {
      "id": "0fcd7407316916e9c3e8ac6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1247.6568125274025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.0247333251555,
        1272.288891729649
      ],
      "voteCount": 508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.94502925743316
      }
    },
    {
      "id": "83132e4d022ed630a0ddcc57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1147.302218568359,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.3285736870826,
        1176.2758634496354
      ],
      "voteCount": 442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.52950581795696
      }
    },
    {
      "id": "4310baf74cea91955b268b17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1226.4902963527857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.1312442267297,
        1240.8493484788416
      ],
      "voteCount": 1739,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.67293717898969
      }
    },
    {
      "id": "2afc2d1591fe48057fec8e19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1017.2320297899589,
      "unit": "Arena rating",
      "confidenceInterval": [
        995.9377290419266,
        1038.5263305379913
      ],
      "voteCount": 2152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.04037619898627
      }
    },
    {
      "id": "90a1a6ad6d8a661325a26ce8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1213.8520877110695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.0924274812955,
        1249.6117479408438
      ],
      "voteCount": 225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 332.88220945131013
      }
    },
    {
      "id": "15ec7c1c9cb30bba29b36cf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1236.8621247951114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.4832502431996,
        1261.2409993470233
      ],
      "voteCount": 511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.71453740859502
      }
    },
    {
      "id": "bdaa8a865a5376de9f2913ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1218.1335239247128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.096378199445,
        1237.1706696499805
      ],
      "voteCount": 832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.34252305731937
      }
    },
    {
      "id": "6ace559503579940c34e7f20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1214.4042436247948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.7675899782646,
        1244.0408972713249
      ],
      "voteCount": 382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 228.64523098172398
      }
    },
    {
      "id": "07860e95e758c11c6ffb2ca5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1147.3570922249432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1123.5333566977133,
        1171.1808277521736
      ],
      "voteCount": 567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.74865512390224
      }
    },
    {
      "id": "80202d462af784bd356b4345",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1177.2933486879456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.8920459041158,
        1204.6946514717752
      ],
      "voteCount": 549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 195.45475541904779
      }
    },
    {
      "id": "912e623dc9c63027b6340f24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1229.1323775819699,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.2758020146644,
        1257.9889531492754
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 216.76711695718578
      }
    },
    {
      "id": "8050a08ecf69a7249fdce38c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1223.2925788462305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.0403937361484,
        1243.5447639563129
      ],
      "voteCount": 828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.76959480172846
      }
    },
    {
      "id": "f903e78ee420c2c200aff781",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1127.0242312261184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.910837482713,
        1148.137624969524
      ],
      "voteCount": 850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.0432575673228
      }
    },
    {
      "id": "f28ef309fd20ba125919fd98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1171.5312252687672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.1164275757656,
        1187.9460229617691
      ],
      "voteCount": 1252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.14147381996155
      }
    },
    {
      "id": "fd05e21c57bb6036d5cb8ac1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1220.8181855844314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.487236756349,
        1247.149134412514
      ],
      "voteCount": 489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.4832222727891
      }
    },
    {
      "id": "03a61abc7e006f5eec7dd31b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1197.1435846541058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.7600274417746,
        1223.527141866437
      ],
      "voteCount": 391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.2051420222124
      }
    },
    {
      "id": "ba43cf4716f6477bc27ba5da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1141.9763907266693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.6523041321777,
        1169.3004773211608
      ],
      "voteCount": 579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.35473424868417
      }
    },
    {
      "id": "9bdbe1f6782d7a8cc87228b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1178.2069813816902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.0117166516425,
        1189.402246111738
      ],
      "voteCount": 3188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.62665519168608
      }
    },
    {
      "id": "2e7367b06c5127e64c31813b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-2b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1109.782932241647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1081.3100398916235,
        1138.2558245916703
      ],
      "voteCount": 464,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.04107491891133
      }
    },
    {
      "id": "0a86efd17f4e7cd626d8889b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1217.5871327156467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.6883462924516,
        1257.4859191388416
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 414.4032859256533
      }
    },
    {
      "id": "168d133516280e5d2f538d87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1286.7700959713588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.0043987370673,
        1312.5357932056504
      ],
      "voteCount": 478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.81745944870573
      }
    },
    {
      "id": "df719d6d38a93a6b67a787b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1170.4109455032303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.875992769158,
        1196.9458982373026
      ],
      "voteCount": 450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.29071049946145
      }
    },
    {
      "id": "43353a0230ddc4a998362c84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1247.6592396753517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.6466404780347,
        1261.671838872669
      ],
      "voteCount": 1737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.114158820833914
      }
    },
    {
      "id": "1b283ebc1725e55d55022096",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1074.0768986690596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1054.172120585798,
        1093.9816767523212
      ],
      "voteCount": 2075,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.13795072057992
      }
    },
    {
      "id": "3d30d47f59243c7a8bde5c8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1230.9934727663122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.7330778932308,
        1266.2538676393938
      ],
      "voteCount": 237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 323.651900134381
      }
    },
    {
      "id": "239623a79bc1d101fa980586",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1248.8620549539266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.7035387060369,
        1273.0205712018164
      ],
      "voteCount": 517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.93027819418177
      }
    },
    {
      "id": "3f7f3b0062adc6b931b23d59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1229.6573317863163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.81633706832,
        1249.4983265043124
      ],
      "voteCount": 798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.47801415411742
      }
    },
    {
      "id": "7dbce828177fd19e6e2a7203",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1226.7292385082442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.5215300929253,
        1259.936946923563
      ],
      "voteCount": 316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 287.06591679605
      }
    },
    {
      "id": "3323f09c015c865f1fec1329",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1165.3553118335958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.423216279018,
        1190.2874073881735
      ],
      "voteCount": 537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.81597089989737
      }
    },
    {
      "id": "82ba75cc63f242cb953d79f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1251.444716265149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.7476219884402,
        1293.141810541858
      ],
      "voteCount": 215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 452.60088739063434
      }
    },
    {
      "id": "981eba9687e86e493b47b1a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1216.1083609655648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.9454470348467,
        1241.271274896283
      ],
      "voteCount": 560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.82598591811058
      }
    },
    {
      "id": "a1ac90e69758a231ee2a5b82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1225.4318324004455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.5139043921629,
        1256.3497604087281
      ],
      "voteCount": 320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.84251450927144
      }
    },
    {
      "id": "34964c68a986ff7bbfcdc536",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1250.2989507381644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.6442794570603,
        1270.9536220192686
      ],
      "voteCount": 780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.05558217421803
      }
    },
    {
      "id": "0cb9b974548a9971f74df5c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1178.636641405991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.0217135787434,
        1199.2515692332386
      ],
      "voteCount": 837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.62860990029816
      }
    },
    {
      "id": "6b191a880b495229fd1bbfc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1190.9129087446051,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.2817827283477,
        1207.5440347608626
      ],
      "voteCount": 1258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.00242550528164
      }
    },
    {
      "id": "70d583ddff4fba0fb5c1d34f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1229.6077365059552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.463886346962,
        1256.7515866649483
      ],
      "voteCount": 461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.7991668906508
      }
    },
    {
      "id": "17a778102280e6786ed31092",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1189.9951880585845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.7809541154224,
        1218.2094220017466
      ],
      "voteCount": 382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 207.22413909818636
      }
    },
    {
      "id": "2899f335a9e1d847985b1790",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1155.2868342874522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.4744396035667,
        1181.0992289713379
      ],
      "voteCount": 551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.444451812787
      }
    },
    {
      "id": "5ee3c91e3722a1753a687b86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1207.6496662943164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.5458037887124,
        1218.7535287999203
      ],
      "voteCount": 3090,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.09607815633849
      }
    },
    {
      "id": "593ac97ed79616f8d62f2b1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-3.1-8b-instruct",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1149.3039790079501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.7967218382141,
        1177.8112361776857
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.5508064185398
      }
    },
    {
      "id": "2dcb6f6dab2172ac6e47e6cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1360.130430884169,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.2880582112684,
        1380.97280355707
      ],
      "voteCount": 944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.0832110696915
      }
    },
    {
      "id": "71579192deb659e782d4ceef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1269.1746333051217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.7082488294145,
        1295.6410177808286
      ],
      "voteCount": 571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.34466121112118
      }
    },
    {
      "id": "2b6d05c03ecec78c5968ea9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1337.295016026442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.5243906332444,
        1352.0656414196396
      ],
      "voteCount": 1743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.793886044247714
      }
    },
    {
      "id": "7af51dda71bec8b114227bdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1254.342333719961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.8308930546257,
        1269.8537743852962
      ],
      "voteCount": 2692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.63370316976146
      }
    },
    {
      "id": "091132726e38a8394e799014",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1337.167086015741,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.8066880088886,
        1370.527484022593
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 289.7118535230045
      }
    },
    {
      "id": "356b3e5b3d9f5de33d4079dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1350.7781397871793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.3848696879354,
        1369.1714098864231
      ],
      "voteCount": 1182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.06872616237227
      }
    },
    {
      "id": "dfa946036111c14bc49c11ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1331.3811399229637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.0906112667135,
        1344.671668579214
      ],
      "voteCount": 2300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.982050103217816
      }
    },
    {
      "id": "5f28313acdfc63d8fc4fa36b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1310.9191455932018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.0750833311977,
        1335.763207855206
      ],
      "voteCount": 587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.6752690809314
      }
    },
    {
      "id": "5751559f349246fdbd94e684",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1260.7975347678441,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.0557192220194,
        1284.539350313669
      ],
      "voteCount": 743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.73430894935908
      }
    },
    {
      "id": "eb2bd95a50e1435ea2f32f4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1367.3313990659067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.0733132895507,
        1409.589484842263
      ],
      "voteCount": 206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 464.86137085785396
      }
    },
    {
      "id": "b8982167f45d55d8c441cf39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1327.3643465178332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.4248497582796,
        1353.3038432773867
      ],
      "voteCount": 603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.15676297613132
      }
    },
    {
      "id": "1bf4af9e52c290cee6e6689e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1341.9615270023442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.2624045432372,
        1384.660649461451
      ],
      "voteCount": 187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 474.6152812978394
      }
    },
    {
      "id": "d1d2928aa6435d62a5b142ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1327.1345619145097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.6066735651343,
        1365.6624502638851
      ],
      "voteCount": 280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 386.41522659709915
      }
    },
    {
      "id": "5dcc7479e8b781fceb64f85c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1360.3244954083787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.4631960214479,
        1377.1857947953094
      ],
      "voteCount": 1398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.00923198347458
      }
    },
    {
      "id": "3d74eda0c9275179ad08bcc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1279.4510674475655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.4494754185591,
        1301.452659476572
      ],
      "voteCount": 821,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.01203719876752
      }
    },
    {
      "id": "3693bec0ac448df9c246127f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1298.7653618161698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.5979457420856,
        1316.932777890254
      ],
      "voteCount": 1215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.91918388682755
      }
    },
    {
      "id": "c4764c01c447c166b61fee84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1308.488166171191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.3330963641333,
        1326.6432359782489
      ],
      "voteCount": 1280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.80244513452432
      }
    },
    {
      "id": "2e900ba6b5d278d862dd816d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1314.8495008038847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.063696545375,
        1354.6353050623943
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 412.0596612852455
      }
    },
    {
      "id": "65ae6ae073d1537022d22af1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1295.8894480797228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.4962203421828,
        1322.2826758172628
      ],
      "voteCount": 581,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.33800280586445
      }
    },
    {
      "id": "c55cbb9bcd4760b5614cab7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1312.420412959459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.0128322163932,
        1322.8279937025254
      ],
      "voteCount": 3614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.197031903589973
      }
    },
    {
      "id": "1cf1672659152452322e041b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "granite-4.1-8b",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1266.6043018658079,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.914145601952,
        1297.294458129664
      ],
      "voteCount": 400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.1895843386151
      }
    },
    {
      "id": "4293b6baf75b261c89a17c42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1340.5904443187392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.2001699503626,
        1349.9807186871158
      ],
      "voteCount": 5317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.954105934540948
      }
    },
    {
      "id": "7927e42833d0f128353b52be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1358.6712428902208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.7487766513536,
        1365.593709129088
      ],
      "voteCount": 10368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.474567882937386
      }
    },
    {
      "id": "720ad46a4591a6fb22a9e91b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1317.0468131738357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.620670123751,
        1324.4729562239204
      ],
      "voteCount": 9339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.355900498851527
      }
    },
    {
      "id": "f6aafcfb74cd3984694b8c50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1345.8951024178232,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.3596692426133,
        1350.4305355930333
      ],
      "voteCount": 34362,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.354776673898579
      }
    },
    {
      "id": "f9b84b8b53ff27ce43ffc179",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1288.0384324886677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.4495430387942,
        1293.6273219385412
      ],
      "voteCount": 40763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.13120398808922
      }
    },
    {
      "id": "8b09f0776b60b5dc8ffcccf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1313.0476037521794,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.2017559806654,
        1323.893451523693
      ],
      "voteCount": 3541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.621807853089006
      }
    },
    {
      "id": "333403b2fa24ccf1a0020e65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1352.967859966774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.0656094813412,
        1378.870110452207
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.65411228562428
      }
    },
    {
      "id": "6d094b0d740c117cfb2110e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1312.6971827482982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.004990121277,
        1328.3893753753196
      ],
      "voteCount": 1609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.1019261008376
      }
    },
    {
      "id": "d35bb0bea0cb631de2352b07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1331.1030988621856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.3405599041464,
        1337.865637820225
      ],
      "voteCount": 10486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.904834932145762
      }
    },
    {
      "id": "4d8c07e629b13049a5ba7166",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1325.9534287563647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.3659339290366,
        1331.540923583693
      ],
      "voteCount": 17283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.127146457287504
      }
    },
    {
      "id": "49669755bc10f031e8cbf173",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1315.2954833778822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.1842846702853,
        1323.4066820854791
      ],
      "voteCount": 7490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.126708249402796
      }
    },
    {
      "id": "9942a00279242816d698b2f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1314.6807738835384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.69593957303,
        1321.665608194047
      ],
      "voteCount": 10293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.700360103415608
      }
    },
    {
      "id": "bd15269f11772db345c9b4e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1364.9575976502708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.926840803555,
        1375.9883544969866
      ],
      "voteCount": 3813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.674840806800063
      }
    },
    {
      "id": "d3513d8cfa9b04aa72faa452",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1350.8969013017434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.7974564754031,
        1357.9963461280836
      ],
      "voteCount": 10796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.12056674165835
      }
    },
    {
      "id": "543d8b4a304814c9d06dbcd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1299.574653150534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.1024354320568,
        1307.0468708690112
      ],
      "voteCount": 7604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.534592257385079
      }
    },
    {
      "id": "c8d7b8723b8bf31d084200b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1355.0721945636888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.2594755350651,
        1366.8849135923126
      ],
      "voteCount": 3206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.32482797876159
      }
    },
    {
      "id": "2d4d667af7326c9a84d8b657",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1350.6436623216273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.7795311617365,
        1356.507793481518
      ],
      "voteCount": 16648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.951816449301347
      }
    },
    {
      "id": "99cd1d25e1682f54f0716cfd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1326.449184328007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.5551434933295,
        1332.3432251626846
      ],
      "voteCount": 17406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.043365810327511
      }
    },
    {
      "id": "00d1ab81e6fb8cd9984e1d2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1311.587942514116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.6010318315193,
        1316.5748531967124
      ],
      "voteCount": 25659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.473915071593055
      }
    },
    {
      "id": "9fd26b9ffb42b5e8c14c0287",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1269.680666076794,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.4960179513719,
        1285.8653142022163
      ],
      "voteCount": 1478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.18837508621218
      }
    },
    {
      "id": "c0988b3bcc7d9e0d1a01d97d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1277.5282733228764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.9055128994537,
        1299.1510337462994
      ],
      "voteCount": 952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.70995190943039
      }
    },
    {
      "id": "8df3ab2baa2762956d54e854",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1334.6193525492986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.3785011650684,
        1341.8602039335287
      ],
      "voteCount": 8902,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.648442223580544
      }
    },
    {
      "id": "b9601d1c65f7bbf4ee38ee8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1293.7611211605795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.550070114763,
        1300.9721722063964
      ],
      "voteCount": 8950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.536330756756033
      }
    },
    {
      "id": "bc1d9b48aa6c115c9c4ce5c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1324.5585234012442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.5127786007324,
        1331.6042682017558
      ],
      "voteCount": 10743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.922830130707192
      }
    },
    {
      "id": "b899bf2ad15ec4d961234802",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1335.3478251852048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.6814087787861,
        1339.0142415916234
      ],
      "voteCount": 63498,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.4993500887837947
      }
    },
    {
      "id": "a920da361d9b8ab5b2628b69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1325.1349895524377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.4742925373657,
        1332.7956865675094
      ],
      "voteCount": 8745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.277081311033054
      }
    },
    {
      "id": "9b4ef94d421d9c6ea75a1aab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1309.3896788815587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.9744173245858,
        1333.8049404385317
      ],
      "voteCount": 671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.17672444753472
      }
    },
    {
      "id": "1ff99c5e6abbcddfd069b937",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1310.6507787215362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.780935435431,
        1320.5206220076416
      ],
      "voteCount": 4510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.358545031773808
      }
    },
    {
      "id": "4797732f44e167e441058500",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1335.372616641448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.2004235074728,
        1342.5448097754236
      ],
      "voteCount": 8652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.390838416367215
      }
    },
    {
      "id": "2e20d05f02097580ff898f86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1271.9260533736679,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.215503091516,
        1279.6366036558197
      ],
      "voteCount": 7924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.476564614806463
      }
    },
    {
      "id": "296edd70fe886586cb34cad5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1320.7405446751964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.9341065271128,
        1325.54698282328
      ],
      "voteCount": 28429,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.013821506272894
      }
    },
    {
      "id": "b65eeb93bb5bdccd1b7cd4d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1248.0913219743938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.2657074131102,
        1253.9169365356775
      ],
      "voteCount": 33168,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.834608569487928
      }
    },
    {
      "id": "aae33f33def4c4043066decb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1292.9058271085214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.177491400929,
        1304.6341628161135
      ],
      "voteCount": 2759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.807713915602704
      }
    },
    {
      "id": "3ad65b7f7b0c9ebedb18b86b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1321.7357514747778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.0870881985481,
        1350.3844147510072
      ],
      "voteCount": 471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 213.65474571623255
      }
    },
    {
      "id": "1cdf6877cb777c7067f7d9c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1292.6945114377172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.6893449976887,
        1309.6996778777454
      ],
      "voteCount": 1298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.27757009791827
      }
    },
    {
      "id": "3a1595d9924d582212b89b97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1315.4165097040914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.3187018020926,
        1322.5143176060903
      ],
      "voteCount": 8664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.114517001271125
      }
    },
    {
      "id": "978daa6e02bfaf41c0fe546c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1303.8939185724166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.0111810809917,
        1309.7766560638415
      ],
      "voteCount": 14208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.008713097895859
      }
    },
    {
      "id": "d232b7aadd08c7dcf716a570",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1301.4123869545108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.942728996054,
        1309.8820449129676
      ],
      "voteCount": 6124,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.673922923971173
      }
    },
    {
      "id": "2789aea835bf92556f4c02e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1263.6711517372978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.369734885558,
        1270.9725685890376
      ],
      "voteCount": 8614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.877719515222655
      }
    },
    {
      "id": "db277ddaeaa9c2a0d4155c8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1328.745140996356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.8449053477939,
        1340.645376644918
      ],
      "voteCount": 3012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.865059630059974
      }
    },
    {
      "id": "6480510ec8a1509717719a1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1332.5633856318962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.1132962997863,
        1340.013474964006
      ],
      "voteCount": 8788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.448633617368593
      }
    },
    {
      "id": "b0c25eace668646fbf22a978",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1285.3716459853406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.4557481434595,
        1293.2875438272217
      ],
      "voteCount": 6253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.311886074513545
      }
    },
    {
      "id": "f1317c4bf74caa6f690edfbc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1342.9954155544679,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.1377251038684,
        1355.8531060050673
      ],
      "voteCount": 2609,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.03578703820807
      }
    },
    {
      "id": "ea022969b64e51d1cbdf9226",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1329.6929155979203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.5327982027939,
        1335.8530329930468
      ],
      "voteCount": 13865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.878290538301929
      }
    },
    {
      "id": "e64ac13cec770877c8f347f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1293.8364588825443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.6270265731628,
        1300.0458911919254
      ],
      "voteCount": 14508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.03708523363074
      }
    },
    {
      "id": "7c607f2103266a96136f324e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1283.0670194054946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.8024763268556,
        1288.3315624841334
      ],
      "voteCount": 21131,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.214814767124539
      }
    },
    {
      "id": "b65fd0188c09c5b20d4acad8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1235.6268416678085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.2264584260402,
        1253.0272249095774
      ],
      "voteCount": 1225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.81728038560924
      }
    },
    {
      "id": "14b87c03d21b1d982406fb5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1227.213787601122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.18397874988,
        1250.2435964523643
      ],
      "voteCount": 852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.06528209221162
      }
    },
    {
      "id": "b2854d99300633fcbdb10988",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1316.6072897559561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.8637431538334,
        1324.350836358079
      ],
      "voteCount": 7048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.609308020230888
      }
    },
    {
      "id": "b3f89f485aced2ab1e431ce9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1272.4126029874983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.814744118843,
        1280.0104618561531
      ],
      "voteCount": 7261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.027483589572798
      }
    },
    {
      "id": "4680aaf66dfa8c85c960f654",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1296.599379568333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.240509255681,
        1303.958249880985
      ],
      "voteCount": 9399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.096981070500044
      }
    },
    {
      "id": "181cdf7cdeeef4b03fa99b2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1308.2159722309402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.5087226449984,
        1311.923221816882
      ],
      "voteCount": 52567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.5777292257898345
      }
    },
    {
      "id": "57479d5088fda5921b6235d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1296.4830124824027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.5050835917427,
        1304.4609413730627
      ],
      "voteCount": 7193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.568536161720044
      }
    },
    {
      "id": "573cb43cfd55ea97474b98ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-2-mini-2024-08-13",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1308.6910224776348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.7019545764877,
        1333.680090378782
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.55634739703117
      }
    },
    {
      "id": "5ca5b67c0ae6f6c5b3482298",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1375.8574834789347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.620591818346,
        1394.0943751395234
      ],
      "voteCount": 1061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.57758236230652
      }
    },
    {
      "id": "23e5207bb2606ec65400a8ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1386.6806200906997,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6684825641464,
        1395.692757617253
      ],
      "voteCount": 4255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.142650901262048
      }
    },
    {
      "id": "23b87d04b60158f6f286240c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1335.457461578104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.2276430535308,
        1346.687280102677
      ],
      "voteCount": 2761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.82836807087293
      }
    },
    {
      "id": "15af1e431acb1f43666fd9a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1369.3661643151681,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.10801553504,
        1375.6243130952957
      ],
      "voteCount": 11614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.195196143515844
      }
    },
    {
      "id": "83d9adfd198adc5f92037e99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1320.0647737064355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.160797555131,
        1326.96874985774
      ],
      "voteCount": 16057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.408017090019918
      }
    },
    {
      "id": "c4987fecbcc42256ce4bb195",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1374.9697718710286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.8167413638625,
        1392.1228023781946
      ],
      "voteCount": 1168,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.59237527023807
      }
    },
    {
      "id": "104f517ced43daa76e4cf62e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1359.9656148591534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.0622745985404,
        1396.8689551197665
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 354.515455184421
      }
    },
    {
      "id": "c3388e080ddd4467bb0521c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1328.9994426972182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.7202371868127,
        1354.2786482076235
      ],
      "voteCount": 546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.35300834016022
      }
    },
    {
      "id": "5e85c1bb94471fd51bc43106",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1381.6352498705082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.3488622304442,
        1389.921637510572
      ],
      "voteCount": 5304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.874516772510642
      }
    },
    {
      "id": "f434f8905c5f9c2a3be26361",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1370.009931670784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.4324819751155,
        1376.5873813664525
      ],
      "voteCount": 9626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.262087274237976
      }
    },
    {
      "id": "2b9334657786f4d84cfdb791",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1345.082843053519,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.0149546808625,
        1355.1507314261753
      ],
      "voteCount": 3551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.38642792113957
      }
    },
    {
      "id": "b7c5c95daeede383ea3e7a98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1321.586824293891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.9892983514314,
        1331.1843502363502
      ],
      "voteCount": 3818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.97852183653918
      }
    },
    {
      "id": "159d8aa967921c446e8f115e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1356.3615086246832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.983724585296,
        1371.739292664071
      ],
      "voteCount": 1507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.558968350286925
      }
    },
    {
      "id": "1b1e53d6907a3d4a52440291",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1370.7717984129367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.103180600739,
        1380.4404162251349
      ],
      "voteCount": 3894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.335070284954753
      }
    },
    {
      "id": "d8ff7533bee9e33d5decfa61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1362.7179066213507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.9623303700444,
        1377.4734828726569
      ],
      "voteCount": 1463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.678215404837175
      }
    },
    {
      "id": "a702f3a3695a22f1c1e2432f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1360.57763531381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.533382206455,
        1376.6218884211653
      ],
      "voteCount": 1425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.01049517598636
      }
    },
    {
      "id": "5323a98f3659ced4f3ea50e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1379.122771965252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.9048164832657,
        1386.3407274472381
      ],
      "voteCount": 7604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.562264694671478
      }
    },
    {
      "id": "c1fb8c6f024153da57d07d6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1341.6667411555118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.9559222807752,
        1350.377560030248
      ],
      "voteCount": 4799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.752487013450015
      }
    },
    {
      "id": "b35f3bbe34530de93a1a776a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1353.05238964517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.0096669045752,
        1361.0951123857649
      ],
      "voteCount": 5545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.83875634267335
      }
    },
    {
      "id": "9ab6e61e57b6de4ab666655d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1329.626324125295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.7711675172993,
        1354.4814807332905
      ],
      "voteCount": 591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.81880317966275
      }
    },
    {
      "id": "06ae5a8de009dc1d0e4b7203",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1290.490528475204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.221002168143,
        1319.7600547822653
      ],
      "voteCount": 411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.01558085814534
      }
    },
    {
      "id": "44f453c676c7401b79c52d2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1366.2288259795498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.0201021366709,
        1375.4375498224288
      ],
      "voteCount": 4149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.07510187473125
      }
    },
    {
      "id": "d8ee33fdcf0d435ab9c19e73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1369.7952382452654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.5857193595016,
        1384.0047571310295
      ],
      "voteCount": 1530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.5608724157559
      }
    },
    {
      "id": "54e3c3f119de07b2b9f9af1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1342.9994311859612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.3927707548175,
        1352.6060916171048
      ],
      "voteCount": 3874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.024186890183845
      }
    },
    {
      "id": "84f46b4ce37433892346c546",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1357.0093951170493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.001633050088,
        1362.0171571840108
      ],
      "voteCount": 22724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.52816601448486
      }
    },
    {
      "id": "f3211e3890623980952b57cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1348.8940760882815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.5415012086519,
        1364.2466509679114
      ],
      "voteCount": 1389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.3573036797635
      }
    },
    {
      "id": "b373bcb8103429c673bd1155",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-beta",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1372.6130544117837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.0921713318621,
        1402.133937491705
      ],
      "voteCount": 399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.86239225673214
      }
    },
    {
      "id": "7d36348c61fab2abb9510390",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1383.929175099382,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.8535782453773,
        1406.0047719533868
      ],
      "voteCount": 718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.86117415479184
      }
    },
    {
      "id": "5cb4b50c81c770136a09dc6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1390.1370371752691,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.8867912396288,
        1400.3872831109097
      ],
      "voteCount": 3296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.35094833637424
      }
    },
    {
      "id": "4fa806ad9c5c75c5f604fc89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1329.0659604163643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.8969298887341,
        1342.2349909439943
      ],
      "voteCount": 2062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.14518393465844
      }
    },
    {
      "id": "8b5ed77c49d869b128657920",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1373.7338406370254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.8808887335026,
        1380.5867925405482
      ],
      "voteCount": 8442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.225290438883679
      }
    },
    {
      "id": "da5cd5ea0a459a0e04d6ee86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1326.4309333114627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.1426256974662,
        1333.7192409254592
      ],
      "voteCount": 12119,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.827931094843997
      }
    },
    {
      "id": "6d82646e8298b3de31a08c63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1402.2031258464558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.389850425278,
        1421.016401267634
      ],
      "voteCount": 921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.13669821641992
      }
    },
    {
      "id": "61879b2a2f008ba1410c11dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1347.6427462404058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.5069155647943,
        1392.7785769160168
      ],
      "voteCount": 162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 530.3306128918327
      }
    },
    {
      "id": "a9568fc785f56e353a96e6c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1341.6056696571934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.6161359527257,
        1370.595203361661
      ],
      "voteCount": 424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.76924981604083
      }
    },
    {
      "id": "3b36546d295bb91f6cf9835d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1382.2324324016943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.784703944496,
        1391.6801608588926
      ],
      "voteCount": 4050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.235853139987036
      }
    },
    {
      "id": "09ff86d7905678ad03d82f68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1377.1702996524757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.0089643756987,
        1384.3316349292527
      ],
      "voteCount": 7566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.350324795917984
      }
    },
    {
      "id": "b7eb3529ced168946d4738ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1340.749211109154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.4597040034737,
        1352.038718214834
      ],
      "voteCount": 2790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.17827331705499
      }
    },
    {
      "id": "52dbddc0736e83b1d5b0da89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1326.3973320603009,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.5783273767743,
        1337.2163367438275
      ],
      "voteCount": 2987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.470419651932335
      }
    },
    {
      "id": "3258d8f838d4cff9e996312c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1378.6616725059396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.3158384973958,
        1396.0075065144833
      ],
      "voteCount": 1171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.32387941557712
      }
    },
    {
      "id": "258236293a917d9f2274f7fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1377.5133593093271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.1814832147315,
        1388.8452354039227
      ],
      "voteCount": 2750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.4277736185813
      }
    },
    {
      "id": "395669c3f682d15a3b50f2ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1375.9722906148654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.6638299758595,
        1394.2807512538716
      ],
      "voteCount": 987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.25844701609131
      }
    },
    {
      "id": "662853b4ef252cb1bc4e68b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1385.0475618263558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.1316152039976,
        1403.9635084487143
      ],
      "voteCount": 988,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.14509235198724
      }
    },
    {
      "id": "70b4aa60e04f38682177dafb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1379.9091530439596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.977069694005,
        1387.841236393914
      ],
      "voteCount": 5893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.378659568516824
      }
    },
    {
      "id": "d57c9b6c48c3cd63bba2a52f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1346.681997036998,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.7671860856485,
        1356.5968079883473
      ],
      "voteCount": 3617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.59014186783229
      }
    },
    {
      "id": "e522e5d3fa2b43d8a82dc5f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1362.14663558461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.9969708613062,
        1371.2963003079142
      ],
      "voteCount": 4223,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.792857468076807
      }
    },
    {
      "id": "34180ba834ad2dc4843c73ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1309.5734411791955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.2228157072511,
        1338.9240666511396
      ],
      "voteCount": 419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 224.2531433510682
      }
    },
    {
      "id": "8455115a4eefd7ed8ee5e97a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1329.8676931073828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.4999910127926,
        1364.2353952019728
      ],
      "voteCount": 307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 307.47145873323944
      }
    },
    {
      "id": "7b38b1f262a31a01823c8b45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1377.6078194549627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.3347588692782,
        1387.8808800406473
      ],
      "voteCount": 3303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.472837461804833
      }
    },
    {
      "id": "f9a676ba95183af8204834da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1388.3823465245084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.1332314287529,
        1406.631461620264
      ],
      "voteCount": 977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.69368001137495
      }
    },
    {
      "id": "c9ea8b2d6733593fe1916580",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1348.206423459226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.153245741206,
        1359.259601177246
      ],
      "voteCount": 2875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.803734822818164
      }
    },
    {
      "id": "31643a0a1014c612d5d193cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1362.162304246302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.8245854796414,
        1367.5000230129626
      ],
      "voteCount": 16968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.416776532518629
      }
    },
    {
      "id": "32056a68edc79658111665f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1352.9345459738427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.7104725965676,
        1371.158619351118
      ],
      "voteCount": 991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.45591843160706
      }
    },
    {
      "id": "5e7a59b2abbf41cc94e26111",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-mini-high",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1351.667229107154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.242131580439,
        1386.0923266338693
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 308.4992954602873
      }
    },
    {
      "id": "f03714b2f5bcdb38e8d423ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1435.5104952331633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.0061703762024,
        1450.0148200901244
      ],
      "voteCount": 1758,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.764465630337064
      }
    },
    {
      "id": "31b0bee5d2dfdd11f3b91ba7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1442.966839224234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.6531763339244,
        1451.2805021145439
      ],
      "voteCount": 5400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.99238098853921
      }
    },
    {
      "id": "d43d682935c3723d457d2af2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1400.0622252923854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.9065364643407,
        1409.2179141204304
      ],
      "voteCount": 4728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.821563585273346
      }
    },
    {
      "id": "4baf77350962377c60e9de14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1420.4955170376052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.16050420745,
        1425.8305298677603
      ],
      "voteCount": 18065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.409258624508028
      }
    },
    {
      "id": "898eed33ba44a6a011d7be91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1400.4194198814096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.287297990357,
        1406.551541772462
      ],
      "voteCount": 23357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.78870805126338
      }
    },
    {
      "id": "f59abad85dd61d1ffe5fa4ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1405.5412076823761,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.302661837449,
        1420.7797535273035
      ],
      "voteCount": 1538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.449243453295615
      }
    },
    {
      "id": "7fcff07f8b27acef5c18cc8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1455.270846779658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.2656141482216,
        1488.2760794110948
      ],
      "voteCount": 359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 283.5759621284724
      }
    },
    {
      "id": "e99e7b01d14a7866d37fcbe3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1414.6471835190164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.909205701195,
        1436.3851613368374
      ],
      "voteCount": 755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.01047640091582
      }
    },
    {
      "id": "b153eace96d975c697d55723",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1433.496928360632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.6021455370083,
        1441.3917111842557
      ],
      "voteCount": 6348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.22498085790279
      }
    },
    {
      "id": "1e3b840b3f515ad5598d6492",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1426.1453354663875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.7656173209734,
        1432.5250536118017
      ],
      "voteCount": 10695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.595142500465933
      }
    },
    {
      "id": "9de8c95f3c19d9fcc535df06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1400.4640113162807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.796374321572,
        1410.1316483109892
      ],
      "voteCount": 3974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.330133270716484
      }
    },
    {
      "id": "5531ed42e4bfc01a80808a18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1397.2289890149057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.8763324098209,
        1405.5816456199905
      ],
      "voteCount": 5731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.16155674678268
      }
    },
    {
      "id": "69d8d5cba9de98b88da8fa85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1421.643666534664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.447530026393,
        1435.8398030429346
      ],
      "voteCount": 1885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.461916466683455
      }
    },
    {
      "id": "9d53a7b4c81f242e5428dee7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1417.3554836885805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.1426355765195,
        1425.5683318006415
      ],
      "voteCount": 5786,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.558661243073313
      }
    },
    {
      "id": "03880c4735af82c23b4cfb43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1391.9073504178066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.2033776345438,
        1403.6113232010696
      ],
      "voteCount": 2448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.659103821034115
      }
    },
    {
      "id": "3460516d251752c240671af5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1443.0238777393613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.8194015788008,
        1458.2283538999218
      ],
      "voteCount": 1625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.17924598636756
      }
    },
    {
      "id": "42ecd223dda2161a5969f269",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1434.2110868891655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.4822360474964,
        1440.9399377308346
      ],
      "voteCount": 9317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.786520632609658
      }
    },
    {
      "id": "591c6610df7a091b4d61f509",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1406.639064438902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.4491626205847,
        1413.8289662572195
      ],
      "voteCount": 7814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.457046025994673
      }
    },
    {
      "id": "332b10ddc5978e27e36fc645",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1405.4663164915887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.9011313225108,
        1412.0315016606667
      ],
      "voteCount": 9671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.220127122563563
      }
    },
    {
      "id": "60ba9f8f5559e4d3fb601b07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1379.7208773608768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.998749921522,
        1401.4430048002318
      ],
      "voteCount": 777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.83115413074171
      }
    },
    {
      "id": "cd8d9f28838e43a574ca63d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1354.597973814278,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.2382320396805,
        1382.9577155888753
      ],
      "voteCount": 492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.367063676221
      }
    },
    {
      "id": "654088b9476dd222c6e1a437",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1428.98226467191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.292031226756,
        1437.6724981170635
      ],
      "voteCount": 4878,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.65923906939647
      }
    },
    {
      "id": "8b0f1c07497dfd18bad4fb77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1374.9292559425003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.8492525366032,
        1386.0092593483976
      ],
      "voteCount": 2677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.95829532607424
      }
    },
    {
      "id": "d4617eff4191744c3180c472",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1408.9341048348351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.0154894744912,
        1417.852720195179
      ],
      "voteCount": 4770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.706118081304627
      }
    },
    {
      "id": "bcefcea1f7bf7109b90bc8d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1411.743697156228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.4349382053852,
        1416.052456107071
      ],
      "voteCount": 32909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.8329045196207705
      }
    },
    {
      "id": "4699c8bb0a1e4a98f065d944",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1411.006092784158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.3003391155366,
        1422.7118464527794
      ],
      "voteCount": 2494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.66995647910746
      }
    },
    {
      "id": "adb428ee9f4502ea9c90b828",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-3-preview-02-24",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1398.7014961650407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.468057368434,
        1429.9349349616473
      ],
      "voteCount": 345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 253.94719678007746
      }
    },
    {
      "id": "6465ac3b8670373117d2e04c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1434.3604257580796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.742854873785,
        1447.9779966423744
      ],
      "voteCount": 2005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.27286857529815
      }
    },
    {
      "id": "85c1e78e53691b54ea19680b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1435.5920961241393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.7119451992942,
        1442.4722470489844
      ],
      "voteCount": 8155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.322526143881252
      }
    },
    {
      "id": "c72f51a40b9bdd4700a31dc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1396.8923034866725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.4800784538459,
        1405.3045285194992
      ],
      "voteCount": 5457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.421525078362777
      }
    },
    {
      "id": "2a841d9d3f6c00a57b02555a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1419.2967788264793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.3269919237935,
        1424.266565729165
      ],
      "voteCount": 20259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.429531855203847
      }
    },
    {
      "id": "e0411455300436e066bc4de0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1395.2685684810199,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.9335166607164,
        1400.6036203013236
      ],
      "voteCount": 29975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.409366923835005
      }
    },
    {
      "id": "7869201811563d1c30ea4468",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1432.5393145917787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.0724906486666,
        1446.006138534891
      ],
      "voteCount": 2012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.21001983356172
      }
    },
    {
      "id": "fe4e8620e454c9464a9a448f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1432.2447352144698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.409500272841,
        1459.0799701560986
      ],
      "voteCount": 544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.46259376595256
      }
    },
    {
      "id": "252d0f277b4b5f27904bd006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1415.360975734326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.557540778019,
        1436.164410690633
      ],
      "voteCount": 853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.66108168331101
      }
    },
    {
      "id": "2a885762b5d459a299ce0400",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1424.9488698154596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.6302355096996,
        1431.2675041212199
      ],
      "voteCount": 10381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.393223343915512
      }
    },
    {
      "id": "bafb9b2bbe7b47cd0767fc97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1420.0649652340242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.0550754047188,
        1425.0748550633298
      ],
      "voteCount": 19653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.53371473528995
      }
    },
    {
      "id": "73782a11f5c8137abd9cab84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1393.9616049308443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.6341819920528,
        1401.2890278696357
      ],
      "voteCount": 7285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.976754516979366
      }
    },
    {
      "id": "c5dcb79912c243e909a3dd50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1387.0621238656895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.8642885068107,
        1394.2599592245683
      ],
      "voteCount": 7427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.486760179343484
      }
    },
    {
      "id": "c7ad3a6ff39db479ddef57d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1421.8213196803056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.2118776118216,
        1433.4307617487896
      ],
      "voteCount": 2684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.08540672502395
      }
    },
    {
      "id": "26c036fe8582657cea317104",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1434.8595843668381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.33047036792,
        1442.3886983657565
      ],
      "voteCount": 6874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.756778675676038
      }
    },
    {
      "id": "40fe9eacb3feb95aa58a5956",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1434.496271211445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.725695443641,
        1447.2668469792488
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.454602028443176
      }
    },
    {
      "id": "ba94604572eff6dc72f8cf79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1438.7129725451332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.8498799499605,
        1451.5760651403061
      ],
      "voteCount": 2291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.0719575127689
      }
    },
    {
      "id": "e72bfd8f73839059ad9eea0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1424.4595757055506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.837522722916,
        1430.081628688185
      ],
      "voteCount": 14301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.227988692545091
      }
    },
    {
      "id": "059a9e93efdec7b1a52c8528",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1398.8089315453317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.1361103284733,
        1405.4817527621901
      ],
      "voteCount": 9138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.59105044997233
      }
    },
    {
      "id": "f0b04684762ec5b2f7768d6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1397.3200674860304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.1427044895872,
        1403.4974304824739
      ],
      "voteCount": 10814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.933677639405696
      }
    },
    {
      "id": "ab93bc4c4ae680d61cb6d632",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1383.8965042122136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.8324300405538,
        1404.960578383873
      ],
      "voteCount": 860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.5017511365654
      }
    },
    {
      "id": "04e7fe9106b042d2ac8ea02b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1360.3343422984308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.7415348687794,
        1381.927149728082
      ],
      "voteCount": 808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.37298730948211
      }
    },
    {
      "id": "dd780e772e3b5d37455fdfc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1416.9210547886435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.2009556645019,
        1423.641153912785
      ],
      "voteCount": 8841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.755880863543805
      }
    },
    {
      "id": "cf8d506b49247a53412549be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1428.0082186195918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.7188149717838,
        1440.2976222673997
      ],
      "voteCount": 2264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.315647796392284
      }
    },
    {
      "id": "607a866d2241f7121a2ba386",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1412.2639436734387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.6536295058295,
        1419.874257841048
      ],
      "voteCount": 6623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.07679359146407
      }
    },
    {
      "id": "c075ea895b8652edee707181",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1409.963970614826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.0708156682192,
        1413.8571255614327
      ],
      "voteCount": 41413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.9455467690134993
      }
    },
    {
      "id": "4db680593ba3253eaf4f4090",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1414.5284947059363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.1917844968807,
        1426.8652049149919
      ],
      "voteCount": 2236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.61891195145335
      }
    },
    {
      "id": "0bbab02c7b7aa369170bf695",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-0709",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1407.623418637192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.4655876521026,
        1427.781249622281
      ],
      "voteCount": 912,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.77704174113713
      }
    },
    {
      "id": "833626e36d74b88cd662c21f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1464.3499375683755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.506343627864,
        1476.1935315088872
      ],
      "voteCount": 2753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.51496058530569
      }
    },
    {
      "id": "84a453a93409f10b2143e6cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1462.0924049139132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.1885646414012,
        1467.9962451864255
      ],
      "voteCount": 12670,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.073461825379749
      }
    },
    {
      "id": "2dbcc59db04ac466201b8bc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1412.7437425905814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.7127152343803,
        1419.7747699467827
      ],
      "voteCount": 8455,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.86889902797829
      }
    },
    {
      "id": "94741acfc0233e4f5b24371d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1440.883838536838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.3856145982425,
        1445.3820624754337
      ],
      "voteCount": 25337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.267274633468236
      }
    },
    {
      "id": "a73f5cac4102a5c9ce4fb622",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1424.618859839631,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.9489767040616,
        1429.2887429752006
      ],
      "voteCount": 38903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.67696011275629
      }
    },
    {
      "id": "1e5dd2584a9799508e7b0012",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1442.2922129932886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.2324960295443,
        1452.3519299570328
      ],
      "voteCount": 3841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.343613224612675
      }
    },
    {
      "id": "696341d01a674e4b39c588cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1446.649356240827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.9305549500748,
        1465.3681575315793
      ],
      "voteCount": 1229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.21366077779619
      }
    },
    {
      "id": "e537cf9cbd39f5f82db5ac78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1412.5022058692175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.524105111491,
        1433.4803066269442
      ],
      "voteCount": 875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.56083012802088
      }
    },
    {
      "id": "4fd33efa80004c248b27b690",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1443.9026485536447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.3809082322443,
        1449.424388875045
      ],
      "voteCount": 15109,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.936988940953607
      }
    },
    {
      "id": "75d61c9b4bcfe8a517120e46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1441.224787769903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9724280736418,
        1445.4771474661643
      ],
      "voteCount": 30899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.707212501921159
      }
    },
    {
      "id": "11d6215f44bec6f83e3f8a09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1416.7603483070263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.3219101254426,
        1423.19878648861
      ],
      "voteCount": 10301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.791079158460043
      }
    },
    {
      "id": "0e971dd8e8e36f1df710bd6e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1401.7119911220614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.308855379867,
        1408.1151268642557
      ],
      "voteCount": 10343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.673066990096908
      }
    },
    {
      "id": "93960f46284cc3c69822164c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1426.7397870888697,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.790945640566,
        1436.6886285371734
      ],
      "voteCount": 3905,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.7661088621542
      }
    },
    {
      "id": "cdf5a0697bfed34baafff60b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1447.6675808070472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.818226038752,
        1454.5169355753421
      ],
      "voteCount": 8764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.212459623213864
      }
    },
    {
      "id": "0dbcb01aa4d695ab03550f69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1423.4103906743378,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.4165813255554,
        1435.4042000231202
      ],
      "voteCount": 2617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.44709221403219
      }
    },
    {
      "id": "6b00e2a0f2dc34dc965d32d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1447.7552693244472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.3075073334053,
        1458.2030313154892
      ],
      "voteCount": 3536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.41517655569663
      }
    },
    {
      "id": "adc70ea18243896721f9fe25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1457.86059103504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.879815912355,
        1462.8413661577251
      ],
      "voteCount": 19406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.457994730833906
      }
    },
    {
      "id": "3f8f60f0e7c16a28885bddc9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1405.7378978979787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.8143853898084,
        1411.661410406149
      ],
      "voteCount": 12449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.134030083942976
      }
    },
    {
      "id": "b9d16be2f7d04a461f1351f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1401.547873232409,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.151215606816,
        1406.944530858002
      ],
      "voteCount": 15657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.581472270632971
      }
    },
    {
      "id": "05970764e468a8527319f96a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1369.3687188055276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.6521827156346,
        1402.0852548954208
      ],
      "voteCount": 355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.6367845348574
      }
    },
    {
      "id": "e11ac8ada5d48c0da933ef2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1375.2349304146226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.4267483642786,
        1397.0431124649667
      ],
      "voteCount": 814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.80630029896041
      }
    },
    {
      "id": "e98f8cbb048676116368c6d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1423.4852056736804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.0120797687985,
        1428.9583315785624
      ],
      "voteCount": 16033,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.797846747521933
      }
    },
    {
      "id": "05b215abbe3f2abd921ab791",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1419.9065464075948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.504165537559,
        1430.3089272776308
      ],
      "voteCount": 3382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.168863136671014
      }
    },
    {
      "id": "51a2da89a676848cba250d19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1416.046398400792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.3896945236736,
        1422.7031022779101
      ],
      "voteCount": 9787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.535124695059435
      }
    },
    {
      "id": "2a6d4170b533a9bced328295",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1431.0556844084776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.7392129066043,
        1434.372155910351
      ],
      "voteCount": 54616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.8632308027062168
      }
    },
    {
      "id": "8b657a5ba44b3c39e78047d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1406.9275101979524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.797272519303,
        1415.0577478766018
      ],
      "voteCount": 5744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.207203772493983
      }
    },
    {
      "id": "a28b3fe062b73265484ca7e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-1-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1428.4995865406042,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.0374132267684,
        1445.96175985444
      ],
      "voteCount": 1352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.3780464858241
      }
    },
    {
      "id": "8bb6c06d9f7c5c2c71dda9bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1482.7713783021893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.9169194742467,
        1514.625837130132
      ],
      "voteCount": 358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.14614722792726
      }
    },
    {
      "id": "f206f57851a4643f1e8f9ac6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1458.6106109031575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.1777552049075,
        1475.0434666014078
      ],
      "voteCount": 1249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.29588471567136
      }
    },
    {
      "id": "8ca72a5a2e2fce677e4caff7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1386.543168913975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.0782751052209,
        1406.0080627227292
      ],
      "voteCount": 941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.62974163487587
      }
    },
    {
      "id": "b51330ddadbe4f8e8b31f931",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1429.4801819385834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.1333209258619,
        1439.827042951305
      ],
      "voteCount": 3230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.868978378696262
      }
    },
    {
      "id": "a00248b31ddf7ecf153b7b34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1411.330282983239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.7669900668404,
        1421.8935758996372
      ],
      "voteCount": 4900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.047078843206418
      }
    },
    {
      "id": "b63c9384cc3bf0a4d58ad69b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1422.618345510709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.3267056327009,
        1456.9099853887174
      ],
      "voteCount": 298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 306.111979956232
      }
    },
    {
      "id": "23f2742f95a5de71fee32bcd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1445.0204671284637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.2889626348185,
        1459.751971622109
      ],
      "voteCount": 1612,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.49344032460019
      }
    },
    {
      "id": "9afa84618c47f07d39769335",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1433.2121889929103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.7187811024849,
        1443.7055968833358
      ],
      "voteCount": 3167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.664008725452803
      }
    },
    {
      "id": "ee0b7d5264e8be7f7962c4ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1402.7167418401962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.7965284347954,
        1419.6369552455967
      ],
      "voteCount": 1205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.52731762788197
      }
    },
    {
      "id": "25060cfbcc58188c2d0feea3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1386.1919667382256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.6396315462052,
        1402.744301930246
      ],
      "voteCount": 1279,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.32181108724906
      }
    },
    {
      "id": "5aefead5c5ab9c8ad1ae497f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1423.5288938407507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.6481397914015,
        1451.4096478901001
      ],
      "voteCount": 436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.354491520971
      }
    },
    {
      "id": "effe33c5ddf0293c777e4cd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1433.4016345768755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.5432184030165,
        1452.2600507507343
      ],
      "voteCount": 1008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.579376009608
      }
    },
    {
      "id": "b25ad08eaa97097960baee65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1444.084723290715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.2678946900176,
        1475.9015518914123
      ],
      "voteCount": 320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.52243495434305
      }
    },
    {
      "id": "3bbcd833aac67a2f090c2387",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1444.1852317040775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.4499344739704,
        1473.9205289341846
      ],
      "voteCount": 394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.1698241823271
      }
    },
    {
      "id": "ee3856b13e8dd9ac4509755a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1459.3196512110017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.8279693817578,
        1471.8113330402452
      ],
      "voteCount": 2253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.6205356367354
      }
    },
    {
      "id": "25a4647e5481624cc03994ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1394.5864987551238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.4870191535294,
        1409.6859783567181
      ],
      "voteCount": 1529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.35096401678097
      }
    },
    {
      "id": "eb3da5999811d2be025758a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1400.6230894067394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.2085595588183,
        1415.0376192546603
      ],
      "voteCount": 1731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.0884805577742
      }
    },
    {
      "id": "ea5f0c3f58c2990771306cc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1348.400672105287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.9728618326628,
        1388.8284823779113
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 425.4654077338185
      }
    },
    {
      "id": "93f774ebb883348af9de7bef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1421.532082874186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.0436066367322,
        1437.0205591116398
      ],
      "voteCount": 1457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.44838415704438
      }
    },
    {
      "id": "81a9b1190623a621c35d3648",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1424.2310937076438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.2227006563023,
        1453.2394867589853
      ],
      "voteCount": 399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 219.05398618045538
      }
    },
    {
      "id": "0374505e6294b5a5ab5cac57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1424.4657345454682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.6172551141526,
        1441.314213976784
      ],
      "voteCount": 1218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.89673361022045
      }
    },
    {
      "id": "31486bdb5f4d41d72ce520bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1421.2455715209642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.6316076575959,
        1428.8595353843323
      ],
      "voteCount": 6820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.091257883691439
      }
    },
    {
      "id": "33fdc571200dc6c8e479d56e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1397.910336024897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.5601306455255,
        1425.2605414042687
      ],
      "voteCount": 408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.72647481319194
      }
    },
    {
      "id": "563f657bd29495ff2d9fc038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-chat",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1426.583974107452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.514136217397,
        1465.6538119975069
      ],
      "voteCount": 244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 397.3626437258933
      }
    },
    {
      "id": "6b2f9e5e0e092a38377def02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1441.7666617546422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.139503258914,
        1464.3938202503705
      ],
      "voteCount": 695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.2796537692147
      }
    },
    {
      "id": "8ee6981c324478a10327b216",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1437.1506824544724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.7650438030498,
        1446.5363211058948
      ],
      "voteCount": 3956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.93144792299465
      }
    },
    {
      "id": "b634d633ffc999b096755efd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1381.7788796174832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.934845159629,
        1393.6229140753371
      ],
      "voteCount": 2519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.5176769520821
      }
    },
    {
      "id": "1b4ddd1c0de8a8e2b270a829",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1413.95765926837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3834227240163,
        1420.5318958127236
      ],
      "voteCount": 9303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.25108667266805
      }
    },
    {
      "id": "3541c5275ba67da1a51a3fad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1386.9988116590696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.9594442476557,
        1394.0381790704832
      ],
      "voteCount": 13243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.899446763799935
      }
    },
    {
      "id": "1ce31abcf475dbb91bd641f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1418.6843475329324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.7909929625341,
        1438.5777021033307
      ],
      "voteCount": 862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.01960128576277
      }
    },
    {
      "id": "f47e7e503a1b7ba0a654c637",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1444.277775962328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.0364910194867,
        1480.5190609051692
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 341.90936194153585
      }
    },
    {
      "id": "70a8d0cb2fa3705ced6c9215",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1385.8535692879755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.320224023908,
        1417.3869145520432
      ],
      "voteCount": 350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 258.84746133064885
      }
    },
    {
      "id": "3a580e529283a36eae6c7d5f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1423.3571056503197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.9664946476612,
        1431.747716652978
      ],
      "voteCount": 5205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.32698364971964
      }
    },
    {
      "id": "0d26c15051b407790f751584",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1412.7938806396974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.3719249576832,
        1419.2158363217113
      ],
      "voteCount": 9915,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.735899226508067
      }
    },
    {
      "id": "2acafb0819ad2910e704068c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1400.6514924325506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.7777369288617,
        1410.5252479362393
      ],
      "voteCount": 3655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.378652302983504
      }
    },
    {
      "id": "83de328479ce3b9bd6fee8dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1367.8756899098523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.674964289737,
        1378.0764155299676
      ],
      "voteCount": 3329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.087314490090957
      }
    },
    {
      "id": "478d9df3aebafdcc9200e1a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1425.6831123032734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.7212082769981,
        1442.645016329549
      ],
      "voteCount": 1187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.89503379463316
      }
    },
    {
      "id": "a6163ec2511e5f4a35e0b095",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1432.4822688023164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.6909174405744,
        1443.2736201640585
      ],
      "voteCount": 2987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.314854238507962
      }
    },
    {
      "id": "1c59a4e917f5c530777a71ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1412.7694210620516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.0027552299093,
        1431.536086894194
      ],
      "voteCount": 941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.68072935158047
      }
    },
    {
      "id": "73ebddab9f502387b88eebde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1434.4926647109285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.6828105256168,
        1454.3025188962401
      ],
      "voteCount": 882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.15658716143732
      }
    },
    {
      "id": "ee41cf4376b40405beb99857",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1425.6142684420993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.1645653674739,
        1433.0639715167247
      ],
      "voteCount": 6779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.447135447895915
      }
    },
    {
      "id": "adc741c3d0ef6e6d4642d410",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1388.1781187353956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.9610988937754,
        1397.3951385770156
      ],
      "voteCount": 4186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.114894035351412
      }
    },
    {
      "id": "acec5b631921a73f9201a82d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1388.4143439586994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.1147834640904,
        1396.7139044533083
      ],
      "voteCount": 5310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.931392114006215
      }
    },
    {
      "id": "7e8ce4cf6ed8e595f9126933",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1363.2294591810203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.5576507740861,
        1408.9012675879544
      ],
      "voteCount": 177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 543.0005059335228
      }
    },
    {
      "id": "bc95871baa79ca197387d1bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1354.5862371437522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.9098916407966,
        1387.2625826467079
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.9526230182508
      }
    },
    {
      "id": "6fad8acd9e93d7b8a91703d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1411.5582361923114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.5383499831103,
        1420.5781224015127
      ],
      "voteCount": 4451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.17902365337299
      }
    },
    {
      "id": "d3bf4ef1516c56df771a3470",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1412.1425760245534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.459169432583,
        1429.8259826165238
      ],
      "voteCount": 1085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.40211396056071
      }
    },
    {
      "id": "b5fae9a67a3096d3ad822d38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1406.4102505860517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.668669404038,
        1417.1518317680654
      ],
      "voteCount": 3070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.03587222339192
      }
    },
    {
      "id": "e2351dfe5d029d4a9c11493a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1403.9832499916936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.9720210891803,
        1408.9944788942068
      ],
      "voteCount": 18729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.537207942488408
      }
    },
    {
      "id": "f910b885859995ec8f04d038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1399.8036370127452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.3222142959278,
        1417.2850597295626
      ],
      "voteCount": 1038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.55314750682147
      }
    },
    {
      "id": "bcb3dc28310ddbd1c8c412b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4-fast-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1413.1168565745352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.9584307119853,
        1439.2752824370848
      ],
      "voteCount": 521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.1258827819139
      }
    },
    {
      "id": "18a7312884b13e157e020d48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1492.3350709292888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.170062005476,
        1503.5000798531019
      ],
      "voteCount": 3307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.45054290242244
      }
    },
    {
      "id": "a05601b2ba645bccb5bb97a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1498.8927223836556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.0909534372356,
        1504.6944913300756
      ],
      "voteCount": 14270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.762432315117275
      }
    },
    {
      "id": "eef25e37e931780d75aa4dce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1428.909019584696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.0030626599857,
        1435.8149765094058
      ],
      "voteCount": 9576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.415137912979835
      }
    },
    {
      "id": "38a64ec8044d7e9f1577ca19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1472.119137595823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.7282876033644,
        1476.5099875882818
      ],
      "voteCount": 29452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.018813048942438
      }
    },
    {
      "id": "4b7b9b7474fcf99f10ecf768",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1474.2502894192494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.7212965581796,
        1478.7792822803192
      ],
      "voteCount": 46350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.339579907800552
      }
    },
    {
      "id": "b928ed699034f708a737920c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1468.8032198584117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.2659221818112,
        1478.340517535012
      ],
      "voteCount": 4350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.678516734860896
      }
    },
    {
      "id": "aac5c87460113c8f39f2d153",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1490.361086550225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.4415915978207,
        1508.2805815026295
      ],
      "voteCount": 1494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.59019693753451
      }
    },
    {
      "id": "062e1e3ec6879403a50e0e8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1459.0503031078667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.0143015553722,
        1478.086304660361
      ],
      "voteCount": 1078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.33118302725727
      }
    },
    {
      "id": "aabe0d70af96f1e7ce7ba497",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1478.1665003904661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.81212122873,
        1483.5208795522026
      ],
      "voteCount": 17364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.4631481283082195
      }
    },
    {
      "id": "a3bc2051668a3f75eaecaed7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1477.9035847511109,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.735151701884,
        1482.0720178003378
      ],
      "voteCount": 35775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.523238409398547
      }
    },
    {
      "id": "0b70b5968518b5fceeb1795e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1461.4300588382348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.182332802181,
        1467.6777848742884
      ],
      "voteCount": 12053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.161264884919245
      }
    },
    {
      "id": "a80d9bcb86d12e355c9f9cb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1434.6099072939292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.2798767896136,
        1440.939937798245
      ],
      "voteCount": 11957,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.430747290511716
      }
    },
    {
      "id": "bc7070afc04f1ee4b634f809",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1479.509004867577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.1353963705008,
        1488.8826133646535
      ],
      "voteCount": 4593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.872700283322253
      }
    },
    {
      "id": "48d39deb2326bf33c1902431",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1480.0159554038312,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.4641862027745,
        1486.5677246048879
      ],
      "voteCount": 10434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.17431727568531
      }
    },
    {
      "id": "c6345369a915f8df78a6f98b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1437.6152373404122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.2388580406496,
        1448.991616640175
      ],
      "voteCount": 2905,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.690848194145964
      }
    },
    {
      "id": "711e57433a79101a4ddd6d68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1503.329888963061,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.2515870851182,
        1513.4081908410037
      ],
      "voteCount": 4219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.44104062648558
      }
    },
    {
      "id": "ee0439061b042e130b234aa8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1497.2716762973666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.375085546293,
        1502.1682670484406
      ],
      "voteCount": 22596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.241535339215273
      }
    },
    {
      "id": "14bbe489385e7634a9a788fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1428.2620414930168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.475479996301,
        1434.0486029897327
      ],
      "voteCount": 14363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.716556786940767
      }
    },
    {
      "id": "214cfaa1ec42275f2fc06218",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1431.0458294527568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.7507388714384,
        1436.3409200340752
      ],
      "voteCount": 17643,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.298785584612888
      }
    },
    {
      "id": "2312849c48358aa34de1adae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1413.0331964192612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.0037994457,
        1440.0625933928225
      ],
      "voteCount": 529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.18511842913668
      }
    },
    {
      "id": "c1a175873869ffe6eb69cf44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1433.2208702967714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.0351806661542,
        1453.4065599273888
      ],
      "voteCount": 1035,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.06961700815121
      }
    },
    {
      "id": "4a74f9902c9e3f6cf0fb8702",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1447.8259183883613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.5055035054215,
        1453.146333271301
      ],
      "voteCount": 18634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.36876687942527
      }
    },
    {
      "id": "84495864aa4b189f3ec816b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1444.3657178147425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.3685086450566,
        1454.3629269844284
      ],
      "voteCount": 3727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.017249135679666
      }
    },
    {
      "id": "7f2dcd3f85910dff6377128e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1461.0557584310898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.6325295082063,
        1467.4789873539735
      ],
      "voteCount": 11701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.740156727311785
      }
    },
    {
      "id": "ea64cd323f7e2231d2713b9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1466.431872731223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.1366623431059,
        1469.7270831193403
      ],
      "voteCount": 63569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.826637485598135
      }
    },
    {
      "id": "bb0ca02766657c202c1faf85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1461.6873998958085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.6842684854535,
        1469.6905313061636
      ],
      "voteCount": 6489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.673382524985378
      }
    },
    {
      "id": "8b26ffe6d40d63572f23f16c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1-thinking",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1466.5646923418146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.092557219984,
        1483.0368274636455
      ],
      "voteCount": 1634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.63234259083514
      }
    },
    {
      "id": "ced45b96f60e65459603e983",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1503.2052975433294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.293865843335,
        1514.116729243324
      ],
      "voteCount": 3506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.993262534084163
      }
    },
    {
      "id": "b8b456f0c206cb41bf118f1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1490.4753400594318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.7076769244986,
        1496.2430031943652
      ],
      "voteCount": 14818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.659714861151956
      }
    },
    {
      "id": "7d21f53089102d503b8ceb45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1432.2171682818105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.2600728516413,
        1439.1742637119796
      ],
      "voteCount": 9505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.599686495073371
      }
    },
    {
      "id": "94cd643e1a1409aca0d71ed1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1469.3795045002405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.976052550862,
        1473.782956449619
      ],
      "voteCount": 30631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.047662873809248
      }
    },
    {
      "id": "16c1ee021b6035d2a8328b49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1466.45522444003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.8904234329113,
        1471.0200254471486
      ],
      "voteCount": 46949,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.424347678110994
      }
    },
    {
      "id": "5f65979694c356edb00e8418",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1455.059256859021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.5777011292064,
        1464.5408125888353
      ],
      "voteCount": 4413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.40254139216149
      }
    },
    {
      "id": "0903d3928777bbd6e702b85e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1477.656961876024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.0166296587443,
        1495.2972940933041
      ],
      "voteCount": 1536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.00602798594463
      }
    },
    {
      "id": "e2ab7e486378c63b4a33deac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1464.325229657058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.6798093442774,
        1482.9706499698386
      ],
      "voteCount": 1181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.49991549237305
      }
    },
    {
      "id": "8bef37cc5b162d7dbfa0e858",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1476.4271394842276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.0345033593815,
        1481.8197756090738
      ],
      "voteCount": 17893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.570177303043798
      }
    },
    {
      "id": "d7f6ee18c6679876dc359a68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1474.2240155917443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.0568211295067,
        1478.3912100539821
      ],
      "voteCount": 36654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.520550784654023
      }
    },
    {
      "id": "31526d1fc3e9d36f0ec89e36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1463.207701047074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.9162253516713,
        1469.4991767424763
      ],
      "voteCount": 12305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.304071519029828
      }
    },
    {
      "id": "98f87d22a7004bace5772350",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1428.926621728929,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.6218935908996,
        1435.2313498669582
      ],
      "voteCount": 12108,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.347526486637122
      }
    },
    {
      "id": "37c1adfe494931b0df353473",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1474.9138051514292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.552148072645,
        1484.2754622302136
      ],
      "voteCount": 4742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.814411751241053
      }
    },
    {
      "id": "42b4182cb830ba3df55b07c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1479.1046597097757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.514153183587,
        1485.6951662359643
      ],
      "voteCount": 10390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.306844170175754
      }
    },
    {
      "id": "5faaacae2647389c60600d2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1425.9350934194924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.888100456749,
        1436.9820863822358
      ],
      "voteCount": 3229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.768153510194846
      }
    },
    {
      "id": "0ffa6c1b7f0e6c24290fdf51",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1486.6629495273637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.6623718281658,
        1496.6635272265614
      ],
      "voteCount": 4238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.034784956935358
      }
    },
    {
      "id": "7fef4d58dc46685cb2966b8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1488.4643435365674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.6021174032824,
        1493.3265696698527
      ],
      "voteCount": 23588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.1542356887557785
      }
    },
    {
      "id": "1a7521aeeed9a1704e438d23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1427.0294158576842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.2138037502245,
        1432.8450279651438
      ],
      "voteCount": 14386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.804296951521076
      }
    },
    {
      "id": "496f285b9a8c9a2796bf6543",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1430.3498352879074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.0620757592894,
        1435.6375948165253
      ],
      "voteCount": 17848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.278589238511572
      }
    },
    {
      "id": "fca8a1f77f2253fc0e41fcdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1431.411446799007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.7965105034434,
        1457.0263830945707
      ],
      "voteCount": 586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.8009878672143
      }
    },
    {
      "id": "cbb5e836296091bea4e3f023",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1440.0653215112022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.1657670481927,
        1459.9648759742117
      ],
      "voteCount": 1060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.08382474206215
      }
    },
    {
      "id": "dfb92b62bef3dd35f8b1387c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1449.044085618698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.7086109902666,
        1454.3795602471296
      ],
      "voteCount": 18583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.410541369669388
      }
    },
    {
      "id": "7c0952012fe6ad1ea2ed1da8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1430.713206553207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.225984383159,
        1440.200428723255
      ],
      "voteCount": 4143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.43052176401812
      }
    },
    {
      "id": "b07decc720ef8ead425c4dbf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1461.6177307912021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.154880161781,
        1468.080581420623
      ],
      "voteCount": 11890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.87306677171679
      }
    },
    {
      "id": "4350394716fe8babf7f9a2d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1460.114460210335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.8352652058907,
        1463.393655214779
      ],
      "voteCount": 65655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.7992282044634575
      }
    },
    {
      "id": "8c000155e429d3833463d970",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1451.0319246916627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.992776663952,
        1459.0710727193732
      ],
      "voteCount": 6298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.82379117622987
      }
    },
    {
      "id": "65f0e787ace3030804fa84f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1443.1196024992394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.8872237842968,
        1459.351981214182
      ],
      "voteCount": 1635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.59116055751767
      }
    },
    {
      "id": "2016f29d344ca215b4fcb68e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1507.7977114390146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.6505322438886,
        1523.9448906341406
      ],
      "voteCount": 1518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.87301598937817
      }
    },
    {
      "id": "2091767de19bd4cdbde0f255",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1512.3916821440662,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.8680090233559,
        1519.9153552647765
      ],
      "voteCount": 7705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.735458550892252
      }
    },
    {
      "id": "9e917827a64013c383690e11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1447.3436712614994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.0722787607665,
        1456.6150637622322
      ],
      "voteCount": 4697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.37658215664858
      }
    },
    {
      "id": "9ca3b1425a40feb9af182d12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1478.001427654335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.065028897089,
        1483.9378264115812
      ],
      "voteCount": 13717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.173814389259897
      }
    },
    {
      "id": "f356339fd5f1ff64e804ce6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1485.2226446422462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.108327316169,
        1491.3369619683235
      ],
      "voteCount": 21575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.73194770761966
      }
    },
    {
      "id": "2f12a1148176f6c6f79ccc39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1480.4689928151417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.2012088865606,
        1492.7367767437227
      ],
      "voteCount": 2555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.177440015133534
      }
    },
    {
      "id": "fa587075739589ff71c7b329",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1512.6232489088238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.6103587845337,
        1535.6361390331137
      ],
      "voteCount": 809,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.86249875169872
      }
    },
    {
      "id": "778f0d67975f2f908aee4052",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1440.9028939735429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.102950586972,
        1468.7028373601138
      ],
      "voteCount": 453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.18316722106815
      }
    },
    {
      "id": "af35dc61df4c63a5f7e813e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1489.3269175996602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.3297084952121,
        1496.3241267041083
      ],
      "voteCount": 9039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.745401561411182
      }
    },
    {
      "id": "74c03e322959b3e147baf8a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1491.3724426465242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.867297237087,
        1496.8775880559613
      ],
      "voteCount": 18349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.889353340398739
      }
    },
    {
      "id": "d5f1b10f8823e7a9a4880301",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1468.2655638584267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.8927298048336,
        1476.63839791202
      ],
      "voteCount": 5679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.249408196531107
      }
    },
    {
      "id": "3f3e19796af9f02a55c0c2fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1448.043804836301,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.6131478430577,
        1456.474461829544
      ],
      "voteCount": 5835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.502340036766704
      }
    },
    {
      "id": "84aa0768ca12dd3f0d18f6a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1472.0256191437607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.7405349323997,
        1485.3107033551214
      ],
      "voteCount": 2189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.944384865503
      }
    },
    {
      "id": "36bf2ccdbbaba23614f16dfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1484.0767398043592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.9570270824404,
        1493.196452526278
      ],
      "voteCount": 4678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.650410433216503
      }
    },
    {
      "id": "7ef0d34d8d004855a19b5f33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1470.1699502127396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.717495152767,
        1485.6224052727123
      ],
      "voteCount": 1582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.1582525092195
      }
    },
    {
      "id": "eeced8b337043abebbba5540",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1491.6836960358964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.8278945615102,
        1505.5394975102827
      ],
      "voteCount": 2089,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.976647794161025
      }
    },
    {
      "id": "94e8c687c770b3fd405b6b9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1506.1897044387695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1499.7462434898139,
        1512.633165387725
      ],
      "voteCount": 11053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.80792244265517
      }
    },
    {
      "id": "8f33cb7921112d4e38356e92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1455.029247043718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.280586936012,
        1462.777907151424
      ],
      "voteCount": 6884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.629930260167347
      }
    },
    {
      "id": "9e4a729c52245d33234bb547",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1450.3315979534962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.498706420594,
        1457.1644894863985
      ],
      "voteCount": 9354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.153821993064808
      }
    },
    {
      "id": "a024ca1230b73c4291aab0de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1438.193948748027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.7852013841289,
        1478.602696111925
      ],
      "voteCount": 225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 425.06426327493324
      }
    },
    {
      "id": "5ec9378fc728bac6312c5ead",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1441.0521360684381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.6394796932939,
        1470.4647924435826
      ],
      "voteCount": 455,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 225.2020379294357
      }
    },
    {
      "id": "c1b542b134e927d192b0c83f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1464.4324948001574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.7326309664293,
        1471.1323586338856
      ],
      "voteCount": 10946,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.685189790057015
      }
    },
    {
      "id": "2aba069fd0655743ed149041",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1471.965988756017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.4515602239574,
        1486.4804172880765
      ],
      "voteCount": 1734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.84078977428607
      }
    },
    {
      "id": "d900cdf68e0be0604d72bb8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1483.6908373159492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.9289895331035,
        1492.4526850987952
      ],
      "voteCount": 5271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.984589228497146
      }
    },
    {
      "id": "e81d6733caf6369e06920045",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1475.1102770894493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.5694114508935,
        1479.651142728005
      ],
      "voteCount": 29068,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.36761207391783
      }
    },
    {
      "id": "ba2f4bf678453fdf09adf0fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1489.111532956729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.043852025167,
        1500.1792138882906
      ],
      "voteCount": 3237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.887250890983797
      }
    },
    {
      "id": "2e81be21c9057f4a1590f863",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta-0309-reasoning",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1459.4811584250092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.7003519401453,
        1480.2619649098733
      ],
      "voteCount": 902,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.41612583089847
      }
    },
    {
      "id": "f22def8a269c662b69690a2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1514.3229306484898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.5626647403776,
        1532.0831965566017
      ],
      "voteCount": 1210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.1112654983117
      }
    },
    {
      "id": "ac08b30410b8ed1cf0d02f42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1509.4787367122808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1501.4107634937775,
        1517.546709930784
      ],
      "voteCount": 6203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.944654333877295
      }
    },
    {
      "id": "fbd49400c1e708eb5eb52870",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1462.0684110256984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.8485582860026,
        1472.288263765394
      ],
      "voteCount": 3685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.188991186997278
      }
    },
    {
      "id": "13a3eb218bc319499cef274d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1482.7659017752903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.5624083967223,
        1488.9693951538584
      ],
      "voteCount": 11634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.01789473588175
      }
    },
    {
      "id": "2fda8c6df1967e08ccc59f5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1487.164950775032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.7902368593545,
        1493.5396646907095
      ],
      "voteCount": 17959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.578527430209562
      }
    },
    {
      "id": "8706b8847fe5a45dd42b8e01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1472.886835708098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.2220941643259,
        1486.5515772518702
      ],
      "voteCount": 2030,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.60787793746333
      }
    },
    {
      "id": "7f920f5b631a3d7b8844b721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1485.1908536521555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.809598770502,
        1509.5721085338093
      ],
      "voteCount": 695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.74475123925737
      }
    },
    {
      "id": "8653b3f5515ad5ad971b8307",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1484.2445176009285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.8202385532695,
        1512.6687966485874
      ],
      "voteCount": 427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.32104653231642
      }
    },
    {
      "id": "18a911dfb248bdea4a5a34d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1488.127752043119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.6452553157824,
        1495.6102487704559
      ],
      "voteCount": 7386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.574608212119028
      }
    },
    {
      "id": "9651ae95d069dd8a6f4cec6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1488.9046950444535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.1339255387418,
        1494.6754645501653
      ],
      "voteCount": 14726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.669045339925365
      }
    },
    {
      "id": "ac22dba57e5aa7719f0f7dcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1471.8442295454001,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.6947863952864,
        1480.9936726955139
      ],
      "voteCount": 4550,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.791801985797445
      }
    },
    {
      "id": "366d3dda15890ee4884447c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1448.9136161209367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.700072089961,
        1458.1271601519122
      ],
      "voteCount": 4591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.098217779512005
      }
    },
    {
      "id": "7d34eaffdece3f254146f794",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1473.509903767578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.1292981115782,
        1487.890509423578
      ],
      "voteCount": 1840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.83418869917998
      }
    },
    {
      "id": "2a444229293d7c3c8e617977",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1480.9333511296722,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.166355438495,
        1490.7003468208493
      ],
      "voteCount": 3981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.832806827859415
      }
    },
    {
      "id": "13ebe757450084e214286756",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1455.2698926718056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4658733818026,
        1472.0739119618086
      ],
      "voteCount": 1259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.50724750129476
      }
    },
    {
      "id": "98a7339d9dcd2396360ca0c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1502.654954323458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.999265291866,
        1517.3106433550502
      ],
      "voteCount": 1769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.91345137780652
      }
    },
    {
      "id": "ee193420f3351fb795c20383",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1504.975753100244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.1855635551606,
        1511.7659426453276
      ],
      "voteCount": 9200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.002386647953163
      }
    },
    {
      "id": "d845dd7ea77e09cde39e9f3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1451.8172379600342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.4505149646518,
        1460.1839609554168
      ],
      "voteCount": 5501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.222778623672415
      }
    },
    {
      "id": "1797fdf939c6e5c3e2b5bb8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1450.6135087142607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.202695959434,
        1458.0243214690875
      ],
      "voteCount": 7377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.296689942697117
      }
    },
    {
      "id": "df4cca4f56d9ae3a3a8d29c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1449.9392476035885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.052224964194,
        1493.826270242983
      ],
      "voteCount": 189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 501.39044723709696
      }
    },
    {
      "id": "528b7ba71f1d0a564dac8aad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1445.3807548251111,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.6386625484286,
        1475.122847101794
      ],
      "voteCount": 424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.27503203454017
      }
    },
    {
      "id": "314c4c7d622a673e239d2567",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1465.561279758529,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.196515088167,
        1472.9260444288914
      ],
      "voteCount": 8173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.11957310530662
      }
    },
    {
      "id": "b3aba7d653c998f8e22be92d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1452.1380580228988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.0161500530935,
        1467.2599659927043
      ],
      "voteCount": 1491,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.527411673762444
      }
    },
    {
      "id": "3966571fe49446361fcbf440",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1485.6476469778186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.617882416065,
        1495.677411539572
      ],
      "voteCount": 3885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.18697267358173
      }
    },
    {
      "id": "9c1f14dcc7117d390f6e081f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1476.2101175578007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.4381593680562,
        1480.982075747545
      ],
      "voteCount": 24468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.927848254417529
      }
    },
    {
      "id": "34f3df750ff0547f9cac3b94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1476.9360305791279,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.9921106333165,
        1488.879950524939
      ],
      "voteCount": 2620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.13621057277628
      }
    },
    {
      "id": "39898708ba08795480c243f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-beta1",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1470.083901758505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.9405381393915,
        1492.2272653776186
      ],
      "voteCount": 768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.6412361176071
      }
    },
    {
      "id": "b5651bdc162aa3737c27a4be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1502.304459928338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.2571367959335,
        1518.3517830607427
      ],
      "voteCount": 1509,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.03614218862734
      }
    },
    {
      "id": "7ab0ea3126544c0fea49790e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1514.5392172718964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.0989078557532,
        1521.9795266880396
      ],
      "voteCount": 7631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.410724360686011
      }
    },
    {
      "id": "cbfde8d8c006e2589e830fb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1444.1595041750254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.847163654206,
        1453.471844695845
      ],
      "voteCount": 4566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.574675409386984
      }
    },
    {
      "id": "e3d9091df8c3ada225ab41c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1474.7584857470763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.7672411516742,
        1480.7497303424786
      ],
      "voteCount": 13380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.34410948480494
      }
    },
    {
      "id": "42371e7b3e2c7eca5f17a6f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1481.3976090414392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.2625361977477,
        1487.5326818851308
      ],
      "voteCount": 21054,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.798131531343685
      }
    },
    {
      "id": "e3a1f1d85742a6729a76dcd4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1487.313455550061,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.0588810115892,
        1499.568030088533
      ],
      "voteCount": 2524,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.093116476992556
      }
    },
    {
      "id": "afff94a074547a04b87e79eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1498.7354135207427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.3405412478412,
        1521.1302857936441
      ],
      "voteCount": 850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.55725117182155
      }
    },
    {
      "id": "2ec7224a2104ceb1b3affb30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1466.1389730531253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.5586521816142,
        1493.719293924636
      ],
      "voteCount": 483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.0169864838098
      }
    },
    {
      "id": "05aa8e251ceea8d35cb7ec11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1482.495626114771,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.4277967721007,
        1489.5634554574413
      ],
      "voteCount": 8761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.003969051550348
      }
    },
    {
      "id": "63390857b0862020c5e329a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1486.0618329014997,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.4909375561829,
        1491.6327282468164
      ],
      "voteCount": 17791,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.078929489309314
      }
    },
    {
      "id": "0783ee9734bd55cd5219ce76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1457.9746763708085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.524392309971,
        1466.4249604316462
      ],
      "voteCount": 5460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.588589398426308
      }
    },
    {
      "id": "8c067d89881e812d1900a5cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1441.8960748224622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.408789067776,
        1450.3833605771486
      ],
      "voteCount": 5624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.751735432812648
      }
    },
    {
      "id": "a08c1f4aa35cbdc2bccc0846",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1476.0120310129603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.8468702247903,
        1489.1771918011302
      ],
      "voteCount": 2187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.118655872262956
      }
    },
    {
      "id": "4595c7e8ad76ae4730d2f4fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1484.823159395229,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.7613460859095,
        1493.884972704548
      ],
      "voteCount": 4665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.376373999010685
      }
    },
    {
      "id": "508902da45a8b3019d62fdf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1467.693052262523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.1338491992913,
        1483.2522553257547
      ],
      "voteCount": 1561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.02001694219242
      }
    },
    {
      "id": "a8f75210c2fc5f6d0e8b4999",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1492.1204181704607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.3010898976531,
        1505.939746443268
      ],
      "voteCount": 2029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.713882882937746
      }
    },
    {
      "id": "302e34228122fdfb4b246d11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1507.1631255729394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1500.730032645533,
        1513.5962185003457
      ],
      "voteCount": 11084,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.773168877850631
      }
    },
    {
      "id": "0f9923da5075fe941825ba87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1445.858887298879,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.0712617738377,
        1453.6465128239204
      ],
      "voteCount": 6671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.7875208739885
      }
    },
    {
      "id": "8050cfed4de35ea5cb9d3f8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1445.0331710390265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.1745175395772,
        1451.8918245384755
      ],
      "voteCount": 9086,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.245641570356572
      }
    },
    {
      "id": "70fd0b2af9bf022f66e5c477",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1399.226570183072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.4018461341873,
        1444.0512942319567
      ],
      "voteCount": 182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 523.0450148872361
      }
    },
    {
      "id": "c4f03ee61783e8453ab0ae64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1431.25770177046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.8265092235545,
        1459.6888943173653
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.42336970649862
      }
    },
    {
      "id": "5e1929fdbadc4a1506bcf943",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1459.3052740662022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.5683982718635,
        1466.0421498605408
      ],
      "voteCount": 10714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.814651044507636
      }
    },
    {
      "id": "cea28252daa2e0ea69586dbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1458.7727740265211,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.2961448481815,
        1473.2494032048608
      ],
      "voteCount": 1704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.55552230266708
      }
    },
    {
      "id": "0f58e0fe321bb94e3a9f51df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1481.0744522588452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.1041890653544,
        1490.044715452336
      ],
      "voteCount": 4828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.946631349274213
      }
    },
    {
      "id": "ba256e4a19e0b48a21564402",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1472.2468751344097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.6612970145914,
        1476.832453254228
      ],
      "voteCount": 28630,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.473838891538109
      }
    },
    {
      "id": "fdbec267dcb2eff88bccd4f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1481.6021140063099,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.430775400785,
        1492.7734526118345
      ],
      "voteCount": 3163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.48734714192216
      }
    },
    {
      "id": "ade8a5721ac02395828db2fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.20-multi-agent-beta-0309",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1451.5398662499983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.6737607436305,
        1473.4059717563662
      ],
      "voteCount": 826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.46484326212672
      }
    },
    {
      "id": "2fc3997c963c0bdfb2316a11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1490.0395391845498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.047842603602,
        1512.0312357654975
      ],
      "voteCount": 787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.89871220357878
      }
    },
    {
      "id": "437c90fb2f817819be0abf75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1492.8975793641496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.4328785119064,
        1502.3622802163925
      ],
      "voteCount": 4422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.319412338842596
      }
    },
    {
      "id": "c022fb3415610339db8cd1c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1431.7159606382463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.3653581174033,
        1444.0665631590896
      ],
      "voteCount": 2523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.70819153549998
      }
    },
    {
      "id": "6f03ebf4efed64288a378fc6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1454.3326982416343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.0601456861234,
        1461.6052507971451
      ],
      "voteCount": 7810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.768212322814856
      }
    },
    {
      "id": "bafd11149070dbb836be6402",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1446.0507624929548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.6241507075667,
        1453.477374278343
      ],
      "voteCount": 11832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.357712833922845
      }
    },
    {
      "id": "bc91cf2434688a321b285733",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1442.509823280141,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.6904708714121,
        1458.32917568887
      ],
      "voteCount": 1461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.14501972100787
      }
    },
    {
      "id": "6d3c72cd86170b1b95b05e5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1460.7900579321754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.5651576650032,
        1488.0149581993478
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.94628138784694
      }
    },
    {
      "id": "8d72b0967e25048620a72d83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1430.8023821093004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.2912062406722,
        1471.3135579779287
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 427.2219088794978
      }
    },
    {
      "id": "938185bfda2791749a92b243",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1462.7696298161306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.0610020599624,
        1471.4782575722988
      ],
      "voteCount": 5344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.742551185749694
      }
    },
    {
      "id": "6decdb4ff0d74c79e9d78a57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1459.0792119734467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.3368988800949,
        1465.8215250667986
      ],
      "voteCount": 10268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.833729833024753
      }
    },
    {
      "id": "5be61314a6006b4a4cfb1535",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1442.248944391877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.1849822783406,
        1453.3129065054136
      ],
      "voteCount": 3216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.86582581344775
      }
    },
    {
      "id": "866c6f61633b7b9abf232ec9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1424.2358412829296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.463726205589,
        1435.0079563602703
      ],
      "voteCount": 3401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.206874173521847
      }
    },
    {
      "id": "47849410d98fa80b0731254e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1440.5735285137462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.019872095296,
        1458.1271849321963
      ],
      "voteCount": 1210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.21193719351677
      }
    },
    {
      "id": "e47b624dc5ca9b8876edb976",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1468.7196022221285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.705492142934,
        1480.7337123013228
      ],
      "voteCount": 2601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.573965447043115
      }
    },
    {
      "id": "8aedc3bd8f7f570c53438514",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1448.226289662009,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.397993028234,
        1469.0545862957842
      ],
      "voteCount": 813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.93051960560692
      }
    },
    {
      "id": "6846f550783b673e88b599a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1470.6742341544086,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.9005099863311,
        1488.447958322486
      ],
      "voteCount": 1196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.23575614063701
      }
    },
    {
      "id": "3df7148492ba71443f381833",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1480.995865409248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.9522694788463,
        1489.0394613396493
      ],
      "voteCount": 6280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.8424128726908
      }
    },
    {
      "id": "d4769b9b47adaa5b527f2054",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1429.7455802077857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.6037454064676,
        1439.8874150091037
      ],
      "voteCount": 3791,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.775456392538118
      }
    },
    {
      "id": "0822fdb65230bd42d5d3953f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1420.9578473569036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.266370707167,
        1429.6493240066402
      ],
      "voteCount": 5349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.66486428175943
      }
    },
    {
      "id": "de8971cae31720e8866927bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1403.6803892848764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.4670263818434,
        1445.893752187909
      ],
      "voteCount": 203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 463.87794084466134
      }
    },
    {
      "id": "f904f6430a87dcca2f8a9341",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1445.8943587624597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.6951588652057,
        1454.0935586597134
      ],
      "voteCount": 6584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.50035132303704
      }
    },
    {
      "id": "e33f37845a42cb3fba2fe43f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1425.3960152562531,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.0459657426704,
        1445.746064769836
      ],
      "voteCount": 846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.80397097435105
      }
    },
    {
      "id": "09daff90d76c30f750962155",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1464.5790513138613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.084002252299,
        1476.0741003754238
      ],
      "voteCount": 2974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.3973888815116
      }
    },
    {
      "id": "732656f2a9cbf8990a2d3f96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1446.7662706903084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.1353822398476,
        1452.3971591407692
      ],
      "voteCount": 15773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.25387078750557
      }
    },
    {
      "id": "60f348508a4759f13c84a6d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1458.834078230917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.798918696751,
        1473.8692377650827
      ],
      "voteCount": 1660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.846399966608324
      }
    },
    {
      "id": "48f6ffb4561521f3dd2117d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "grok-4.3",
      "organization": "xai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1434.4895099981943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.8871795615828,
        1463.091840434806
      ],
      "voteCount": 435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.9642265063496
      }
    },
    {
      "id": "04a5d28b6dcd541e71371208",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1111.9816683435527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.161770393408,
        1147.8015662936973
      ],
      "voteCount": 263,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 334.00464486221745
      }
    },
    {
      "id": "17d26f842a7b8cd3dfc69944",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1134.685319284714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.1465517484476,
        1162.2240868209806
      ],
      "voteCount": 515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.420759356074
      }
    },
    {
      "id": "d166cc362a70e5db3fa555c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1155.61891901796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.1700526993443,
        1169.0677853365755
      ],
      "voteCount": 2352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.0841973579488
      }
    },
    {
      "id": "45304dc784f3b843175e09cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 973.173679669119,
      "unit": "Arena rating",
      "confidenceInterval": [
        955.0886317247503,
        991.2587276134876
      ],
      "voteCount": 2032,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.14186261432181
      }
    },
    {
      "id": "71733c859266772247ab5694",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1117.888658262466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.687602903884,
        1146.089713621048
      ],
      "voteCount": 434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 207.0305996913173
      }
    },
    {
      "id": "357074fa2e87e6e6e8d99af8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1103.7079678392859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.2572292353502,
        1129.1587064432215
      ],
      "voteCount": 517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.61825825034165
      }
    },
    {
      "id": "42f366c61b0de75d18dfad3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1081.9392403746806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1043.5710297618614,
        1120.3074509874996
      ],
      "voteCount": 261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 383.21889009958016
      }
    },
    {
      "id": "7d66ff8b6d63e94892cccac9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1140.1231982729503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.6465636582702,
        1169.5998328876303
      ],
      "voteCount": 443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.1828197992641
      }
    },
    {
      "id": "7e93230a40530bfc32424d55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1161.7407672719617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.434756078824,
        1188.0467784650991
      ],
      "voteCount": 526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.1415184162878
      }
    },
    {
      "id": "8e21886821da7c7798c3bf49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1075.5119223723864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.2969436783865,
        1110.7269010663865
      ],
      "voteCount": 236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 322.8186952671284
      }
    },
    {
      "id": "3c243fb9675a94bdecbc3672",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1116.0485586687255,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.2761077874625,
        1139.8210095499885
      ],
      "voteCount": 635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.11323153008436
      }
    },
    {
      "id": "6c2af7b6230a0ea563a8b96e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1121.667607481549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.6714055382429,
        1144.6638094248556
      ],
      "voteCount": 714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.66262466970034
      }
    },
    {
      "id": "792655a57fea02e5885756c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1063.4768543487498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1042.207302783686,
        1084.7464059138142
      ],
      "voteCount": 777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.76615210394982
      }
    },
    {
      "id": "2e487d0e003cdfc1da9ebe77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1079.7581278431799,
      "unit": "Arena rating",
      "confidenceInterval": [
        1047.4868969557408,
        1112.0293587306187
      ],
      "voteCount": 280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.1033468275511
      }
    },
    {
      "id": "1c1ec50679c1811aa269e31a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1069.6758494403305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1036.1839207768667,
        1103.1677781037943
      ],
      "voteCount": 331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.00086164033553
      }
    },
    {
      "id": "5249ffdd93091eeaeca14d9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "guanaco-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1126.3107348735248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.194291936174,
        1138.4271778108757
      ],
      "voteCount": 2921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.216780735281205
      }
    },
    {
      "id": "3cfca98fa20d4a5bfd69401b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1486.2294599270542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.9623658374546,
        1518.4965540166538
      ],
      "voteCount": 334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.03384666738293
      }
    },
    {
      "id": "84573c42effbf52745a64276",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1462.0009425795254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.4341315870763,
        1476.5677535719744
      ],
      "voteCount": 1648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.237344038844086
      }
    },
    {
      "id": "bdd3163c4910292f36ac45fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1367.075661933818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.918351608777,
        1387.2329722588593
      ],
      "voteCount": 890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.77157754527096
      }
    },
    {
      "id": "0f115638fa03718071cd70e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1422.0234319174615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.0757403399675,
        1432.9711234949555
      ],
      "voteCount": 2831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.199592777172242
      }
    },
    {
      "id": "c78ce4b6477e538f0105ec52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1403.0607288362257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.9285453803784,
        1414.192912292073
      ],
      "voteCount": 4156,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.2600122190688
      }
    },
    {
      "id": "ac9f1f949b9774d11c0d30d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1452.7983317853364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.356896767902,
        1476.2397668027706
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.04484346321868
      }
    },
    {
      "id": "9496a6c6ee2641325449b003",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1432.5448552134908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.809581332964,
        1477.2801290940176
      ],
      "voteCount": 178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 520.959568376718
      }
    },
    {
      "id": "382ba4a777a7265ad7ab4944",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1439.976385852449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.5007114848981,
        1453.4520602199998
      ],
      "voteCount": 1877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.272093268841274
      }
    },
    {
      "id": "62dc29a4862c98af1d27d6f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1441.5094061829163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.7427209524587,
        1451.276091413374
      ],
      "voteCount": 3706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.831228146187133
      }
    },
    {
      "id": "8a2f8fdc42664be388f745ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1411.2104400363864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.952977449801,
        1428.4679026229717
      ],
      "voteCount": 1161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.52784263182072
      }
    },
    {
      "id": "e874c4c5024ad1c29e7de3df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1374.2327733583986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.2141284079853,
        1392.2514183088122
      ],
      "voteCount": 1111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.51777853247766
      }
    },
    {
      "id": "72a01ae3385074b3037c63ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1442.0228439784062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.686363979861,
        1470.3593239769514
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.0237423299673
      }
    },
    {
      "id": "39cc8d8720afcd8d97279573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1438.2222809225484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.1579020804895,
        1456.2866597646073
      ],
      "voteCount": 1050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.94735937074574
      }
    },
    {
      "id": "ef024f9a1d1bda91b4f9379d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1451.5993851636777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.3147662674787,
        1480.8840040598766
      ],
      "voteCount": 360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.24563243415363
      }
    },
    {
      "id": "ead154a52cf42981b31bca2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1430.05832953531,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.4807598395969,
        1460.6358992310227
      ],
      "voteCount": 391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 243.39393239343173
      }
    },
    {
      "id": "6e05d77c13a624c8697b7689",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1450.6605178488248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.2905618508644,
        1463.0304738467853
      ],
      "voteCount": 2271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.832735045127755
      }
    },
    {
      "id": "40b3e5034f8d978cb8115c9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1390.5535900874954,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.3773933190591,
        1406.7297868559317
      ],
      "voteCount": 1337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.11717998421432
      }
    },
    {
      "id": "2fa21b9a40bd5785fbb9d0eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1407.3033893809036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.7152918937936,
        1420.8914868680135
      ],
      "voteCount": 1856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.064134470102566
      }
    },
    {
      "id": "c4f6288a135064c7e7571385",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1429.592912417573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.0366160900317,
        1442.1492087451143
      ],
      "voteCount": 2294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.041850199122976
      }
    },
    {
      "id": "98fe91bb9b232e01cab29184",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1428.070962062768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.2299573863907,
        1455.9119667391456
      ],
      "voteCount": 378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.77791239475303
      }
    },
    {
      "id": "c6030d1ab17ad80ca3668bf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1418.2980805270315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.3479575623371,
        1437.2482034917261
      ],
      "voteCount": 990,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.48197576465304
      }
    },
    {
      "id": "9fa22720bef8cda8e8b61e0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1415.8526209839351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.0203338219567,
        1423.6849081459136
      ],
      "voteCount": 5812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.969121380977835
      }
    },
    {
      "id": "7af75f66978221f18c6dd9c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1413.423676450543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.7548738843595,
        1438.0924790167269
      ],
      "voteCount": 562,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.4163330792618
      }
    },
    {
      "id": "b5d24b010e9c1d0fa1c9e48e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-hy3-preview",
      "organization": "tencent",
      "license": "tencent-hunyuan-community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1393.3584356336332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.779831801692,
        1437.9370394655743
      ],
      "voteCount": 170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 517.3169913731075
      }
    },
    {
      "id": "69c5e091117f618526e15355",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1388.7689888047403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.7387005308665,
        1421.799277078614
      ],
      "voteCount": 295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 284.0066741254488
      }
    },
    {
      "id": "8614ebf72eb409e9104656f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1366.7332941018526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.9476063220059,
        1391.5189818816993
      ],
      "voteCount": 519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.92109961210951
      }
    },
    {
      "id": "5c7649e7ac2ce5c362bcf37d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1302.8225444703207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.9342916475816,
        1326.7107972930594
      ],
      "voteCount": 568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.54997790135894
      }
    },
    {
      "id": "19e0295e5c24d055d09d164b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1343.5983636589087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.3176208650393,
        1355.8791064527782
      ],
      "voteCount": 2255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.260252578191746
      }
    },
    {
      "id": "d16c32c8d9507c3c0b990311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1270.1352232506779,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.9014503928404,
        1285.3689961085156
      ],
      "voteCount": 2472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.41138179954703
      }
    },
    {
      "id": "6a3496bf052087a57fc62efc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1322.1403593793116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.8817906305712,
        1358.3989281280524
      ],
      "voteCount": 228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 342.23555921643157
      }
    },
    {
      "id": "8010493d7241dcacb66d7545",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1340.0200821905667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.303710317116,
        1362.7364540640176
      ],
      "voteCount": 601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.33270410527706
      }
    },
    {
      "id": "2398aff0b0ef81dc369db6e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1330.3350645273972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.3989249739982,
        1349.2712040807965
      ],
      "voteCount": 889,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.34406482613646
      }
    },
    {
      "id": "2292bb8312693bbcba65bc62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1290.5026414283734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.856682473831,
        1321.148600382916
      ],
      "voteCount": 357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 244.4838911676264
      }
    },
    {
      "id": "cdfba2a1b25a9895cbb0e1e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1301.541463759092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.4351228857006,
        1323.6478046324833
      ],
      "voteCount": 646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.21477168464465
      }
    },
    {
      "id": "a71fd2b0fa2956101a972578",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1335.3274531159611,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.4514843172944,
        1371.2034219146278
      ],
      "voteCount": 252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 335.0511348213125
      }
    },
    {
      "id": "fcac16534bb63bcc905aa39e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1342.6120037750782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.6018924865973,
        1363.622115063559
      ],
      "voteCount": 707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.91071412151406
      }
    },
    {
      "id": "20966620ef039e0a21c87692",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1325.3429763862955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.256825598358,
        1351.4291271742331
      ],
      "voteCount": 431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.14292790676194
      }
    },
    {
      "id": "59a41e5afa52246a660d70cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1389.9385718492422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.5529704533737,
        1428.3241732451104
      ],
      "voteCount": 212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 383.5663645761139
      }
    },
    {
      "id": "d84212e096b55093b8bdc50b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1357.2650977325313,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.554282399735,
        1376.9759130653279
      ],
      "voteCount": 828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.13768211978336
      }
    },
    {
      "id": "eac60ea57c558e476ab97508",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1308.9754983174385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.200638544516,
        1327.7503580903606
      ],
      "voteCount": 890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.76080649205024
      }
    },
    {
      "id": "c041c272e88216497c9214c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1315.8006382330243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.1808726703362,
        1331.4204037957124
      ],
      "voteCount": 1300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.51156881313574
      }
    },
    {
      "id": "386dc5a826ae8a7bd7dd6262",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1376.3987850755348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.035661568137,
        1404.7619085829324
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.4169982409279
      }
    },
    {
      "id": "2feca1054341ea90d0dc6395",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1293.4098363219223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.462550641567,
        1317.3571220022777
      ],
      "voteCount": 497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.28508106535554
      }
    },
    {
      "id": "f57f4863ad3846b5817f6aa6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1312.0105021554355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.880147407698,
        1337.1408569031732
      ],
      "voteCount": 510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.39971355283893
      }
    },
    {
      "id": "08e99170f5fdf0c15253ce4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1326.0107339933415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.272231584326,
        1335.7492364023572
      ],
      "voteCount": 3738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.688128546244872
      }
    },
    {
      "id": "392f144c1f73077670a132de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1303.0040273433415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.3197708395935,
        1331.6882838470897
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 214.18596673233102
      }
    },
    {
      "id": "2c44f6be6431bff59420e9bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1317.5699578589051,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.1188479319437,
        1355.0210677858665
      ],
      "voteCount": 255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 365.117966957124
      }
    },
    {
      "id": "132cdd9ec34b10e0e6fc9913",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1356.007682388739,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.2370469478772,
        1374.7783178296013
      ],
      "voteCount": 964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.71951888581759
      }
    },
    {
      "id": "8cc82468ac68e44435848c97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1284.319782214086,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.7860462571562,
        1307.8535181710158
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.1735429017086
      }
    },
    {
      "id": "5b60371778f9e4d9acf9a943",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1314.1746265070276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.4303634165162,
        1325.918889597539
      ],
      "voteCount": 2753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.90503555475496
      }
    },
    {
      "id": "d4e536ab1368bd1dcd1b5f5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1233.5697364445627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.8644497669993,
        1246.2750231221262
      ],
      "voteCount": 4023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.02161655084601
      }
    },
    {
      "id": "de3acf991011d98892223e8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1299.7151354576754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.1007213071614,
        1333.3295496081894
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 294.1405573828611
      }
    },
    {
      "id": "c3b14e89a5722cd145fc9e05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1322.700715187499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8605888204042,
        1339.5408415545937
      ],
      "voteCount": 1204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.82347938548912
      }
    },
    {
      "id": "f9d2ae03b4f49e0c18ca6932",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1303.2091932078386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.1511265190038,
        1316.2672598966733
      ],
      "voteCount": 2172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.38759169602353
      }
    },
    {
      "id": "b5fe495406d7fc97762efb59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1281.016304962639,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.8561746276037,
        1302.1764352976743
      ],
      "voteCount": 798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.5575727074368
      }
    },
    {
      "id": "c5c13e8c8ba7cf8e3949dee6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1254.6905355617505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.6312139145266,
        1274.7498572089744
      ],
      "voteCount": 885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.74572388467784
      }
    },
    {
      "id": "2e414a630f62bb02a750c52e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1291.8218486557498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.5737849086413,
        1323.0699124028583
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.18507226557253
      }
    },
    {
      "id": "ee1ca83fb6610c43c5014162",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1306.5718169422275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.3888232325708,
        1326.7548106518843
      ],
      "voteCount": 930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.0412864221304
      }
    },
    {
      "id": "9870eb037dd713b59d4f704a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1312.421880600528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.1726657851466,
        1340.6710954159098
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 207.7383033202412
      }
    },
    {
      "id": "b42bad8ad324f0b99c722056",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1284.1515373443253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.5804016158595,
        1316.7226730727916
      ],
      "voteCount": 366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 276.16562669555435
      }
    },
    {
      "id": "1ccdfee76f9073ec4560acad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1327.6041220251714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.4886125195162,
        1341.719631530826
      ],
      "voteCount": 1820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.867693473863966
      }
    },
    {
      "id": "4803a4161d397767f0fb05dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1291.7554439930473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.8861630682409,
        1309.6247249178534
      ],
      "voteCount": 1085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.12238023989696
      }
    },
    {
      "id": "a24ebb3222116f2f9732301f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1286.3030848581527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.6826301501037,
        1302.9235395662017
      ],
      "voteCount": 1215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.91005490263001
      }
    },
    {
      "id": "00c4e02485f5aac753b07d0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1313.928839015272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.330473620318,
        1333.5272044102262
      ],
      "voteCount": 877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.98699558745525
      }
    },
    {
      "id": "def1e2b73c929f61a825ec39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1280.3430640065594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.5413902589894,
        1310.1447377541292
      ],
      "voteCount": 351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.19856273667264
      }
    },
    {
      "id": "7e9b810d7f6366d41a8f8f9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1280.8739358421378,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.3373185975647,
        1300.410553086711
      ],
      "voteCount": 964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.35793436202646
      }
    },
    {
      "id": "ee8c513ca8d202f33e9c01de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1294.0240085887726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.9247387632563,
        1303.1232784142894
      ],
      "voteCount": 5374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.553455398642985
      }
    },
    {
      "id": "73512adb5427d10e64d38fd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-large-vision",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1279.8018324848194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.2324047619475,
        1310.3712602076916
      ],
      "voteCount": 358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 243.26433131854986
      }
    },
    {
      "id": "c04b1b3ee098abbeb7387f8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1360.896267575289,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.6044409643837,
        1392.1880941861941
      ],
      "voteCount": 340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.89754240552602
      }
    },
    {
      "id": "5ac7022e671e8ceeb39a440f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1331.7997877741873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.1527058024947,
        1355.44686974588
      ],
      "voteCount": 549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.56565926558804
      }
    },
    {
      "id": "f060756e3472be5ac50787af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1276.6477004115143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.7403710330402,
        1300.5550297899883
      ],
      "voteCount": 590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.78732916042864
      }
    },
    {
      "id": "802f0b0519c5330bfa2cbbbf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1319.2124969583556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.8193017563685,
        1331.6056921603426
      ],
      "voteCount": 2312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.98254165504849
      }
    },
    {
      "id": "25f96b7447afebe1695e5dab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1252.9425464776705,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.640123028214,
        1268.2449699271272
      ],
      "voteCount": 2571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.95709321808243
      }
    },
    {
      "id": "5f058097c72ed12282f0bc1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1289.59106211271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.6435706825334,
        1328.5385535428863
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 394.8778730965488
      }
    },
    {
      "id": "182c509e1c4085581220f32d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1323.0325560909191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.531386819309,
        1346.533725362529
      ],
      "voteCount": 587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.77479569937586
      }
    },
    {
      "id": "e16fcec42191196046e92ffb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1310.470303253373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.6293008500566,
        1329.3113056566892
      ],
      "voteCount": 873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.40848024960144
      }
    },
    {
      "id": "7e2ff2767dafb4186bb9ce38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1300.6002859387156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.0522359403485,
        1329.1483359370827
      ],
      "voteCount": 376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.15668233090895
      }
    },
    {
      "id": "d9b79a2282580a5a0b645ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1258.5677793770983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.5559269194896,
        1280.579631834707
      ],
      "voteCount": 675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.12959587263965
      }
    },
    {
      "id": "eae3fe659ad90fd3f763d8e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1339.8099431984342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.1253738566743,
        1373.4945125401941
      ],
      "voteCount": 288,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 295.369614696225
      }
    },
    {
      "id": "372ce5cfe15923e275018f4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1332.9170964013688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.5137097273896,
        1354.320483075348
      ],
      "voteCount": 696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.25286264895941
      }
    },
    {
      "id": "7f1fcc1ace268c50113f313a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1308.5669791533328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.9794869837447,
        1334.1544713229214
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.43518779942073
      }
    },
    {
      "id": "0ca2c399f28c10339fd5e50e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1362.2246729759368,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.9268913255978,
        1399.522454626276
      ],
      "voteCount": 247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 362.1344340702843
      }
    },
    {
      "id": "5cca81b696b4757e77d49f9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1335.5089296367105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.3139968770317,
        1354.7038623963895
      ],
      "voteCount": 880,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.91289685672584
      }
    },
    {
      "id": "1ba7523319fa3d5227eb8fbd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1292.4276728549708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.198222781618,
        1310.6571229283236
      ],
      "voteCount": 937,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.5069405889966
      }
    },
    {
      "id": "e86ee7fcecfe2c652a7c6dd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1281.4463653888731,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.1059725951325,
        1296.7867581826138
      ],
      "voteCount": 1329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.2599697277839
      }
    },
    {
      "id": "64f9872fb7966ae6c53e8611",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1333.1893451088526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.631001272811,
        1359.7476889448944
      ],
      "voteCount": 432,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.61400192908135
      }
    },
    {
      "id": "6b1937487e4a066a1eb0f190",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1289.9832989029633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.9005018178746,
        1314.0660959880524
      ],
      "voteCount": 499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.97939155749455
      }
    },
    {
      "id": "147f454117822230e506278f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1300.2447811245802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.3584055048755,
        1324.131156744285
      ],
      "voteCount": 570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.52663190660616
      }
    },
    {
      "id": "0a2ad18f757282c956cdac26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1310.9981680006172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.3223398670261,
        1320.6739961342082
      ],
      "voteCount": 3904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.371379322471764
      }
    },
    {
      "id": "cd06bd0f21649b0677fc720c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-2025-02-10",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1294.6012333818107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.4101122229422,
        1321.7923545406793
      ],
      "voteCount": 379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.46778486686375
      }
    },
    {
      "id": "b44be9bb09af8c1e34abda8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1294.3942097534757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.9261493659899,
        1327.8622701409613
      ],
      "voteCount": 305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 291.5848167020041
      }
    },
    {
      "id": "e5b095c678284a0604861844",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1300.4127430423418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.8622933428333,
        1324.9631927418504
      ],
      "voteCount": 497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.89991968707034
      }
    },
    {
      "id": "a21a8d117fb18032179b71fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1194.5422441655126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.2114430944794,
        1223.8730452365457
      ],
      "voteCount": 357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.95030940695398
      }
    },
    {
      "id": "6d9cb8ad34557db14d8b1a82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1244.8889648707388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.5580875580563,
        1261.2198421834214
      ],
      "voteCount": 1278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.42611290408072
      }
    },
    {
      "id": "dfe13cf6f8c4cc14fbc1fa50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1124.5789460456976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.8496788191023,
        1143.3082132722927
      ],
      "voteCount": 1812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.31568688320114
      }
    },
    {
      "id": "4605d3a5662560150e08833b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1277.4206374932128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.2246610130815,
        1305.6166139733439
      ],
      "voteCount": 370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.95603591670334
      }
    },
    {
      "id": "386d56381a4d690b70847f9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1270.2677792332915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.753126764251,
        1290.782431702332
      ],
      "voteCount": 700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.55498563680207
      }
    },
    {
      "id": "cbba16035e036c132078c27d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1224.4124078537125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.0011423929236,
        1255.8236733145013
      ],
      "voteCount": 328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.84711040840057
      }
    },
    {
      "id": "db64456e8689a79ef7656c92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1185.6666021842889,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.5318264285293,
        1214.8013779400483
      ],
      "voteCount": 379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.96687689730632
      }
    },
    {
      "id": "9eca59af19ac4b240ce1f133",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1243.3674844662542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.20688287402,
        1268.528086058488
      ],
      "voteCount": 538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.7956940401979
      }
    },
    {
      "id": "b3ba444101b3e1ac769bb4cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1266.457703553261,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.1877681243682,
        1297.7276389821536
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.541023961942
      }
    },
    {
      "id": "c8802933529a0bfa495abc4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1277.3659617550713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.6239762920036,
        1298.1079472181393
      ],
      "voteCount": 737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.99650472170926
      }
    },
    {
      "id": "489cbc713989e68a716422c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1207.7610827763892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.9825092135945,
        1228.539656339184
      ],
      "voteCount": 752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.39196863926196
      }
    },
    {
      "id": "bf3f6c39b70bc49d2ce24650",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1242.9545616805244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1226.084014264379,
        1259.8251090966698
      ],
      "voteCount": 1098,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.09043892054098
      }
    },
    {
      "id": "d092de62abd516b73affed5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1270.210998823724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.5296777897079,
        1296.89231985774
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.31837131384208
      }
    },
    {
      "id": "1d8080261acf4a8181940429",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1249.9521264824693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.41498457116,
        1278.4892683937787
      ],
      "voteCount": 361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.99458499442306
      }
    },
    {
      "id": "f1b6a7e7038ea12045269711",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1207.8556852588838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.8483377200344,
        1232.8630327977332
      ],
      "voteCount": 532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.79425606749018
      }
    },
    {
      "id": "86603f9e9a1e19d25d729516",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1233.1850135777227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.4401604950244,
        1244.9298666604209
      ],
      "voteCount": 2728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.90864314126439
      }
    },
    {
      "id": "264220df19cb83c85d378e6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-standard-256k",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1192.9272442199356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.6917198412482,
        1219.162768598623
      ],
      "voteCount": 444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.17743533180143
      }
    },
    {
      "id": "59417fdb88a89e92e8005c71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1422.6925782861915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.7071262584477,
        1459.6780303139353
      ],
      "voteCount": 258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.09483936869555
      }
    },
    {
      "id": "06a5792ff4f0ba2378caf43a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1399.6885606147416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.6944771595086,
        1419.6826440699747
      ],
      "voteCount": 805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.06551049337786
      }
    },
    {
      "id": "9b807d087d8b837a7db9f199",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1377.8352524885681,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.1920035093171,
        1401.4785014678193
      ],
      "voteCount": 622,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.51847316011208
      }
    },
    {
      "id": "44cd2639d4f36c59b6cedfa2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1385.7491212790542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.0737676343545,
        1398.424474923754
      ],
      "voteCount": 2092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.82384805290532
      }
    },
    {
      "id": "91257aa40489fa88f87b060b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1361.9033795673874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.4854262327851,
        1374.3213329019898
      ],
      "voteCount": 3350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.14244905858324
      }
    },
    {
      "id": "d7bd4bd805959a164bb59607",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1402.4195945213376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.0841018391595,
        1440.7550872035156
      ],
      "voteCount": 215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 382.5656001486884
      }
    },
    {
      "id": "a677a8e82d64646f9e15093b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1398.7052145178723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.8205188569873,
        1417.5899101787572
      ],
      "voteCount": 931,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.83757729825321
      }
    },
    {
      "id": "b929c9f6cb48b31031153f0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1399.2602570752215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.1867858679502,
        1412.3337282824925
      ],
      "voteCount": 1977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.49238098990362
      }
    },
    {
      "id": "7e0f4e2ef45889ca68ee755b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1365.554572894338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.3292457626726,
        1386.7799000260036
      ],
      "voteCount": 770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.27693380943539
      }
    },
    {
      "id": "8621034f84dcfddc80b268da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1341.3706803184168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.6496952394677,
        1361.0916653973661
      ],
      "voteCount": 859,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.24207251396832
      }
    },
    {
      "id": "2e8706dfde92384e75d2a658",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1407.2891312108377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.008096234554,
        1441.5701661871215
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 305.9226751864141
      }
    },
    {
      "id": "923022a0703ada3e8b0d5a01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1419.3275407791755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.3961085362212,
        1441.2589730221298
      ],
      "voteCount": 723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.20965150952333
      }
    },
    {
      "id": "f6a40ccd10c671952f59f88b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1386.2955461648023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.3007459827413,
        1424.290346346863
      ],
      "voteCount": 225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 375.79599528646844
      }
    },
    {
      "id": "e07fbf1bc6bc305ab47845df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1441.0719386912356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.9699524941445,
        1479.1739248883264
      ],
      "voteCount": 258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 377.91928012936086
      }
    },
    {
      "id": "daa16444b0ae7e9715e1d008",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1409.1327927973598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.43483681928,
        1423.8307487754396
      ],
      "voteCount": 1558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.23642475869068
      }
    },
    {
      "id": "835ea146f74e10d5d55d0c3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1369.4178010271878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.1958489081453,
        1387.6397531462305
      ],
      "voteCount": 1022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.43579289200507
      }
    },
    {
      "id": "9c225613812d4f1e790958bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1376.3867349991472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.0197733896907,
        1393.7536966086036
      ],
      "voteCount": 1115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.51479597270104
      }
    },
    {
      "id": "63206b443afdf7c732a99f89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1379.8664425392026,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.9403715449544,
        1425.7925135334508
      ],
      "voteCount": 179,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 549.0632843976707
      }
    },
    {
      "id": "dc5f2f0735c234150fd9a300",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1389.773649705231,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.1123622084651,
        1409.4349372019972
      ],
      "voteCount": 889,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.63005854651833
      }
    },
    {
      "id": "743f2d452208ac6e986d45a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1401.5421752498353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.3435724917579,
        1439.7407780079127
      ],
      "voteCount": 236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 379.8383168417626
      }
    },
    {
      "id": "aea837367e7e729002df55ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1388.1944110066213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.3709557982534,
        1410.017866214989
      ],
      "voteCount": 687,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.97977421129198
      }
    },
    {
      "id": "58a7ec7a5ee213cb40852a05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1387.4642960435972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.8475283202229,
        1396.0810637669715
      ],
      "voteCount": 4711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.32825248538519
      }
    },
    {
      "id": "0b3d48141a323ebb49c0f1f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-t1-20250711",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1374.8174991931567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.843155004823,
        1408.79184338149
      ],
      "voteCount": 259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.47336621424
      }
    },
    {
      "id": "c9387695fb4724285d70af4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1399.3939454087913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.3592491565537,
        1438.428641661029
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 396.6481440061695
      }
    },
    {
      "id": "94c610e63691533d386eb706",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1371.8656485026222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.9014470696122,
        1401.8298499356324
      ],
      "voteCount": 299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.72718788008865
      }
    },
    {
      "id": "fc81c9e76c76751b3e97a709",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1302.2325261360888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.9698594350184,
        1327.4951928371593
      ],
      "voteCount": 451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.13540809323354
      }
    },
    {
      "id": "fab8c5260388acfe59aef8db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1358.8780263499048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.415381091445,
        1373.3406716083641
      ],
      "voteCount": 1319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.450175736688294
      }
    },
    {
      "id": "829e9a6639c352d2aa8cdee9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1288.586278064778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.1799625618892,
        1307.992593567667
      ],
      "voteCount": 1358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.0369955728473
      }
    },
    {
      "id": "72997cc61aafdbb20b6f7ce1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1369.4722737767008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.008823517206,
        1396.9357240361956
      ],
      "voteCount": 343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.34236246204281
      }
    },
    {
      "id": "fc1d9d406a0b01db53673b7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1348.593570490567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.255871677542,
        1371.9312693035918
      ],
      "voteCount": 496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.7816020709167
      }
    },
    {
      "id": "5c5e92d05df80caac857bfde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1348.7227712883428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.0669357375818,
        1382.3786068391032
      ],
      "voteCount": 256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 294.86591409436693
      }
    },
    {
      "id": "77d8dbd25a780fe3ee667a9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1301.276385816607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.9788747279092,
        1326.5738969053045
      ],
      "voteCount": 449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.59401991640934
      }
    },
    {
      "id": "d6c1be78e646e163d1330555",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1364.6840797356083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.506589393609,
        1391.8615700776077
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.27486633736677
      }
    },
    {
      "id": "761d585d20e196566523d0d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1312.0955253808024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.7818805120583,
        1346.4091702495462
      ],
      "voteCount": 216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 306.50497093329
      }
    },
    {
      "id": "56a2f959cf26932380d1a4ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1374.7478501178891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.3187061938615,
        1398.1769940419167
      ],
      "voteCount": 517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.89487682536486
      }
    },
    {
      "id": "793e98dff7355897e2b92057",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1322.4971292874097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.5189315630255,
        1342.4753270117942
      ],
      "voteCount": 711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.90021159786305
      }
    },
    {
      "id": "760b70769999ac5c73b60311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1313.4983632342032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.3841553231937,
        1331.612571145213
      ],
      "voteCount": 842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.41664600845456
      }
    },
    {
      "id": "af50bae92eb02b32c45949b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1342.6545959950604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.9871984428341,
        1372.321993547287
      ],
      "voteCount": 313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 229.11985227602165
      }
    },
    {
      "id": "cba4301b0b3408e9eb509ec5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1279.1692256834108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.4381130958043,
        1309.900338271017
      ],
      "voteCount": 243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.84443695832655
      }
    },
    {
      "id": "84854c24dd61e266b540f221",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1326.9716213930712,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.8408733306646,
        1356.1023694554779
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.90578665166302
      }
    },
    {
      "id": "95a2281630708543aa3a3307",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1340.5483359516577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.012272830936,
        1352.0843990723795
      ],
      "voteCount": 2290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.643284891761674
      }
    },
    {
      "id": "f6cce40b2669f78ec0f2a91c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbo-0110",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1332.6109380059756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.409630681515,
        1364.8122453304363
      ],
      "voteCount": 266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 269.9297953731526
      }
    },
    {
      "id": "9ef47d61b2693adc86e529d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1366.7602774850097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.2859426755406,
        1406.234612294479
      ],
      "voteCount": 203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 405.63316734149106
      }
    },
    {
      "id": "a7d8304d4e20bd735a71ed42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1399.6654099161055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.9664263797476,
        1430.3643934524637
      ],
      "voteCount": 275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.33065019171187
      }
    },
    {
      "id": "0d00cc19bd76c4f74eeb7a5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1302.8230432099144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.0092780805412,
        1328.6368083392879
      ],
      "voteCount": 424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.4628695132147
      }
    },
    {
      "id": "8d315b5573bcad850298e5eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1362.4289039969685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.5093996643777,
        1377.3484083295596
      ],
      "voteCount": 1310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.94455177576965
      }
    },
    {
      "id": "ba8d566bee826f0186349566",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1307.8124796106777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.701543147652,
        1326.9234160737033
      ],
      "voteCount": 1373,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.07531111001465
      }
    },
    {
      "id": "450e03e2346d59700656f849",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1382.5279650503167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.9971286706552,
        1410.0588014299783
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.3070614946065
      }
    },
    {
      "id": "26e39a05d3c6bacceff5da5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1367.6794960176546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.1230792500564,
        1390.2359127852528
      ],
      "voteCount": 531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.44758336408538
      }
    },
    {
      "id": "2ed90232463a6993041ee578",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1369.1083595644018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.0410228042012,
        1401.175696324602
      ],
      "voteCount": 263,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 267.68843163240984
      }
    },
    {
      "id": "15a073a63a6a12b0acc04d31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1286.5035424640182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.9186425687788,
        1312.0884423592577
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.400655897476
      }
    },
    {
      "id": "2c57b67e45cec579192544fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1359.6610619072303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.206360058514,
        1387.1157637559468
      ],
      "voteCount": 384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.21729368576368
      }
    },
    {
      "id": "9e812aaae76cbb073f6d525a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1302.887246738339,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.9794868203603,
        1334.7950066563174
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 265.0308621034216
      }
    },
    {
      "id": "81c5c1605e23aa3e4a0ed2b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1398.058293735718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.115469449618,
        1423.0011180218182
      ],
      "voteCount": 470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.95526554020097
      }
    },
    {
      "id": "50060ecdc9922c1338429319",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1332.2209740641874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.2203006458094,
        1353.2216474825655
      ],
      "voteCount": 662,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.80750012196582
      }
    },
    {
      "id": "e2a91ceee8b1d1049098a713",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1350.4917129856485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.626141219625,
        1368.357284751672
      ],
      "voteCount": 886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.0878760973578
      }
    },
    {
      "id": "816b5cf91d0b04a4c48082c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1354.8428816315304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.1420829508438,
        1386.543680312217
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 261.6039072395492
      }
    },
    {
      "id": "aec423ef20752a4802f9714f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1301.410513420259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.463839895081,
        1332.3571869454368
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 249.30544539870738
      }
    },
    {
      "id": "e3acbe0be7d664607af4d20f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1343.6459385148103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.9970109017527,
        1376.2948661278679
      ],
      "voteCount": 293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.48637276555877
      }
    },
    {
      "id": "a3d719e584edd061da2f9bb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1348.746429872176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.018457724641,
        1360.4744020197109
      ],
      "voteCount": 2220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.805493983793234
      }
    },
    {
      "id": "afdaca0512610a97ec2bc1ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250226",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1342.2103227487505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.2741915784054,
        1378.1464539190958
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 336.1758081423118
      }
    },
    {
      "id": "909e9073c9bab9015394961b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1434.395317158655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.6428189082922,
        1462.1478154090175
      ],
      "voteCount": 466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.49704945091958
      }
    },
    {
      "id": "71ac8ed8ec23ba3e07ee6b63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1394.2872730062868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.4088560232221,
        1408.1656899893514
      ],
      "voteCount": 1776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.139925207115695
      }
    },
    {
      "id": "fc4547ffa21c1f9c25c45b06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1362.2748240837452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.8151691473117,
        1377.734479020179
      ],
      "voteCount": 1494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.21618971055681
      }
    },
    {
      "id": "a79ea2ded3066bcd42ed0db4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1390.7885464211572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.5650214111322,
        1399.0120714311824
      ],
      "voteCount": 5671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.604344273118873
      }
    },
    {
      "id": "6ecb999b5c0bb0b07d1ef5dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1358.9854080435912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.9883790320043,
        1367.982437055178
      ],
      "voteCount": 7508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.07182058005489
      }
    },
    {
      "id": "454c4701b0fab357d896ffc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1350.8743371245073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.5817327342793,
        1375.1669415147353
      ],
      "voteCount": 581,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.62149006545695
      }
    },
    {
      "id": "8425facd3d167c184d2142bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1395.1157403910238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.5642176534825,
        1443.6672631285653
      ],
      "voteCount": 144,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 613.6341609170386
      }
    },
    {
      "id": "224e2c84b37621bb8d84c9e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1346.5103486694798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.8118041935138,
        1379.2088931454455
      ],
      "voteCount": 322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.3304105947743
      }
    },
    {
      "id": "ec4f1557924149871be5df08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1391.1973065960701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.6300768316478,
        1403.764536360492
      ],
      "voteCount": 2209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.113355973249845
      }
    },
    {
      "id": "a54aede8552c0e5483c26956",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1390.9977750462135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.4411197282507,
        1400.5544303641761
      ],
      "voteCount": 3914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.77473380017738
      }
    },
    {
      "id": "735dd6a2a192bfbc2a750e1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1404.4259222073574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.5854241400832,
        1420.2664202746319
      ],
      "voteCount": 1405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.3192942398851
      }
    },
    {
      "id": "4986149e2b04d7dd4730a1df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1335.6850107830237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.210041125803,
        1349.159980440244
      ],
      "voteCount": 1881,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.26714921031046
      }
    },
    {
      "id": "44d991db50dc6a78b5b39955",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1382.2631603964078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.9663977404466,
        1403.5599230523692
      ],
      "voteCount": 741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.06767189095935
      }
    },
    {
      "id": "e34003c9fefc98e54be28f24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1412.4404957318786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.9570214695307,
        1425.9239699942266
      ],
      "voteCount": 1955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.32683250540455
      }
    },
    {
      "id": "7e5de648e2c9d68633ba5c23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1356.9650015494808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.588299268556,
        1377.3417038304055
      ],
      "voteCount": 795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.08654087574332
      }
    },
    {
      "id": "ad2fef06cfe99d7decf39418",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1437.262622801499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.306953737105,
        1462.2182918658928
      ],
      "voteCount": 589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.12211233309836
      }
    },
    {
      "id": "ece149e9ac9b0ff2f741bf58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1412.8690092521533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.142914357854,
        1423.5951041464523
      ],
      "voteCount": 3085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.94932838059732
      }
    },
    {
      "id": "86d788ddccb76ef35cdcab5f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1355.5186323711532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.8519021493896,
        1367.185362592917
      ],
      "voteCount": 2541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.432527178000754
      }
    },
    {
      "id": "95759f00a4b6700da2da858d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1352.5667553894205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.7371073927184,
        1364.3964033861225
      ],
      "voteCount": 2427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.42901779189011
      }
    },
    {
      "id": "eb20b7c06ecd330eabf4c787",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1332.3225849676087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.2582222421581,
        1366.3869476930593
      ],
      "voteCount": 316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 302.06774614894687
      }
    },
    {
      "id": "f662d80e635446e1ad7119a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1359.7638291064632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.8993214273592,
        1411.6283367855672
      ],
      "voteCount": 129,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 700.2358432960592
      }
    },
    {
      "id": "a0f3b72a6631f798aba24e7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1374.860673133623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.034298239077,
        1389.687048028169
      ],
      "voteCount": 1530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.22341505509113
      }
    },
    {
      "id": "ed679200d6da33f9f56761cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1348.147698615855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.6241738207864,
        1367.6712234109236
      ],
      "voteCount": 845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.22480969216379
      }
    },
    {
      "id": "bf9adc0e584b0c9ee89787d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1390.281724916307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.2009069171193,
        1404.3625429154947
      ],
      "voteCount": 1720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.61305763793805
      }
    },
    {
      "id": "94d6925cffc8286cdecf2a09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1382.436150833045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.9791217263146,
        1388.8931799397756
      ],
      "voteCount": 10725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.85348739405012
      }
    },
    {
      "id": "32111dbf1631c2b04e05fbbd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-turbos-20250416",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1380.8113272363587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.8183076036507,
        1398.8043468690666
      ],
      "voteCount": 919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.27755459956137
      }
    },
    {
      "id": "0a07ac4cc332330bee261339",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1438.3816031761726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.3427465433451,
        1465.4204598089998
      ],
      "voteCount": 437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.31826244553827
      }
    },
    {
      "id": "1bda79f565d239dff5018d87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1375.9972056400723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.9858188295598,
        1412.0085924505847
      ],
      "voteCount": 261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 337.5852873992356
      }
    },
    {
      "id": "9d5753e58cf183b68729ddbe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1407.7791997914435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.548152027643,
        1425.010247555244
      ],
      "voteCount": 1104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.29069108821682
      }
    },
    {
      "id": "6dfbe57da442ba9c123d5040",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1374.0064559902798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.5213325722132,
        1391.4915794083465
      ],
      "voteCount": 1595,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.5868328193555
      }
    },
    {
      "id": "872ae370a8a653a477562f22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1425.97559729213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.7652063072442,
        1449.1859882770161
      ],
      "voteCount": 583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.23897556031346
      }
    },
    {
      "id": "0b18500c199da09daeba9200",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1421.34973250443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.2797569068796,
        1438.4197081019804
      ],
      "voteCount": 1093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.85245098327442
      }
    },
    {
      "id": "0b22c33940f7771cfc9395cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1414.3248032176307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.6556147289434,
        1440.993991706318
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.14987348389974
      }
    },
    {
      "id": "3012a9f134c95ee4e27de688",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1374.346995198525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.1069649172946,
        1403.5870254797555
      ],
      "voteCount": 375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 222.56632460602336
      }
    },
    {
      "id": "57f3345babca39a4b661651b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1400.8050562900487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.909359234344,
        1431.7007533457534
      ],
      "voteCount": 339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.48479213566006
      }
    },
    {
      "id": "c2d6936735645ac72fe0f7c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1428.5275586344148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.1053949782233,
        1448.9497222906066
      ],
      "voteCount": 783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.56937113409272
      }
    },
    {
      "id": "9430c05f58792171f0fd3573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1381.1970519747822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.9939043004413,
        1407.4001996491231
      ],
      "voteCount": 489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.7354700627124
      }
    },
    {
      "id": "1a444307a7dbf27e0cdb889c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1395.7825401975779,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.5867183405387,
        1417.978362054617
      ],
      "voteCount": 626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.24672368097802
      }
    },
    {
      "id": "f828017acaf007d5ce37cda5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1401.0520036242463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.4412718286358,
        1425.6627354198567
      ],
      "voteCount": 506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.67138157322103
      }
    },
    {
      "id": "bd2ce28cb44eeabb39e12b85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1412.8875894284552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3957725506648,
        1440.3794063062458
      ],
      "voteCount": 438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.748170557089
      }
    },
    {
      "id": "b0e0163fdae7d0b61eab56c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "hunyuan-vision-1.5-thinking",
      "organization": "tencent",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1395.8724221633659,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.61510993911,
        1408.1297343876215
      ],
      "voteCount": 2220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.11058532074539
      }
    },
    {
      "id": "1806383c9f12676c4f641e6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1308.0172952916134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.8135388945125,
        1348.2210516887142
      ],
      "voteCount": 219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 420.762555029905
      }
    },
    {
      "id": "996e4424ad1c2a42b4baa65d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1328.7974789175937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.6324427661389,
        1345.9625150690485
      ],
      "voteCount": 1264,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.69962892574046
      }
    },
    {
      "id": "cc44968ff5e2a4009b36faaa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1243.601429134159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.0777346600291,
        1267.125123608289
      ],
      "voteCount": 715,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.05053588787834
      }
    },
    {
      "id": "79ec95f9ca943aca56bc0f40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1306.434722480884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.8169945971254,
        1318.0524503646425
      ],
      "voteCount": 2807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.13550645238269
      }
    },
    {
      "id": "a8ebbe77df9aba134a6f5ef7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1221.4776302575342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.732887139986,
        1234.2223733750825
      ],
      "voteCount": 4220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.28301921584667
      }
    },
    {
      "id": "42a52f156fe7caf993ac8ad6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1306.2573127394098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.2318801216636,
        1343.282745357156
      ],
      "voteCount": 283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.86511935159973
      }
    },
    {
      "id": "44db0b1b5eda2a958f52a7f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1326.0881391048545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.824397804452,
        1341.351880405257
      ],
      "voteCount": 1594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.6493026114276
      }
    },
    {
      "id": "23d7465da5b11fdbb1fee37e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1301.1437728857445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.814343138095,
        1312.4732026333943
      ],
      "voteCount": 2985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.413342273896
      }
    },
    {
      "id": "46d181c6920e5d58fdb84ffd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1271.8472070742384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.468560919677,
        1291.2258532287997
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.75763435512769
      }
    },
    {
      "id": "19b0041eff0c6416a2c10620",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1258.1540689160474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.4195282511698,
        1277.8886095809253
      ],
      "voteCount": 978,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.38130159191495
      }
    },
    {
      "id": "8ba91f0078d34753a359beb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1289.6536055288934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.7268945901026,
        1324.580316467684
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 317.5551773275095
      }
    },
    {
      "id": "9d273c2d6f7eb0e4238fb29d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1315.3016412946827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.111349244231,
        1336.4919333451342
      ],
      "voteCount": 898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.89009257745813
      }
    },
    {
      "id": "4912fa2c02382d550ccaa80d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1307.8422347286944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.1453763962684,
        1343.5390930611206
      ],
      "voteCount": 279,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.714006132453
      }
    },
    {
      "id": "9fde8b2ab867c28e953f9b49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1298.9368983294448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.9229665959176,
        1339.9508300629723
      ],
      "voteCount": 254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 437.89161221269865
      }
    },
    {
      "id": "0b8f2e101644566d171d94cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1319.8097106884038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.4626879638297,
        1333.1567334129782
      ],
      "voteCount": 2157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.373792854588565
      }
    },
    {
      "id": "41f75453e73474b6c3102a36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1261.3468056243837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.399935246238,
        1279.293676002529
      ],
      "voteCount": 1202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.84579176922085
      }
    },
    {
      "id": "edf69a110aad4414249817c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1267.1920513799625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.6407470341046,
        1282.7433557258205
      ],
      "voteCount": 1569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.95604824778554
      }
    },
    {
      "id": "84e1546f083e0065881ba65a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1290.217137837003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.797271085566,
        1307.63700458844
      ],
      "voteCount": 1280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.99388534457604
      }
    },
    {
      "id": "f22285242d51b849b8c8e887",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1278.952358830792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.4339624596632,
        1310.4707552019208
      ],
      "voteCount": 358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 258.60209784263395
      }
    },
    {
      "id": "4d54b5382eac432ce74e357d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1283.0666947191444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.091132710536,
        1303.0422567277528
      ],
      "voteCount": 974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.87279837810642
      }
    },
    {
      "id": "33d688da981f8f47a6b2d919",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1287.104842737886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.7140667407152,
        1295.495618735057
      ],
      "voteCount": 5677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.327704427136528
      }
    },
    {
      "id": "6b887a909fee5bdfe3641c3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1236.3532037213827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.234727588489,
        1269.4716798542763
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 285.5252425084834
      }
    },
    {
      "id": "799d36c3dcf3d37ec495dafb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ibm-granite-h-small",
      "organization": "ibm",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1302.7056911687637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.5915192981863,
        1351.8198630393413
      ],
      "voteCount": 168,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 627.9390177340892
      }
    },
    {
      "id": "43575a5700b3de6f1fc5f526",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1381.9729709929043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.520077518442,
        1416.4258644673666
      ],
      "voteCount": 293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 308.9976813933848
      }
    },
    {
      "id": "3a28bb252e678da0f9aab768",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1409.2544734911303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.4693846844898,
        1428.0395622977708
      ],
      "voteCount": 973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.86082109546273
      }
    },
    {
      "id": "a5407fa440d941c36861fb5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1311.8087595996737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.2717550358461,
        1333.3457641635014
      ],
      "voteCount": 800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.74646305814636
      }
    },
    {
      "id": "7dfb16e5a3a34c259a64afd1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1384.796625178489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.3576041332487,
        1396.235646223729
      ],
      "voteCount": 2615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.06289344260193
      }
    },
    {
      "id": "e56f98c7eea1a786ad818ef8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1317.5708891230606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.6310859163418,
        1329.5106923297794
      ],
      "voteCount": 3801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.11061533373842
      }
    },
    {
      "id": "39e1ccb23d05b62d2377c676",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1354.0168646436803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.8264303175379,
        1388.2072989698227
      ],
      "voteCount": 309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.30777836609036
      }
    },
    {
      "id": "9010021a3df2f610b1c8c9b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1398.8874151124464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.485539393446,
        1414.2892908314466
      ],
      "voteCount": 1433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.752002751045154
      }
    },
    {
      "id": "71a2bc05c9218187ef340add",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1372.956421225052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.5439410052745,
        1384.3689014448296
      ],
      "voteCount": 2741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.90501131111475
      }
    },
    {
      "id": "5f3017a807df0dd1924c3883",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1363.063684958301,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.4415131214787,
        1381.6858567951238
      ],
      "voteCount": 985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.27437234313163
      }
    },
    {
      "id": "3b8926962b670a9242107103",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1304.5261449244877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.7718186048123,
        1323.280471244163
      ],
      "voteCount": 1064,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.5602046311444
      }
    },
    {
      "id": "7a8ec64a9c491d5162ac1102",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1328.1941589536177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.7093551632797,
        1357.6789627439557
      ],
      "voteCount": 398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.30820610948112
      }
    },
    {
      "id": "ed19c20546155dc53e4949ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1368.3243769862372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.3935381955139,
        1388.2552157769605
      ],
      "voteCount": 890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.40819814646048
      }
    },
    {
      "id": "b16ee1a097abde2e819aa568",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1385.1864543618117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.718201182759,
        1421.654707540864
      ],
      "voteCount": 233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 346.2053225110866
      }
    },
    {
      "id": "e92b2f8ad00e3be6f56ce59a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1332.7311139631774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.087928312537,
        1366.374299613818
      ],
      "voteCount": 315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 294.6442988340917
      }
    },
    {
      "id": "183f3392cd5c8bd42f2f2a21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1399.8462890840683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.6856673708603,
        1414.0069107972765
      ],
      "voteCount": 1711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.19975448502768
      }
    },
    {
      "id": "e123e5ffb4d0b52920919185",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1336.721750998042,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.9922742547433,
        1353.4512277413407
      ],
      "voteCount": 1268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.85653840589687
      }
    },
    {
      "id": "1042803e84823891f9165075",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1329.8053098872501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.838874282843,
        1345.771745491657
      ],
      "voteCount": 1393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.36204572501724
      }
    },
    {
      "id": "d8b832695d592c7a6da5939c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1351.5278482865224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.5186674611737,
        1368.537029111871
      ],
      "voteCount": 1262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.31311562963363
      }
    },
    {
      "id": "e06da3e3e32202d34962543f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1384.0393993715168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.1411904399274,
        1414.937608303106
      ],
      "voteCount": 332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.52519830152184
      }
    },
    {
      "id": "26e3ea8c11525b502aab2570",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1359.0211984176628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.5269687887142,
        1379.5154280466115
      ],
      "voteCount": 780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.33696485862242
      }
    },
    {
      "id": "c2e4482183bbafa50a5aec27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1356.47561138146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.1253224497418,
        1364.8259003131782
      ],
      "voteCount": 5329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.151261928814655
      }
    },
    {
      "id": "421ed39bc2db7acdfd8292d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "intellect-3",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1331.3742190249588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.7974371446885,
        1358.951000905229
      ],
      "voteCount": 449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.9661723237176
      }
    },
    {
      "id": "768df32fa01f23fa224812a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1245.9668013440075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.1953752902782,
        1264.7382273977369
      ],
      "voteCount": 959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.72724543926098
      }
    },
    {
      "id": "69b5adbb2ee80702ad77284b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1247.4308606290672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.1940259587927,
        1261.6676952993416
      ],
      "voteCount": 1684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.76314829586194
      }
    },
    {
      "id": "8504d7960012c3f288c3aa92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1131.3765022548018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.2584781995035,
        1147.4945263101001
      ],
      "voteCount": 1432,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.6281359695095
      }
    },
    {
      "id": "8579e705604437025e5c163e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1233.9695653589329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.6235897305428,
        1243.3155409873227
      ],
      "voteCount": 4966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.738044197146248
      }
    },
    {
      "id": "103dedb4967ea2c2b600a36e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1054.2969926611265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1041.9268955365822,
        1066.667089785671
      ],
      "voteCount": 6447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.83364393920818
      }
    },
    {
      "id": "8d094c602166c6249515caca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1216.7620450302222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.7874156646003,
        1238.7366743958441
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.70337423770587
      }
    },
    {
      "id": "b7022e4a7c222c6acf2c40c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1084.259680745982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1046.5243295233458,
        1121.9950319686182
      ],
      "voteCount": 265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 370.68124334036304
      }
    },
    {
      "id": "d4be47d25c9d144724e044e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1255.9780931799305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.414243333756,
        1270.5419430261052
      ],
      "voteCount": 1456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.214888989384576
      }
    },
    {
      "id": "a814ad949a4624e90de6d46b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1224.560777147643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.0876761435093,
        1236.0338781517767
      ],
      "voteCount": 2597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.26616105890388
      }
    },
    {
      "id": "840835ae91502191eed0776c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1167.0615947762913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.9198226008086,
        1184.2033669517737
      ],
      "voteCount": 1289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.49186598935158
      }
    },
    {
      "id": "620a16d78310b4531540ff19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1122.3050666464505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1106.3242741937074,
        1138.2858590991934
      ],
      "voteCount": 1427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.48144346670458
      }
    },
    {
      "id": "001f6c036bd83d3aae814dd3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1193.948005866675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.3784911275648,
        1217.5175206057854
      ],
      "voteCount": 685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.6122556473889
      }
    },
    {
      "id": "4bcdbbc3752f95094e63ac26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1209.3598651360253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.4005481932384,
        1224.3191820788124
      ],
      "voteCount": 1700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.25421378702157
      }
    },
    {
      "id": "ac9c205e045c12a388414f96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1212.99293152867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.7846376230023,
        1229.2012254343376
      ],
      "voteCount": 1086,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.38776714650223
      }
    },
    {
      "id": "9b9085c10ae1c30b9cb3bb7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1207.0437660612142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.2691245430856,
        1232.8184075793433
      ],
      "voteCount": 548,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.93746370760607
      }
    },
    {
      "id": "6432b48f3e485ba415febc63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1233.7023548968882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.8375805877909,
        1245.5671292059853
      ],
      "voteCount": 2727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.64567966926066
      }
    },
    {
      "id": "f2d209998e7d141d2354754f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1151.5865036290309,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.3122162126951,
        1163.8607910453663
      ],
      "voteCount": 2757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.21898909008508
      }
    },
    {
      "id": "1a2789a745fa7207823de7a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1176.9184872767103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.7709651818514,
        1187.0660093715694
      ],
      "voteCount": 4092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.805494858082543
      }
    },
    {
      "id": "941cff93f62b8bbb0c7c6aeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1199.0335053752328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.635614681004,
        1215.4313960694617
      ],
      "voteCount": 1266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.99705887027909
      }
    },
    {
      "id": "11ac87e764b2126cef2cded8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1206.623980127019,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.8655140265982,
        1221.3824462274397
      ],
      "voteCount": 1387,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.70041820151895
      }
    },
    {
      "id": "a75a1f5d5104e3a886dbcf38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1165.8370027119122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.1476475230113,
        1180.5263579008133
      ],
      "voteCount": 1751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.170628382970065
      }
    },
    {
      "id": "fa5026947b6fcdd72e9c2dc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1190.5971730304486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.4170780489362,
        1197.7772680119615
      ],
      "voteCount": 9901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.420360948767868
      }
    },
    {
      "id": "22c17c3c26125a1e6c4836d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "internlm2_5-20b-chat",
      "license": "Other",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1145.424806013059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.5232358938129,
        1161.3263761323046
      ],
      "voteCount": 1425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.82393409897432
      }
    },
    {
      "id": "ace51712a5334cadf01dcc5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1275.6497471737007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.770909200401,
        1297.5285851469998
      ],
      "voteCount": 675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.60983532693189
      }
    },
    {
      "id": "27308ef52055581e0a9944f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1311.8204126207947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.285127392436,
        1326.3556978491533
      ],
      "voteCount": 1440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.99851138104016
      }
    },
    {
      "id": "c16bfee872e070e096e2c52e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1260.7772856633187,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.6664105796567,
        1276.8881607469807
      ],
      "voteCount": 1379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.56815784750762
      }
    },
    {
      "id": "e85665a7d8eefa7727bc3de7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1315.2266907203548,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.0051337467985,
        1324.4482476939113
      ],
      "voteCount": 4915,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.136671766061607
      }
    },
    {
      "id": "765d4034ff130be779934066",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1213.3065096691419,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.926230974546,
        1224.6867883637378
      ],
      "voteCount": 5535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.71394806290687
      }
    },
    {
      "id": "c8f0757a57f298796bb5bfa0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1282.7228651434375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.798225465302,
        1311.6475048215727
      ],
      "voteCount": 331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 217.79090172800147
      }
    },
    {
      "id": "49be984382c08c9456cc1220",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1252.6833281018216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.3283514755713,
        1289.038304728072
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 344.0579184072581
      }
    },
    {
      "id": "99d1a263a7e58f28a2c979b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1294.7500693697236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.7972178069745,
        1308.7029209324728
      ],
      "voteCount": 1528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.67920178744393
      }
    },
    {
      "id": "531e7cccaa4231f236cc9ed9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1283.2835187781639,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.625286999812,
        1294.9417505565157
      ],
      "voteCount": 2372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.380925461335835
      }
    },
    {
      "id": "57f4172ca0307f713cfbf1ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1265.3883465788977,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.8611648472613,
        1283.9155283105338
      ],
      "voteCount": 979,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.35575752314018
      }
    },
    {
      "id": "e50b314ebf887d4129bb5fbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1269.936423668119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.6192954438147,
        1285.253551892423
      ],
      "voteCount": 1433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.07430223536295
      }
    },
    {
      "id": "3d6f4aec44338ba11ece4dd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1326.486571431757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.2637799779245,
        1353.7093628855898
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.916391696465
      }
    },
    {
      "id": "92b6eff102bdecbcef91d3bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1313.8109288837563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.9117243313938,
        1329.7101334361187
      ],
      "voteCount": 1358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.80435121056034
      }
    },
    {
      "id": "1860bc8fdf6627fddf46564b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1256.8424524510688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.0551062192117,
        1273.6297986829254
      ],
      "voteCount": 962,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.36145112114357
      }
    },
    {
      "id": "d96c6758008a9ad604e324f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1282.8670619489665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.27759321451,
        1310.456530683423
      ],
      "voteCount": 474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.14836513384859
      }
    },
    {
      "id": "3c84d073d667b5475aeb2abe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1309.846928691688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.7089460303018,
        1321.984911353074
      ],
      "voteCount": 2339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.35277949471567
      }
    },
    {
      "id": "2ad40ebdfb4014810bdc6999",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1275.8424938463654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.2051024436967,
        1288.479885249034
      ],
      "voteCount": 2350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.5737012730454
      }
    },
    {
      "id": "c8455ac07746113cc28d06d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1265.4995336556553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.8025625257997,
        1276.196504785511
      ],
      "voteCount": 3266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.78691083099758
      }
    },
    {
      "id": "0ff3f25c5cdc4c610c5e6d9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1177.2932340383127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.2325975765625,
        1214.3538705000628
      ],
      "voteCount": 242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 357.54405788523604
      }
    },
    {
      "id": "9ed1a56a469110d8c93fd8cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1260.0309133424948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.6236996822493,
        1277.4381270027402
      ],
      "voteCount": 1024,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.87917105374224
      }
    },
    {
      "id": "b49ddad6e3744055b09f0af1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1244.5462457022754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.1319423741734,
        1259.9605490303775
      ],
      "voteCount": 1147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.85169701957249
      }
    },
    {
      "id": "389f69e99070d4d53c406c9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1265.9707170827783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.4022497367696,
        1280.5391844287872
      ],
      "voteCount": 1634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.24990653768748
      }
    },
    {
      "id": "fbc4a0030515bb7787a3a22b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1288.7044486132609,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.4003402817443,
        1296.0085569447779
      ],
      "voteCount": 8662,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.887952730648752
      }
    },
    {
      "id": "835c28e8eeb7b55aeb5e6680",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-large",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1249.939256447226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.036355437806,
        1267.8421574566457
      ],
      "voteCount": 998,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.43545499602058
      }
    },
    {
      "id": "3818c87467c59fd9086128b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1216.311898519526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.5369869743672,
        1238.0868100646849
      ],
      "voteCount": 711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.42883131930064
      }
    },
    {
      "id": "a760494f1f3f86cabba5555b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1265.0152934683326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.6888840095544,
        1280.3417029271109
      ],
      "voteCount": 1352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.14833917591756
      }
    },
    {
      "id": "2b5a1c4d7f10496d2a362fd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1210.8590429920919,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.0543383082227,
        1226.6637476759608
      ],
      "voteCount": 1399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.0244351959956
      }
    },
    {
      "id": "f0e303019407194eda2cf193",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1271.624972948653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.5939763172141,
        1280.6559695800922
      ],
      "voteCount": 5087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.231231145236624
      }
    },
    {
      "id": "5b660ef81b9609e0664d06c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1129.695831248603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.7692362415255,
        1141.6224262556805
      ],
      "voteCount": 5612,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.02855480229822
      }
    },
    {
      "id": "f356e4534e9f16572ca93fc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1209.6525428215282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.717799227925,
        1240.587286415131
      ],
      "voteCount": 332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 249.11326812792637
      }
    },
    {
      "id": "9b2e563355bafcbd81412279",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1212.1294713012253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.4197857665972,
        1249.8391568358534
      ],
      "voteCount": 248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 370.17717734212084
      }
    },
    {
      "id": "0a417d78457f059d3e9096a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1247.5835770122544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.220002312282,
        1261.947151712227
      ],
      "voteCount": 1545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.70675251034123
      }
    },
    {
      "id": "01ac7c3048e74dc6cf2f2779",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1236.3429798874513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.4429564970433,
        1248.2430032778593
      ],
      "voteCount": 2350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.86374455698834
      }
    },
    {
      "id": "0bd41b79b6f81d6b477472d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1224.1459500310614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.6489365550121,
        1242.6429635071104
      ],
      "voteCount": 1005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.06499418658899
      }
    },
    {
      "id": "9fb38a4f5b8c29c3175b9478",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1209.8449304666435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.590711391827,
        1225.09914954146
      ],
      "voteCount": 1450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.57365455253066
      }
    },
    {
      "id": "cfae34e26f2400c8d336e1a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1286.8688168326112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.3916063125803,
        1312.346027352642
      ],
      "voteCount": 531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.96920836045447
      }
    },
    {
      "id": "85cf7dae490151d852c88d4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1254.3355515195003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.5369916622465,
        1270.1341113767544
      ],
      "voteCount": 1490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.97388237475225
      }
    },
    {
      "id": "e3e0ae7698e6bfe647adec08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1193.3053415087115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.1718871423454,
        1210.4387958750776
      ],
      "voteCount": 932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.41765074844731
      }
    },
    {
      "id": "e60380b439479cb135c58ac6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1264.9250729289274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.086366388682,
        1291.763779469173
      ],
      "voteCount": 486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.51109991679147
      }
    },
    {
      "id": "a57a2ee758b17afd9e9db299",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1264.0606389536408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.5677942015197,
        1276.5534837057617
      ],
      "voteCount": 2294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.628099189775405
      }
    },
    {
      "id": "0c4609b7ffbd1e52fcadb25e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1212.8263949914308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.2830125665346,
        1225.369777416327
      ],
      "voteCount": 2361,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.9574721482416
      }
    },
    {
      "id": "9959a36706df1fb8531bdd7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1203.3726868763715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.7462791664725,
        1213.9990945862705
      ],
      "voteCount": 3254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.39522355639817
      }
    },
    {
      "id": "13db59d2e07df9e8e6a63304",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1076.288374286666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.362336811132,
        1112.2144117622
      ],
      "voteCount": 270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 335.9869853974519
      }
    },
    {
      "id": "573b02e040b51443d3ba35bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1216.4164551333968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.8752202827827,
        1233.9576899840108
      ],
      "voteCount": 1023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.09845593732
      }
    },
    {
      "id": "eb12c7ba4b84486f9da16a92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1185.6795071732731,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.7111568978366,
        1201.6478574487094
      ],
      "voteCount": 1094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.37796275347108
      }
    },
    {
      "id": "bcbcca292a1048a0e797a3ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1204.9717157215387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.3039102375571,
        1219.6395212055204
      ],
      "voteCount": 1639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.005941429575444
      }
    },
    {
      "id": "b6d3c711043e90942de3e281",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1238.9581868477821,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.7343128757075,
        1246.1820608198568
      ],
      "voteCount": 8858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.584515050193733
      }
    },
    {
      "id": "70d2a0fb68549b15e1ccae90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "jamba-1.5-mini",
      "license": "Jamba Open",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1215.8579084828868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.7696383545124,
        1233.9461786112613
      ],
      "voteCount": 998,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.1722044954589
      }
    },
    {
      "id": "8221fa312315763ffe4b3f04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1452.5709065932563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.1911248687607,
        1467.950688317752
      ],
      "voteCount": 1578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.57496329750964
      }
    },
    {
      "id": "f21251c87e3270c685b6646e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1459.7955677285454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.369728568159,
        1468.2214068889318
      ],
      "voteCount": 5244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.48119916690231
      }
    },
    {
      "id": "649ca7062c7c40b3dccd04a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1370.3542340727918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.043170239267,
        1380.6652979063163
      ],
      "voteCount": 3444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.676474574263143
      }
    },
    {
      "id": "76d506e3a62eef0042c8f997",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1425.553617707949,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.4720501291629,
        1431.635185286735
      ],
      "voteCount": 13223,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.627973627127883
      }
    },
    {
      "id": "3aa3f0e813d5380e67e0f5ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1405.8535633881575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.4117158808888,
        1412.295410895426
      ],
      "voteCount": 19987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.802510515889026
      }
    },
    {
      "id": "fdb47ea62325756c623936e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1413.3674711545473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.5296727905259,
        1429.2052695185687
      ],
      "voteCount": 1460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.29703134343983
      }
    },
    {
      "id": "a5020084937efdad6fb7b043",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1424.931200637323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.3034388974575,
        1456.5589623771882
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 260.3998531195885
      }
    },
    {
      "id": "880128209b7f0f245bf6cd6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1421.0456004722785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.3995801915084,
        1444.6916207530487
      ],
      "voteCount": 621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.55258853915382
      }
    },
    {
      "id": "e5d247a678a327151f62031e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1433.3481620029304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.4743467728729,
        1441.2219772329881
      ],
      "voteCount": 6371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.138912108886128
      }
    },
    {
      "id": "0b06b13a44c4c767f9e9d447",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1431.2992763106204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.0104569254752,
        1437.5880956957656
      ],
      "voteCount": 12217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.2953724366181
      }
    },
    {
      "id": "bff87e123c2077eafe0d95e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1408.5699387530353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.4934549253715,
        1417.6464225806992
      ],
      "voteCount": 4603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.445644094906324
      }
    },
    {
      "id": "1c052e1ce9a7d7c8f566fa88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1381.03994000157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.3922658899382,
        1389.6876141132016
      ],
      "voteCount": 4860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.467153243483825
      }
    },
    {
      "id": "4b833ab0f7ef19cf1c25e724",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1423.0044084082908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.5747141948063,
        1437.4341026217753
      ],
      "voteCount": 1761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.20234468556463
      }
    },
    {
      "id": "937a15f5c4c3cb13180c958e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1430.8884269199111,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.6215774123327,
        1440.1552764274895
      ],
      "voteCount": 4388,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.354658426506163
      }
    },
    {
      "id": "a3c0c3bd3073c18990d2be08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1386.38497957178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.5311808805075,
        1401.2387782630522
      ],
      "voteCount": 1566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.43529889537585
      }
    },
    {
      "id": "5d20d0307247ad4ec5150990",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1445.9367422304663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.0993818527722,
        1460.7741026081603
      ],
      "voteCount": 1693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.30824492810372
      }
    },
    {
      "id": "407e15d62c230c131e0fa400",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1453.2650911832272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.4136028928808,
        1460.1165794735737
      ],
      "voteCount": 9218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.220068985217395
      }
    },
    {
      "id": "8f1bb881b3beed29b2fea983",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1372.1449742375871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.1508627975516,
        1380.1390856776227
      ],
      "voteCount": 6022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.63582006175414
      }
    },
    {
      "id": "f4536f0255af1f9d836f98b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1378.2565024775085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.5880909180048,
        1385.9249140370123
      ],
      "voteCount": 6752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.30786573297327
      }
    },
    {
      "id": "88a94696217bfe3e436e60ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1365.63587210479,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.4893335316187,
        1386.7824106779613
      ],
      "voteCount": 829,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.40788421775005
      }
    },
    {
      "id": "0cff5b663f11df43e4782f55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1342.3179871931698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.2104198952193,
        1367.42555449112
      ],
      "voteCount": 618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.10170329697806
      }
    },
    {
      "id": "4977e2323e473d549cc7056b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1392.7554729722422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.4561435274245,
        1401.05480241706
      ],
      "voteCount": 5501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.930393751083955
      }
    },
    {
      "id": "4d1a8f1e31b15e2b5bd43137",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1388.1454838219404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9886097660535,
        1402.3023578778273
      ],
      "voteCount": 1694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.17212845145849
      }
    },
    {
      "id": "3847b3dfb45ff3d7f60134de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1420.3889890860435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.4585040181657,
        1429.3194741539212
      ],
      "voteCount": 4709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.761269942021006
      }
    },
    {
      "id": "6265deb601f3be28dd75e2d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1417.3434661813894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.4886319737036,
        1422.1983003890755
      ],
      "voteCount": 27643,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.13553763928103
      }
    },
    {
      "id": "530cf6d6825ef98bbb8ad8e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1402.738393722074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.1000812582843,
        1417.376706185864
      ],
      "voteCount": 1489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.780942029941784
      }
    },
    {
      "id": "0e0349afbf5123ddb4aa115f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0711-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1379.1185463945444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.666987397321,
        1406.5701053917676
      ],
      "voteCount": 532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.17237267217902
      }
    },
    {
      "id": "0333a25d3586c820b5c05b75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1454.01553869965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.2563903793387,
        1475.7746870199617
      ],
      "voteCount": 737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.25019158731095
      }
    },
    {
      "id": "2d2cdab5e780e09a35433608",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1467.4237616893063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.8634308684843,
        1479.9840925101284
      ],
      "voteCount": 2243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.06822894433253
      }
    },
    {
      "id": "eab21a64f06f1479f39e84de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1382.1073919830826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.9486513930433,
        1397.266132573122
      ],
      "voteCount": 1506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.81774815292317
      }
    },
    {
      "id": "235e84d67c7be0919e651d25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1423.2816195572498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.888132743913,
        1431.6751063705863
      ],
      "voteCount": 5470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.33954863869317
      }
    },
    {
      "id": "a983538bd0e557ecf3ebe59f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1406.834781109725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.2506963872424,
        1415.4188658322078
      ],
      "voteCount": 8585,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.181908218254584
      }
    },
    {
      "id": "c2f12853c7f21affa15f5884",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1418.0988630908744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.5183788105633,
        1442.6793473711855
      ],
      "voteCount": 555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.28405162116056
      }
    },
    {
      "id": "8e0eb16f99ad0bf9d3be2c47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1420.431856107693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.205095320995,
        1462.6586168943907
      ],
      "voteCount": 184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 464.1724432737272
      }
    },
    {
      "id": "f84d4d62efe15ab7e3c1cb7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1420.6828811259988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.6118052618388,
        1456.753956990159
      ],
      "voteCount": 260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 338.70531345768586
      }
    },
    {
      "id": "ecfe2b178c18ef6687868809",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1438.7775724785236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.5572232414322,
        1449.997921715615
      ],
      "voteCount": 2842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.77302787266313
      }
    },
    {
      "id": "331921aee9d81ef99f1437ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1436.4378110407604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.0800346632118,
        1444.7955874183092
      ],
      "voteCount": 5584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.183827873101905
      }
    },
    {
      "id": "cbffe5370931be11cbdc95e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1404.8931756695656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.7933545251424,
        1417.9929968139888
      ],
      "voteCount": 2057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.671912943966184
      }
    },
    {
      "id": "dd3e84d525cd17f1db1f1c12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1379.7013676195768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.84792933084,
        1392.5548059083133
      ],
      "voteCount": 2108,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.007327047829
      }
    },
    {
      "id": "5b71128789f366fac5d246f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1452.506159803508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.5638964270331,
        1473.448423179983
      ],
      "voteCount": 781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.16975055596055
      }
    },
    {
      "id": "03c2f5b996bb8f0c0e3c02e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1439.032456464026,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.7274957180728,
        1453.3374172099789
      ],
      "voteCount": 1734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.26932071766478
      }
    },
    {
      "id": "2ab7967ec10df67c93789d58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1423.8286974754637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.9547250027142,
        1446.7026699482133
      ],
      "voteCount": 641,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.20310436897014
      }
    },
    {
      "id": "f3fc8f9e9ea92eff1b9712ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1444.8980150352695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.6102755258669,
        1467.1857545446721
      ],
      "voteCount": 724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.31111737108984
      }
    },
    {
      "id": "c23da4918fe5387f237c827d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1451.6004637714475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.9066675088218,
        1461.2942600340732
      ],
      "voteCount": 3966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.461979255140847
      }
    },
    {
      "id": "b2ef556a95a97555f6596863",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1381.1870608566358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.5835767425312,
        1392.7905449707403
      ],
      "voteCount": 2597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.049404372359184
      }
    },
    {
      "id": "aedd4a7f9eda7abca4e5af3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1389.7175069426105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.704302292581,
        1400.73071159264
      ],
      "voteCount": 2889,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.57411866815691
      }
    },
    {
      "id": "e803f81b46e3a3a53073401b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1374.8152182511694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.4984620176442,
        1418.1319744846946
      ],
      "voteCount": 182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 488.4450044047596
      }
    },
    {
      "id": "07443dcc439e98da70c99ccd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1354.1533663643668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.432700748775,
        1389.8740319799588
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 332.1566133020208
      }
    },
    {
      "id": "3e51730204382628d5d2e807",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1402.2367774388329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.5841316535489,
        1413.8894232241169
      ],
      "voteCount": 2544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.34702833877051
      }
    },
    {
      "id": "48d56dc03d64d5f7b0f9fa62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1416.194202934291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.54747083642,
        1436.840935032162
      ],
      "voteCount": 759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.970224130694
      }
    },
    {
      "id": "898a6b4a0809532cda6bb52e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1404.157248906706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.1722888992224,
        1417.1422089141897
      ],
      "voteCount": 2078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.891967678436416
      }
    },
    {
      "id": "694235939174faad186df43a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1418.0380982970155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.549965403636,
        1424.5262311903953
      ],
      "voteCount": 11795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.958302667565109
      }
    },
    {
      "id": "930afa3551fc93ced838d18d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1411.4687565404613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.7661472310106,
        1433.1713658499123
      ],
      "voteCount": 700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.61051668739668
      }
    },
    {
      "id": "f8d1f3d6ddfb1dc5456b51aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-0905-preview",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1419.2167173189005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3029958299614,
        1453.1304388078395
      ],
      "voteCount": 332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 299.4020133792564
      }
    },
    {
      "id": "aadf2b60a57ef47934146950",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1473.8186398291675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.272975787608,
        1485.3643038707269
      ],
      "voteCount": 3020,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.70097282898186
      }
    },
    {
      "id": "6abfa1d06e2de8842ed21474",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1487.3666106900769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.6696048110473,
        1493.0636165691062
      ],
      "voteCount": 14116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.44884131279913
      }
    },
    {
      "id": "2f87ab7539739bd07a08521f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1393.9055331298305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.0426482156574,
        1400.7684180440035
      ],
      "voteCount": 8987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.260756015776666
      }
    },
    {
      "id": "6aa3f8a2f7fde2d8d0f56747",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1445.0831734518729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.7507411035276,
        1449.415605800218
      ],
      "voteCount": 27534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.8861567776992185
      }
    },
    {
      "id": "82b90554961a44cfa6af64d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1423.222675432967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.7346451657636,
        1427.7107057001701
      ],
      "voteCount": 42695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.243428764828695
      }
    },
    {
      "id": "00ce116302387d9cf6ee489e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1460.3363589052633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.6429105719308,
        1470.029807238596
      ],
      "voteCount": 4121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.46022331016723
      }
    },
    {
      "id": "d680b1766387bb38ce00a868",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1448.8525977896093,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.8282612045818,
        1466.8769343746367
      ],
      "voteCount": 1425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.57118102639372
      }
    },
    {
      "id": "8eb62315f55c265a758f4573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1414.4195961025596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.3426378281317,
        1433.4965543769874
      ],
      "voteCount": 1068,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.73753435641376
      }
    },
    {
      "id": "981129fe1b1af916b8664581",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1460.150568981856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.800433548099,
        1465.5007044156127
      ],
      "voteCount": 16358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.451322660376726
      }
    },
    {
      "id": "a86fd99755e8488436ccd15d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1452.7908964720975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.7054415331477,
        1456.8763514110474
      ],
      "voteCount": 34295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.344948842943513
      }
    },
    {
      "id": "f8dc64114a783e0719b0fa49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1421.57127842851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.390349779255,
        1427.752207077765
      ],
      "voteCount": 11382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.945148640244492
      }
    },
    {
      "id": "33818fe92e3df49fdb85b95a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1395.1796732462424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.9559733373057,
        1401.4033731551792
      ],
      "voteCount": 11111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.083263250886619
      }
    },
    {
      "id": "040ef2fbb31657721061490c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1435.538411508864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.1707502600686,
        1444.9060727576596
      ],
      "voteCount": 4287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.84368552890746
      }
    },
    {
      "id": "52a241cc28fd43864089265a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1443.4691332931252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9010260310874,
        1450.0372405551627
      ],
      "voteCount": 9587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.230117259941743
      }
    },
    {
      "id": "1737085e5c7eac690150b38a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1450.8261976156632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.3787398203772,
        1462.2736554109492
      ],
      "voteCount": 2850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.113157550697245
      }
    },
    {
      "id": "f23959c9716ac37f33e33916",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1447.2918030488088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.9005216451217,
        1457.683084452496
      ],
      "voteCount": 3734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.10878217122244
      }
    },
    {
      "id": "22028df0e0469e90193d85a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1472.7469651877243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.9547092486682,
        1477.5392211267804
      ],
      "voteCount": 21861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.978384269460478
      }
    },
    {
      "id": "257361c5ffc0d48b42d02841",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1398.4556958587498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.7414861633263,
        1404.169905554173
      ],
      "voteCount": 13696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.49994597556819
      }
    },
    {
      "id": "7ae999bda9320fd2fedeeab8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1417.9334238128017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.7452986457076,
        1423.121548979896
      ],
      "voteCount": 17136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.006880460213426
      }
    },
    {
      "id": "91e6493e71b5ff0392ab7fc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1373.777873040963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.9466510524935,
        1402.6090950294322
      ],
      "voteCount": 468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 216.38637823487053
      }
    },
    {
      "id": "5e09e80d98bef334d4373789",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1342.9031368883784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.9956495391216,
        1363.8106242376355
      ],
      "voteCount": 940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.79089238300332
      }
    },
    {
      "id": "5d9c5badef0f0802336dd3c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1433.0575086839322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.7604110904208,
        1438.3546062774435
      ],
      "voteCount": 17498,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.3043195892212855
      }
    },
    {
      "id": "b9aae83061f1389846d1ba19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1440.0555294539643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.1759237865244,
        1449.9351351214038
      ],
      "voteCount": 3688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.40873472814425
      }
    },
    {
      "id": "6839b8e6d842c8b30912fe37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1431.9621296440848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.485713541613,
        1438.4385457465567
      ],
      "voteCount": 10355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.918759640582888
      }
    },
    {
      "id": "5839fbb18d8ff41381ba19e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1430.1501752582494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.9460574500022,
        1433.3542930664967
      ],
      "voteCount": 60235,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 2.6725188029665317
      }
    },
    {
      "id": "84e532faffa426c441a55fbd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1410.6956141755231,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.8133768765108,
        1418.5778514745352
      ],
      "voteCount": 6092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.17345590254504
      }
    },
    {
      "id": "2f772e4c9a58e08746b7d6f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2-thinking-turbo",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1421.446391866961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.0778633972075,
        1437.8149203367143
      ],
      "voteCount": 1624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.74660845556495
      }
    },
    {
      "id": "1ccd588551b2b0a32ce516d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1472.5256613596546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.9564672325116,
        1510.0948554867973
      ],
      "voteCount": 242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 367.42404728105424
      }
    },
    {
      "id": "38d56da4071a5fbece0deab0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1505.2401531651403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.363385765219,
        1519.1169205650615
      ],
      "voteCount": 1803,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.12800669218729
      }
    },
    {
      "id": "209a3ed34ef3cc118d54e582",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1390.7019737518192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.275222566117,
        1407.1287249375212
      ],
      "voteCount": 1273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.24366708380049
      }
    },
    {
      "id": "f7ddeda341f84ab9e9ae2bf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1445.2130451890923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.7038458302416,
        1454.7222445479429
      ],
      "voteCount": 3719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.53920129489416
      }
    },
    {
      "id": "4cc7ae4cce98c39d0ced2a63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1426.456893431212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.9070786055677,
        1436.0067082568562
      ],
      "voteCount": 5655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.740710875983694
      }
    },
    {
      "id": "d6f89f9745dd67842720b4b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1456.1230353595215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.8201957174722,
        1480.425875001571
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.75096863864022
      }
    },
    {
      "id": "654aa1b00f29be5846b6a999",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1421.5679695685492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.8894463500553,
        1469.2464927870433
      ],
      "voteCount": 153,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 591.765181511358
      }
    },
    {
      "id": "348b0e8c3550236935d58bb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1437.7515340562923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.9169718421842,
        1485.5860962704005
      ],
      "voteCount": 133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 595.6448966442205
      }
    },
    {
      "id": "17c8d430248e83140ae60228",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1464.9685311129012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.429100746832,
        1477.5079614789706
      ],
      "voteCount": 2150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.93166717249559
      }
    },
    {
      "id": "8e9f2c57eae62d21598ded30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1461.1632772595146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.5323751982805,
        1469.7941793207488
      ],
      "voteCount": 4541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.391713895075586
      }
    },
    {
      "id": "c62f41c7151d97c1716eec06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1425.6435896341818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.5142559935448,
        1440.7729232748188
      ],
      "voteCount": 1486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.58588835487007
      }
    },
    {
      "id": "d95fa24735e7c84e1de77884",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1401.5041388229704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.333263513513,
        1416.6750141324278
      ],
      "voteCount": 1431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.91355586457118
      }
    },
    {
      "id": "473a1376566ad12bab36a489",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1445.81509376354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.6418675461025,
        1470.9883199809774
      ],
      "voteCount": 517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.96111185171534
      }
    },
    {
      "id": "8a8e8557f703635bec6d88e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1453.8856098439862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.1291220609728,
        1470.6420976269997
      ],
      "voteCount": 1200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.09199341398713
      }
    },
    {
      "id": "739839725d4c44badd923f7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1444.5467623937152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.2585345295208,
        1475.8349902579098
      ],
      "voteCount": 333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.8389163012999
      }
    },
    {
      "id": "7953d62f41a2741f77afc696",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1435.5445349697159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.22711264516,
        1460.8619572942719
      ],
      "voteCount": 541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.8563696965785
      }
    },
    {
      "id": "fdeac6da7653838c9934f2a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1490.3637511059337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.4125367464403,
        1501.314965465427
      ],
      "voteCount": 2856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.219675010313576
      }
    },
    {
      "id": "a73a6dc9cf2fef8272a33bb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1404.7510208382869,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.2719580764192,
        1418.2300836001548
      ],
      "voteCount": 1848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.29586894427268
      }
    },
    {
      "id": "6098478be8f26613ac6acb6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1434.9971567338935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.7433844764494,
        1447.2509289913376
      ],
      "voteCount": 2233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.08799795755026
      }
    },
    {
      "id": "b94e7b5b392659db2d037685",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1380.8270109189211,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.8220975340523,
        1429.8319243037902
      ],
      "voteCount": 126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 625.1483220180854
      }
    },
    {
      "id": "16945952d4c19fefe15bda39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1445.7492810808815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.4719632743124,
        1458.0265988874505
      ],
      "voteCount": 2215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.23835697821159
      }
    },
    {
      "id": "d2ec81764b8ee5c965abbb2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1441.6837838558554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.821330358165,
        1466.546237353546
      ],
      "voteCount": 515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.9132422804759
      }
    },
    {
      "id": "74e5f6a38a2047c383dfc569",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1440.4810877460775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.2523695495393,
        1455.709805942616
      ],
      "voteCount": 1471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.3712987004427
      }
    },
    {
      "id": "e6afdce9a8fec499b89ee8cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1431.93581166436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.344980344931,
        1438.526642983789
      ],
      "voteCount": 8197,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.307958645075079
      }
    },
    {
      "id": "095eabab39922a0b2b94016e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1424.42211831617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.1666500657475,
        1443.6775865665925
      ],
      "voteCount": 865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.51881611893204
      }
    },
    {
      "id": "d486ef1777b1f99967be45ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-instant",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1442.02398197169,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.689217815844,
        1478.3587461275363
      ],
      "voteCount": 261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 343.6754493238087
      }
    },
    {
      "id": "899705b5536c607db7009f1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1507.4904123638105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.3936191266505,
        1522.5872056009707
      ],
      "voteCount": 1653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.32984750943716
      }
    },
    {
      "id": "e0276a55f29adf8fd9ca17d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1503.3807322901478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.698668100525,
        1510.0627964797707
      ],
      "voteCount": 9469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.623183774275459
      }
    },
    {
      "id": "439e78d6bbacbbe7b71cd523",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1420.303601401098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.9484338887391,
        1428.6587689134567
      ],
      "voteCount": 5572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.172477545122415
      }
    },
    {
      "id": "cb472e2352d77fa7f38955a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1459.207536780429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.9082063133,
        1464.506867247558
      ],
      "voteCount": 16436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.310478833863138
      }
    },
    {
      "id": "38741a5d56d7136fb422c609",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1449.7371189012233,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.2026584056373,
        1455.271579396809
      ],
      "voteCount": 26068,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.973599199396388
      }
    },
    {
      "id": "e6f6fc1924fffe416a701719",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1483.4594000705774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.9449644796587,
        1494.973835661496
      ],
      "voteCount": 2833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.513509884106604
      }
    },
    {
      "id": "3a4d60ad60dca43dcc5a1ad4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1469.357205006213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.2582850291917,
        1489.4561249832343
      ],
      "voteCount": 1045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.15968102183521
      }
    },
    {
      "id": "d5d96d91598e0b085eaabc69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1449.8105834152352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.5483969014138,
        1474.0727699290567
      ],
      "voteCount": 639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.23701799440138
      }
    },
    {
      "id": "90143f8a0c1102019c9d331a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1476.1938304346872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.7983052897412,
        1482.5893555796335
      ],
      "voteCount": 10370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.647710619542309
      }
    },
    {
      "id": "547a980a514ab536421a43bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1471.2784159155033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.3665167855343,
        1476.1903150454725
      ],
      "voteCount": 22044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.280622593952894
      }
    },
    {
      "id": "a376676b67a0d7f628ec5ef9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1438.0215643136612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.4776974350916,
        1445.565431192231
      ],
      "voteCount": 6962,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.814665505459487
      }
    },
    {
      "id": "50a9d31373d3049810b9a80f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1424.2679483382685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.6047746177333,
        1431.9311220588038
      ],
      "voteCount": 6714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.28696107706553
      }
    },
    {
      "id": "da04eba7f8fd975d7217d5ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1441.7523488350037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.1611872231751,
        1453.3435104468322
      ],
      "voteCount": 2714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.97500136868609
      }
    },
    {
      "id": "e676ec16413e3a0d90fd4616",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1472.1993429778329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.0631816225805,
        1480.335504333085
      ],
      "voteCount": 5704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.232287182695604
      }
    },
    {
      "id": "146421e64ff19caaf2460efb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1480.1034461991392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.2543753800146,
        1493.952517018264
      ],
      "voteCount": 1849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.928105833104844
      }
    },
    {
      "id": "b5bcb92f6b87f36d68dfa071",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1465.1573914878009,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.719344739174,
        1477.5954382364278
      ],
      "voteCount": 2474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.27246266122222
      }
    },
    {
      "id": "e295735a7be2051c95c94b62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1490.9515246611284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1485.2788211619206,
        1496.624228160336
      ],
      "voteCount": 13994,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.376912650103389
      }
    },
    {
      "id": "0c9115fa45a5f7dab188ef60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1424.04075140665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.0996932300063,
        1430.9818095832936
      ],
      "voteCount": 8298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.541664732161916
      }
    },
    {
      "id": "4edd13a31cb3ad41bdc40cea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1439.0294259937282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.8130129551785,
        1445.245839032278
      ],
      "voteCount": 10821,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.059665577481871
      }
    },
    {
      "id": "d754be7d1bc0eae76c86c9d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1436.783814991525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.9324115970524,
        1473.635218385998
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 353.5182844669375
      }
    },
    {
      "id": "766859aa84fc8a2ebf035f8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1405.9765935293897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.2389739338653,
        1430.714213124914
      ],
      "voteCount": 627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.30141433672756
      }
    },
    {
      "id": "ba2627de6c4edef4f499ba0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1455.8883038660656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.710435014171,
        1462.0661727179602
      ],
      "voteCount": 12008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.935304615425324
      }
    },
    {
      "id": "7fa0f1af06cd15d4423018b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1471.6537893025784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.3423334595004,
        1483.9652451456561
      ],
      "voteCount": 2259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.45687095733771
      }
    },
    {
      "id": "88e62490b60ebef602c05a4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1452.5070676710222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.6781062405996,
        1460.3360291014449
      ],
      "voteCount": 6436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.955562701559835
      }
    },
    {
      "id": "b445e815f8feb51789d1c926",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1449.4375609002298,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.43986948266,
        1453.4352523177995
      ],
      "voteCount": 36795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.160278013138614
      }
    },
    {
      "id": "eb5fc0be10e7e778739662ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1439.7129294965303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.2763269582038,
        1449.149532034857
      ],
      "voteCount": 4171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.1811589354126
      }
    },
    {
      "id": "b584dd345a8813cfb5e0f6f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.5-thinking",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1462.2378477050315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.8610357922698,
        1480.614659617793
      ],
      "voteCount": 1196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.91118995152846
      }
    },
    {
      "id": "65b82ed854291e7224cdd19f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1527.486174039457,
      "unit": "Arena rating",
      "confidenceInterval": [
        1505.60787972744,
        1549.364468351474
      ],
      "voteCount": 808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.60364261219517
      }
    },
    {
      "id": "004ee159b7a5952c80e96cdb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1513.8060930141569,
      "unit": "Arena rating",
      "confidenceInterval": [
        1504.2105661301584,
        1523.401619898155
      ],
      "voteCount": 4237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.96853395525889
      }
    },
    {
      "id": "538eee649dda745e350d8d16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1429.4581223729306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.6507881740313,
        1442.2654565718299
      ],
      "voteCount": 2279,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.69935379722688
      }
    },
    {
      "id": "3705cbd7f26953ed19503401",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1469.133024489261,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.7301046758366,
        1476.5359443026857
      ],
      "voteCount": 7117,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.266252567583505
      }
    },
    {
      "id": "9e834527bb4f8c3fb12b7588",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1467.272433571452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.8378531467952,
        1474.7070139961086
      ],
      "voteCount": 11515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.388540570298693
      }
    },
    {
      "id": "f39e33932fbafe45b0955203",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1500.8476708096848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1484.6579584266333,
        1517.0373831927363
      ],
      "voteCount": 1327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.23105473211103
      }
    },
    {
      "id": "40ee3b758658153d93505164",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1482.8167916870284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.2437660598266,
        1510.38981731423
      ],
      "voteCount": 543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.91224577046032
      }
    },
    {
      "id": "421d7e38756c53b55e411f84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1449.0568317835591,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.243147124138,
        1480.8705164429803
      ],
      "voteCount": 314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.47035822870225
      }
    },
    {
      "id": "13434638b4ed49bbaa07d8b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1492.87773224854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.8994436239477,
        1501.8560208731326
      ],
      "voteCount": 4761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.984128787802923
      }
    },
    {
      "id": "504f414b9e272697202afaf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1488.1451000384134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.5187491736085,
        1494.7714509032185
      ],
      "voteCount": 10015,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.430169587388333
      }
    },
    {
      "id": "537f65cc76be7cb20a755fd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1458.7444925830498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.7507864707302,
        1469.7381986953694
      ],
      "voteCount": 3059,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.46241564089315
      }
    },
    {
      "id": "b902ffd4de465fa3d48ddf60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1429.369765721729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.0020824772678,
        1440.7374489661902
      ],
      "voteCount": 2936,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.63936160144899
      }
    },
    {
      "id": "3f5330745c7a795e8f885e11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1456.7724794304916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.890501963372,
        1474.6544568976112
      ],
      "voteCount": 1124,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.24054299683934
      }
    },
    {
      "id": "ac464652c14a44b806f165a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1476.8121951148125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.0688281150603,
        1488.5555621145645
      ],
      "voteCount": 2634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.89955663404667
      }
    },
    {
      "id": "b5e9270896e203ff6f83bfeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1492.7996003944443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.4057334218337,
        1513.1934673670548
      ],
      "voteCount": 838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.2687149621412
      }
    },
    {
      "id": "1ed40dcaa5cab8ac351f4c48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1482.4403632853252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.4332922264655,
        1500.447434344185
      ],
      "voteCount": 1143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.4092370252801
      }
    },
    {
      "id": "83171268846c86cb36b4482b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1502.1663475918829,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.2174837753944,
        1510.1152114083716
      ],
      "voteCount": 6248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.448031574021414
      }
    },
    {
      "id": "c6c8b290b1195b1ee6f9c2bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1437.0906489888869,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.8981011724084,
        1447.2831968053654
      ],
      "voteCount": 3577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.043900726347083
      }
    },
    {
      "id": "69f603e647cc1fa6daaf72b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1456.1330903206701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.4317859200216,
        1464.8343947213186
      ],
      "voteCount": 5015,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.70936089822878
      }
    },
    {
      "id": "d117a0e1411bd04d214178e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1454.7631324758459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.2065594093294,
        1506.3197055423623
      ],
      "voteCount": 139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 691.9455213326352
      }
    },
    {
      "id": "620634c6f84ce7ca7aa68e1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1429.6633229068862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.359726273731,
        1462.9669195400413
      ],
      "voteCount": 312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 288.72613256426536
      }
    },
    {
      "id": "2b80d840c8435141c1fa4421",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1475.4315701024107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.1656099641477,
        1483.6975302406736
      ],
      "voteCount": 6089,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.78649731692479
      }
    },
    {
      "id": "2102c6bb9fcc92ee1b5fab92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1477.5980509647836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.3071955246578,
        1496.8889064049097
      ],
      "voteCount": 887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.87390155196252
      }
    },
    {
      "id": "b7a3c5f2e579ab1f109c19b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1457.2305511759387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.4108300712242,
        1469.0502722806532
      ],
      "voteCount": 2707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.367904359831144
      }
    },
    {
      "id": "87f56913197124ff656ba841",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1462.3946676814292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.8274113718962,
        1467.9619239909623
      ],
      "voteCount": 15765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.068378254913801
      }
    },
    {
      "id": "19711b45980dbd279eba994e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1453.4316076309153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.1778454863766,
        1467.685369775454
      ],
      "voteCount": 1765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.88869274833897
      }
    },
    {
      "id": "dfbd2089d62879cf4b946a70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "kimi-k2.6",
      "organization": "moonshot",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1447.833212984684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.0921767906173,
        1472.5742491787507
      ],
      "voteCount": 569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.34542071845334
      }
    },
    {
      "id": "bb6b5ee22f23c77735d6dbc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 998.4292186197309,
      "unit": "Arena rating",
      "confidenceInterval": [
        965.0311238171195,
        1031.8273134223423
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 290.3669643509736
      }
    },
    {
      "id": "6434b066fffe117e15ab5156",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1064.3726917628592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.255524203505,
        1088.489859322213
      ],
      "voteCount": 747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.41064846319557
      }
    },
    {
      "id": "baa8aa824ce5c1ee1c076584",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1044.7338277259162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1024.060701041234,
        1065.4069544105982
      ],
      "voteCount": 1200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.2541320548873
      }
    },
    {
      "id": "c0d5ac0bf722be7a248079c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1098.2065068307165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.0650049360277,
        1109.3480087254056
      ],
      "voteCount": 5711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.31404272789427
      }
    },
    {
      "id": "9c247185aacfe79ee858e0fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 895.1002789221295,
      "unit": "Arena rating",
      "confidenceInterval": [
        879.7382080637818,
        910.4623497804773
      ],
      "voteCount": 4743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.43322942461068
      }
    },
    {
      "id": "15c6b78ef42b15727f23456d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1042.9727555604884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1023.1591063911148,
        1062.7864047298617
      ],
      "voteCount": 1100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.19573129149836
      }
    },
    {
      "id": "58df1264b82847cde4fd63f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1032.5735734026396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1014.2293039538805,
        1050.9178428513985
      ],
      "voteCount": 1250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.60011165442319
      }
    },
    {
      "id": "af4a1d075ac3bc47cbeb4aa1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1050.3244287838193,
      "unit": "Arena rating",
      "confidenceInterval": [
        1021.0343029305375,
        1079.614554637101
      ],
      "voteCount": 503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.3296027747262
      }
    },
    {
      "id": "0c6a82c64c6ea6cca5b1b0b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1028.9655637369888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1008.5696810890065,
        1049.361446384971
      ],
      "voteCount": 1134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.2901180013421
      }
    },
    {
      "id": "2c972b5b13e750916f1c4072",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1081.7603003969652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1041.4160303582053,
        1122.1045704357252
      ],
      "voteCount": 248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 423.70885669582157
      }
    },
    {
      "id": "7253822e88e2adc046da6154",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1103.3693123397372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1082.6744971009484,
        1124.064127578526
      ],
      "voteCount": 1211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.48769198317723
      }
    },
    {
      "id": "1d9c1e7983b2d69a854232d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 985.573205712255,
      "unit": "Arena rating",
      "confidenceInterval": [
        962.6321687603352,
        1008.5142426641747
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.0029462750436
      }
    },
    {
      "id": "c2c7200a7d226102db0e630c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1090.629922344668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1048.4893673581769,
        1132.7704773311593
      ],
      "voteCount": 253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 462.27916462439214
      }
    },
    {
      "id": "8cb0f7a46261ffd548d204f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1072.6156408180752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1054.5337523238559,
        1090.6975293122946
      ],
      "voteCount": 1572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.11211671880086
      }
    },
    {
      "id": "a63422f8b76fd81f803c0a26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1047.0864245529265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1029.2358535942112,
        1064.9369955116417
      ],
      "voteCount": 1515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.9484053910933
      }
    },
    {
      "id": "449e5d215d221505af7d131a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1023.6009980658021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1008.2227362295661,
        1038.9792599020382
      ],
      "voteCount": 1913,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.562793756852194
      }
    },
    {
      "id": "629c13365e6d8b2043226225",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 979.4653348145864,
      "unit": "Arena rating",
      "confidenceInterval": [
        958.0849299161682,
        1000.8457397130046
      ],
      "voteCount": 751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.9969058519561
      }
    },
    {
      "id": "850cf5a601be881e4014101f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 996.5636109453096,
      "unit": "Arena rating",
      "confidenceInterval": [
        972.4298289579056,
        1020.6973929327137
      ],
      "voteCount": 792,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.61933531030405
      }
    },
    {
      "id": "561eefbc3995b03460d80cad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "koala-13b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1069.547021626397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1059.6463182713705,
        1079.447724981424
      ],
      "voteCount": 6965,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.51737022304592
      }
    },
    {
      "id": "d6d850542fe3b61caebfc338",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1386.699322415478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.6690926449692,
        1419.729552185987
      ],
      "voteCount": 300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 284.0056680590622
      }
    },
    {
      "id": "ff4e4d2cf77c1c87a82c7d27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1412.491980709276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.72794368938,
        1427.256017729172
      ],
      "voteCount": 1528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.74323201139308
      }
    },
    {
      "id": "724d26f7bc8a72f884c51b34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1270.413450330279,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.958117048728,
        1290.8687836118302
      ],
      "voteCount": 842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.92233372521956
      }
    },
    {
      "id": "305d2061c14c5c08cff1228e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1371.848088468966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.915563649484,
        1381.7806132884477
      ],
      "voteCount": 3394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.68166259082726
      }
    },
    {
      "id": "b6d839f3236a5e97e630c384",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1301.9317343338575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.6305532006113,
        1312.2329154671038
      ],
      "voteCount": 4953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.623446636549822
      }
    },
    {
      "id": "93dbc22f72462315c7229c29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1361.2609111079253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.1659645523596,
        1391.355857663491
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 235.77131773566464
      }
    },
    {
      "id": "3f391b33d49100250ff8dfa5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1389.2559767995563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.7452729069423,
        1402.7666806921704
      ],
      "voteCount": 1836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.518176868264014
      }
    },
    {
      "id": "c2ae8efe1006a25d9e905c7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1366.516360437598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.569674815025,
        1376.463046060171
      ],
      "voteCount": 3450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.754943497330576
      }
    },
    {
      "id": "7cd505797e306b79eed29279",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1347.4076282268243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.3431544673408,
        1363.4721019863077
      ],
      "voteCount": 1336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.179508935228
      }
    },
    {
      "id": "d951cc8784a8782252ea0ab1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1275.4976305152327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.4420757085395,
        1292.5531853219259
      ],
      "voteCount": 1170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.72434414683056
      }
    },
    {
      "id": "8f28d337311fe977c54c5c72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1349.035282826427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.71877657252,
        1376.351789080334
      ],
      "voteCount": 437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.24691211056813
      }
    },
    {
      "id": "9b01aff30f01d83cb747991b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1365.6644881885745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.3569435750876,
        1383.9720328020617
      ],
      "voteCount": 1022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.24971564689514
      }
    },
    {
      "id": "c7761ac8417b98dda3bc96bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1357.6799251649156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.6981149495577,
        1386.6617353802735
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.6526948653464
      }
    },
    {
      "id": "6ea2afcf0a76766e2e3f6837",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1343.5488576056614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.5889912660964,
        1374.5087239452264
      ],
      "voteCount": 352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 249.51805251697064
      }
    },
    {
      "id": "384759f79c25ec71892b46e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1406.162315279329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.5818906310337,
        1417.7427399276241
      ],
      "voteCount": 2546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.910236265557685
      }
    },
    {
      "id": "a35236bcb51eebd594b32240",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1278.4514206959743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.8827783039476,
        1294.0200630880013
      ],
      "voteCount": 1452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.09650506341121
      }
    },
    {
      "id": "c5838b80603cea4de72db5ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1317.5552985408099,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.7976835645172,
        1331.3129135171025
      ],
      "voteCount": 1796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.270857419139006
      }
    },
    {
      "id": "7d0caec0409e05ff2169c7ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1289.680363118344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.1243209923398,
        1330.2364052443481
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 428.1687321664489
      }
    },
    {
      "id": "9b034a6399e3e2396b1cd1c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1326.7513125253095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.4934692503996,
        1343.0091558002196
      ],
      "voteCount": 1254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.806534259236
      }
    },
    {
      "id": "476990fca7f87a7d0a86b5f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1355.354641911898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.6862313848508,
        1382.0230524389451
      ],
      "voteCount": 461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.1390717005298
      }
    },
    {
      "id": "40c0d2fa51ec681b926ac7e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1316.842176119234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.5850652211836,
        1334.0992870172843
      ],
      "voteCount": 1164,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.52468279584336
      }
    },
    {
      "id": "d197724a501a1b0449cdb76a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1346.428318101895,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.1703439429261,
        1353.6862922608639
      ],
      "voteCount": 7010,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.713068745779976
      }
    },
    {
      "id": "4399889729222c0a70c44d7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1292.0563451189194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.2268138335687,
        1321.8858764042698
      ],
      "voteCount": 375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.6309970343321
      }
    },
    {
      "id": "4d99c9763e385b459f1bbff6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ling-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1382.5636230086786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.9320053105187,
        1421.1952407068386
      ],
      "voteCount": 241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 388.4987333294175
      }
    },
    {
      "id": "cfa405077e2c4b1a924919f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 881.3585639029511,
      "unit": "Arena rating",
      "confidenceInterval": [
        842.2351417182995,
        920.4819860876026
      ],
      "voteCount": 304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 398.4533571446457
      }
    },
    {
      "id": "dfbb14d89041209e9c7e187b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 932.1282161932322,
      "unit": "Arena rating",
      "confidenceInterval": [
        898.3893811908313,
        965.867051195633
      ],
      "voteCount": 431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 296.32205900193566
      }
    },
    {
      "id": "ad6e35b06feab90d1939ebaa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 982.0981284607369,
      "unit": "Arena rating",
      "confidenceInterval": [
        964.9077757116895,
        999.2884812097843
      ],
      "voteCount": 1953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.9260433158271
      }
    },
    {
      "id": "2176b865c25bdd70420166ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 724.4362540733008,
      "unit": "Arena rating",
      "confidenceInterval": [
        698.6323933850483,
        750.2401147615534
      ],
      "voteCount": 1647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.32978368317725
      }
    },
    {
      "id": "2db48103895dba1ae33ac0d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 917.3186593312655,
      "unit": "Arena rating",
      "confidenceInterval": [
        883.3022693094644,
        951.3350493530666
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 301.21754367946255
      }
    },
    {
      "id": "3a05d110a73d88abfa50b57b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 915.5514205037109,
      "unit": "Arena rating",
      "confidenceInterval": [
        885.0731177550904,
        946.0297232523315
      ],
      "voteCount": 430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 241.8161906181052
      }
    },
    {
      "id": "ebf85749e75516e6eedcc5e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 936.4074113932965,
      "unit": "Arena rating",
      "confidenceInterval": [
        904.5060329679616,
        968.3087898186313
      ],
      "voteCount": 402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.9248613453914
      }
    },
    {
      "id": "931248382dbe79455a06b2da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 994.1775357504678,
      "unit": "Arena rating",
      "confidenceInterval": [
        961.6265775337765,
        1026.728493967159
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 275.8235686705398
      }
    },
    {
      "id": "8ba8c2b3184f3b5f92b0b09b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 930.8418787227338,
      "unit": "Arena rating",
      "confidenceInterval": [
        893.5062145205169,
        968.1775429249508
      ],
      "voteCount": 228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 362.870431907644
      }
    },
    {
      "id": "ff61b33461423bf48ee653c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 901.596485067352,
      "unit": "Arena rating",
      "confidenceInterval": [
        872.4621835584768,
        930.7307865762273
      ],
      "voteCount": 566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.95968329466058
      }
    },
    {
      "id": "918d119ad557173719009eca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 924.6872759395949,
      "unit": "Arena rating",
      "confidenceInterval": [
        896.0082371927144,
        953.3663146864753
      ],
      "voteCount": 513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 214.10805161161431
      }
    },
    {
      "id": "f5440da9ec9f656fac4fdbae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 913.052199299554,
      "unit": "Arena rating",
      "confidenceInterval": [
        887.6818536783314,
        938.4225449207765
      ],
      "voteCount": 584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.55468872213098
      }
    },
    {
      "id": "9f358b38233fe69e4cc46800",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 918.1748919595415,
      "unit": "Arena rating",
      "confidenceInterval": [
        885.1102031186824,
        951.2395808004006
      ],
      "voteCount": 252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 284.59855986307
      }
    },
    {
      "id": "e6399bd556186e5a144c6da9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 890.5080609032088,
      "unit": "Arena rating",
      "confidenceInterval": [
        847.0330361584274,
        933.9830856479903
      ],
      "voteCount": 247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 492.0208349956567
      }
    },
    {
      "id": "cbae9bfd36acffe057a24396",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-13b",
      "organization": "meta",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 972.0604009174656,
      "unit": "Arena rating",
      "confidenceInterval": [
        956.2413823244684,
        987.8794195104626
      ],
      "voteCount": 2391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.14227040454679
      }
    },
    {
      "id": "baf51ae0b462ecc7e85659ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1091.3770832054502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.2204450932386,
        1110.5337213176617
      ],
      "voteCount": 1161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.5305785878316
      }
    },
    {
      "id": "13aa477a18c9c23aa45d0a31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1160.8981084844131,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.9168552907163,
        1173.8793616781102
      ],
      "voteCount": 2626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.86691159386663
      }
    },
    {
      "id": "94eafe5c7b292ac8255e69b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1091.424973877157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.8034210892442,
        1104.04652666507
      ],
      "voteCount": 3296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.46955680479909
      }
    },
    {
      "id": "bce682d0f223c19e0c3f0d39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1172.0055974155914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.2688816045775,
        1179.7423132266053
      ],
      "voteCount": 13860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.58178138418219
      }
    },
    {
      "id": "f0aa43ce12b49410ebc7965e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 988.4057349697076,
      "unit": "Arena rating",
      "confidenceInterval": [
        978.3194595128597,
        998.4920104265555
      ],
      "voteCount": 12677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.482895519632255
      }
    },
    {
      "id": "b6ddc349f2df13936504b821",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1124.8093198539832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.4672480695733,
        1150.1513916383933
      ],
      "voteCount": 539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.18143609050654
      }
    },
    {
      "id": "23d536ee5a2a18e4ab296d7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1111.0940048256875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.8085233636364,
        1151.3794862877387
      ],
      "voteCount": 262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 422.4749222577944
      }
    },
    {
      "id": "b8e829ff3021363233b3b1f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1070.4641090639677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.6828862886696,
        1100.2453318392659
      ],
      "voteCount": 454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.88135820018374
      }
    },
    {
      "id": "aafdeebe8f5953dbd1e0a667",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1156.1155210605425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.1854309752835,
        1168.0456111458013
      ],
      "voteCount": 3347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.05026035309011
      }
    },
    {
      "id": "346af953918204a746fe4f6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1137.0803771347153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.7125967170389,
        1147.4481575523916
      ],
      "voteCount": 4475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.98178395407888
      }
    },
    {
      "id": "469207a12e005a8f13063c9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1134.953681125014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.8791277161586,
        1151.0282345338694
      ],
      "voteCount": 1709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.26383890988912
      }
    },
    {
      "id": "93b288a9af811971403ad774",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1102.005501951713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.4734917222158,
        1114.5375121812103
      ],
      "voteCount": 3085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.883239342872265
      }
    },
    {
      "id": "6b800627c937ebd1800cb311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1156.128761602748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.0821282751563,
        1177.1753949303397
      ],
      "voteCount": 1004,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.31056171677498
      }
    },
    {
      "id": "27825041fae4b3a2f38ef374",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1158.8820255061455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.998957869659,
        1171.7650931426317
      ],
      "voteCount": 3270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.20583389627199
      }
    },
    {
      "id": "36be1769a612ec7b5d9963c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1120.220424774322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1106.1919797904875,
        1134.2488697581568
      ],
      "voteCount": 1977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.22982644101766
      }
    },
    {
      "id": "e02bd11d27fe31c8944245c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1166.1081731766667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.1237002986736,
        1187.0926460546598
      ],
      "voteCount": 970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.63043664428966
      }
    },
    {
      "id": "87f39a7c2474eb8708537f63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1155.9992723189664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.6253170067407,
        1166.373227631192
      ],
      "voteCount": 4910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.01512494167795
      }
    },
    {
      "id": "4faa87884253c77c7882441b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1103.3799603630532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.6251474801586,
        1114.1347732459476
      ],
      "voteCount": 4785,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.109915411035015
      }
    },
    {
      "id": "037f0bafe6e40f7a96d142f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1108.1283507483884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.6859892073821,
        1117.5707122893948
      ],
      "voteCount": 6097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.209461726044463
      }
    },
    {
      "id": "cfde8146fb4d429141282edd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 961.3241294088286,
      "unit": "Arena rating",
      "confidenceInterval": [
        911.8395653846212,
        1010.8086934330358
      ],
      "voteCount": 175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 637.4458743315145
      }
    },
    {
      "id": "4fa9c2c0ad38ea816b20530a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1045.594069789323,
      "unit": "Arena rating",
      "confidenceInterval": [
        995.1838390335076,
        1096.0043005451384
      ],
      "voteCount": 172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 661.5172733767265
      }
    },
    {
      "id": "5e285a96bf1ce16e3a92202e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1137.783643660063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.0960973074925,
        1155.4711900126335
      ],
      "voteCount": 1193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.44023158311427
      }
    },
    {
      "id": "a9498da95b5c0291232523cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1109.598200998715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.1765260347709,
        1123.019875962659
      ],
      "voteCount": 2218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.89399711050725
      }
    },
    {
      "id": "9c83b217fd2048053935e288",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1099.207797059391,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.2721935535478,
        1113.143400565234
      ],
      "voteCount": 2596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.55398330079623
      }
    },
    {
      "id": "f7d2e10c41f6673858a83538",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1140.6356380430934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.9103635398344,
        1147.3609125463527
      ],
      "voteCount": 19174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.773995051185858
      }
    },
    {
      "id": "f136c01bfb9f475522160e32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1113.5532047969514,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.5881841069622,
        1134.5182254869408
      ],
      "voteCount": 783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.41801488640218
      }
    },
    {
      "id": "492f03bee7d265dc41bbcab8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-13b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1139.8591843033446,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.977352259732,
        1179.7410163469576
      ],
      "voteCount": 262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 414.05117206684974
      }
    },
    {
      "id": "14cbf22b03cdf08f9b3261e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1080.9110700950362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1067.3828960816982,
        1094.4392441083742
      ],
      "voteCount": 3619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.64114381475707
      }
    },
    {
      "id": "515a48b2bea5fb4ab09c8d8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1177.3773609446903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.4480508013612,
        1187.3066710880194
      ],
      "voteCount": 5717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.66504146583625
      }
    },
    {
      "id": "bdb472bc0d3d1d688f8a1786",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1111.6760506611463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.5169712405964,
        1121.8351300816958
      ],
      "voteCount": 6376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.866588837828065
      }
    },
    {
      "id": "b81cb693904151055607137f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1206.811183482897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.3637418985954,
        1213.2586250671986
      ],
      "voteCount": 26045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.821280384172153
      }
    },
    {
      "id": "8d0fd3c1548f004215c3bd94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1031.855099931006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1023.6493751661469,
        1040.060824695865
      ],
      "voteCount": 25547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.52821572728853
      }
    },
    {
      "id": "84de137b2002283941ecd42d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1132.853447867145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.5269687796283,
        1150.1799269546618
      ],
      "voteCount": 1356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.1491853961648
      }
    },
    {
      "id": "d445f7023bfb8d3b64101f68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1154.9532533523939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.941781657446,
        1182.9647250473422
      ],
      "voteCount": 679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 204.2563992330129
      }
    },
    {
      "id": "77fde0c7a84ef03b6c9b5318",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1100.1390985308146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1077.9051814064683,
        1122.3730156551608
      ],
      "voteCount": 878,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.68732785295606
      }
    },
    {
      "id": "26c7a513f2a4257930bda9eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1174.6204869067285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.3963449473245,
        1183.8446288661326
      ],
      "voteCount": 6989,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.149084204387243
      }
    },
    {
      "id": "06ac3e876d5c17a45ec1400f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1158.5991711205568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.3940771391883,
        1166.8042651019252
      ],
      "voteCount": 9650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.525521002701595
      }
    },
    {
      "id": "e8230b98f7adedb83875166b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1161.3457732077277,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.2745311770498,
        1173.4170152384054
      ],
      "voteCount": 3543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.932173938252774
      }
    },
    {
      "id": "62e02db134017e6a79dff6d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1111.6666654194796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.669196088083,
        1121.6641347508762
      ],
      "voteCount": 6070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.018603269617802
      }
    },
    {
      "id": "110b7716de1de997bfc6819f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1190.8692441593455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.2677820108574,
        1206.4707063078336
      ],
      "voteCount": 2073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.362808904644794
      }
    },
    {
      "id": "ad0fe292b750f8119d874815",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1195.1687345569328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.1496862216047,
        1205.1877828922607
      ],
      "voteCount": 6638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.131044020276672
      }
    },
    {
      "id": "1896f5e05b7207f35f5868ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1140.6015683044293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.70877948963,
        1151.4943571192287
      ],
      "voteCount": 4052,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.887445031202287
      }
    },
    {
      "id": "5e75799f8105bcbe17d449d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1180.8417859902693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.3525201888556,
        1196.3310517916832
      ],
      "voteCount": 2169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.454751245646165
      }
    },
    {
      "id": "c964b82d295d08bd80f28370",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1182.6377540656422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.2767709418447,
        1190.9987371894395
      ],
      "voteCount": 10184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.19778424275646
      }
    },
    {
      "id": "a9e7d68c8dd698f1a8e590ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1129.8032458919524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.140611403252,
        1138.465880380653
      ],
      "voteCount": 9591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.53456740980107
      }
    },
    {
      "id": "eea05ae10aba8aa51e8b4a85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1132.740644278103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.0506919361053,
        1140.4305966201005
      ],
      "voteCount": 12635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.393986967562778
      }
    },
    {
      "id": "e4516b68fb634d8ea50935ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 989.2942131043208,
      "unit": "Arena rating",
      "confidenceInterval": [
        955.9144247304109,
        1022.6740014782306
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 290.0487351015452
      }
    },
    {
      "id": "5c8eec5d9de257df4a1337c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1057.915210592134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1018.2023907815546,
        1097.6280304027134
      ],
      "voteCount": 243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 410.54925509329723
      }
    },
    {
      "id": "cfc6b6a8f8f750101b608d2b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1135.8015169667192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.8792766706363,
        1148.723757262802
      ],
      "voteCount": 2813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.46897938099874
      }
    },
    {
      "id": "951f60e6ffe0c7cba8cf1dd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1136.1102558469645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.8508710883518,
        1146.3696406055774
      ],
      "voteCount": 4740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.39974070742108
      }
    },
    {
      "id": "4df72a08799e213a42fc40bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1132.9588061838008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.4107918208401,
        1143.506820546762
      ],
      "voteCount": 5533,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.96311328442795
      }
    },
    {
      "id": "4576919e20b7b4ae38c24e7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1169.8937711527349,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.3928553486098,
        1175.39468695686
      ],
      "voteCount": 38492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.877235211024621
      }
    },
    {
      "id": "6d844b749f4cb43c160eca44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1134.9912494720038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.5224731232665,
        1149.460025820741
      ],
      "voteCount": 1981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.496351204398316
      }
    },
    {
      "id": "5807c5ed782da590af68ffdf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-70b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1189.6653037888502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.2100178927185,
        1219.1205896849822
      ],
      "voteCount": 506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 225.85530854814562
      }
    },
    {
      "id": "ee881eb246de0ecba7f36756",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1060.68375430418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.6386436283974,
        1080.7288649799625
      ],
      "voteCount": 956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.59736281430912
      }
    },
    {
      "id": "547a5a203722eff9e3e788a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1101.3822673587829,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.3013769442377,
        1115.4631577733282
      ],
      "voteCount": 1956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.61358851442978
      }
    },
    {
      "id": "8c018f5743df6bfb80ed8b69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1072.261809411129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1058.645907461567,
        1085.877711360691
      ],
      "voteCount": 2341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.26103690123295
      }
    },
    {
      "id": "93a331d819424221f5ad3ea5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1146.1458208892461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.1763018842785,
        1154.1153398942138
      ],
      "voteCount": 10259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.533623327781566
      }
    },
    {
      "id": "ea3faef90787e8b0fb4e4534",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 936.9035741284738,
      "unit": "Arena rating",
      "confidenceInterval": [
        926.3398862134228,
        947.4672620435248
      ],
      "voteCount": 9245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.04925122858143
      }
    },
    {
      "id": "dcf2cee1114df943132ba08e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1129.2737302746025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.207459501586,
        1157.340001047619
      ],
      "voteCount": 411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.05635798067485
      }
    },
    {
      "id": "a530388b18e8855ceffdb50d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1037.8113143309477,
      "unit": "Arena rating",
      "confidenceInterval": [
        995.1832183656063,
        1080.4394102962888
      ],
      "voteCount": 257,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 473.0376272267307
      }
    },
    {
      "id": "52c8d0fb5104e4e0b1150e46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1038.9892645075959,
      "unit": "Arena rating",
      "confidenceInterval": [
        1004.2110304113892,
        1073.7674986038026
      ],
      "voteCount": 327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 314.8610002884267
      }
    },
    {
      "id": "e2cf12a9fc9c403a2f78fe1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1114.9883475146453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.5255805594406,
        1127.45111446985
      ],
      "voteCount": 2560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.43270211384765
      }
    },
    {
      "id": "a5fb32d96ed20c7fb5ff8311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1095.3184031875242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.408453257744,
        1106.2283531173043
      ],
      "voteCount": 3289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.984845348102027
      }
    },
    {
      "id": "f3498adb5279b169076c347e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1105.28660026879,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.2584988253461,
        1123.3147017122337
      ],
      "voteCount": 1255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.6065145627081
      }
    },
    {
      "id": "3870b15e8af1a5fcf4b8b0e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1067.6782186905068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1054.0259298109988,
        1081.3305075700146
      ],
      "voteCount": 2220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.519325690924774
      }
    },
    {
      "id": "fbdd31fc85f4b504340784fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1137.6428575193945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.9534891293774,
        1160.3322259094111
      ],
      "voteCount": 760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.01352506100096
      }
    },
    {
      "id": "17bcf5d8864d836b767cfba4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1122.07286749839,
      "unit": "Arena rating",
      "confidenceInterval": [
        1108.6458869528085,
        1135.4998480439713
      ],
      "voteCount": 2474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.93107878710696
      }
    },
    {
      "id": "aab5ef8d4dab45201cb02248",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1089.6829686338378,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.3976785579425,
        1104.9682587097334
      ],
      "voteCount": 1401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.820668295501896
      }
    },
    {
      "id": "a311f825ca14cce484b5d0dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1126.413826416664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.3772952816926,
        1149.4503575516353
      ],
      "voteCount": 764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.14589495888882
      }
    },
    {
      "id": "ddaa379e8d5507e1ac36693b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1111.2663779938812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.234347386738,
        1122.2984086010247
      ],
      "voteCount": 3721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.682156440494868
      }
    },
    {
      "id": "1a20a799ed13aac25f0fdddf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1074.912304568128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1063.4289771855233,
        1086.395631950733
      ],
      "voteCount": 3454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.327273551837116
      }
    },
    {
      "id": "7eafd82cdbe39293504c0a9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1067.6063160280385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1057.702897920544,
        1077.509734135533
      ],
      "voteCount": 4541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.531365762272547
      }
    },
    {
      "id": "7ffcc068eb9c2ae889bf1d10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1073.9392539252058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.7267447190725,
        1094.151763131339
      ],
      "voteCount": 835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.3516615633535
      }
    },
    {
      "id": "3570caf31cdf18c8f03a150f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1085.667419811404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1071.7503331169016,
        1099.5845065059066
      ],
      "voteCount": 1656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.41972622976053
      }
    },
    {
      "id": "d799652f9037292c95cebea8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1076.0344731689186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1060.9094750147992,
        1091.159471323038
      ],
      "voteCount": 1851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.55174318926529
      }
    },
    {
      "id": "ff7f528e99f995121d3a4db3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1107.2328408024769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.1792528466306,
        1114.2864287583234
      ],
      "voteCount": 14148,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.95161691772889
      }
    },
    {
      "id": "b22cf3d99ce2104f171c65da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1054.7294269597144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1031.3975499493658,
        1078.061303970063
      ],
      "voteCount": 580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.71087345605565
      }
    },
    {
      "id": "3fafc4343413769e29f55e50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-2-7b-chat",
      "organization": "meta",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1059.308458858061,
      "unit": "Arena rating",
      "confidenceInterval": [
        1008.1789294539713,
        1110.4379882621506
      ],
      "voteCount": 143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 680.5302097736127
      }
    },
    {
      "id": "6a62784e83ee495cc32340d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1200.7143805846486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.678621177669,
        1209.750139991628
      ],
      "voteCount": 15885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.253630943795322
      }
    },
    {
      "id": "bc77d598fd2e700a721de9c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1305.157932309052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.1682984376675,
        1312.1475661804366
      ],
      "voteCount": 28126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.717819957569462
      }
    },
    {
      "id": "023ff1d053a857c97b3a3a10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1253.7399899428867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.1602061402714,
        1261.319773745502
      ],
      "voteCount": 22753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.956068820753021
      }
    },
    {
      "id": "1113dbbe380468c4c1b328a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1325.3642077456695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.7383977888758,
        1329.9900177024633
      ],
      "voteCount": 90553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.570310331351138
      }
    },
    {
      "id": "3fc2af4bd98373ffb26ef0a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1193.2805280044772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.6783730579186,
        1198.8826829510353
      ],
      "voteCount": 103844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.169849401008834
      }
    },
    {
      "id": "74199c5634c130381a9ad4d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1240.0745371359992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.225990108399,
        1250.9230841635995
      ],
      "voteCount": 7958,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.63705173046459
      }
    },
    {
      "id": "4ea76bdf89d10673b055884a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1292.6715970901114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.302611562422,
        1312.0405826178003
      ],
      "voteCount": 2499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.66019053772925
      }
    },
    {
      "id": "b6cc529f9d9dfee101973c6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1226.8776327609885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.61763262,
        1240.1376329019772
      ],
      "voteCount": 4991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.7710499958572
      }
    },
    {
      "id": "238f5cbf826de83c92b5c817",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1309.611812030772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.8838300145444,
        1316.3397940469995
      ],
      "voteCount": 29608,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.783477091263517
      }
    },
    {
      "id": "61305bc5b8ea0a5d5c56585d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1278.4580942390999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.8254832126745,
        1284.0907052655252
      ],
      "voteCount": 45956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.258921533688483
      }
    },
    {
      "id": "8c6c0ca6983c4ff2c193793c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1250.075627346619,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.9810923145678,
        1258.1701623786703
      ],
      "voteCount": 16626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.05641019295493
      }
    },
    {
      "id": "ad1bdadb494b7c256a727fa8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1249.5434007254294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.31986221163,
        1256.7669392392288
      ],
      "voteCount": 23202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.583253419052943
      }
    },
    {
      "id": "64f30b7d8ee15cbf53858e01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1301.7434777443473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.1192964626034,
        1312.3676590260916
      ],
      "voteCount": 8328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.382907165191376
      }
    },
    {
      "id": "fef54f9ba8551bc91a5f1e37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1294.9544696388812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.6858414196558,
        1302.223097858106
      ],
      "voteCount": 25903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.753357423669712
      }
    },
    {
      "id": "f082f81f03a4e7898af4467b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1259.6209506180041,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.0471541704055,
        1267.1947470656028
      ],
      "voteCount": 18728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.932450224545962
      }
    },
    {
      "id": "eb751bf93e01fdfe52a54241",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1298.5788648784082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.5326147001092,
        1309.625115056707
      ],
      "voteCount": 8252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.76388156089095
      }
    },
    {
      "id": "018d2dffc3604d0edfe61fc7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1289.5526939108386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.612654531201,
        1295.4927332904758
      ],
      "voteCount": 45062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.185069911869476
      }
    },
    {
      "id": "be668d814ae5b9b02f68f0b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1248.5933616340742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.275738035145,
        1254.9109852330037
      ],
      "voteCount": 37706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.389898681911944
      }
    },
    {
      "id": "f08eb0c91cdb7208459dcf86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1256.4472520791355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.1227695991197,
        1261.7717345591516
      ],
      "voteCount": 56558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.3800384185490895
      }
    },
    {
      "id": "49d3b652b0f61322c812fc83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1082.2590460688182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1067.0547667572857,
        1097.4633253803506
      ],
      "voteCount": 3276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.177687741378165
      }
    },
    {
      "id": "73f980ec93b7202a4c7fa6fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1110.324405366037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1093.610165546957,
        1127.0386451851168
      ],
      "voteCount": 5410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.72388583856704
      }
    },
    {
      "id": "0f6e15f89239fa93a4794d6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1250.9631692041467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.2660844815266,
        1258.660253926767
      ],
      "voteCount": 17500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.422555855092734
      }
    },
    {
      "id": "47df5128849a9393970ab877",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1257.170401136853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.7839681857486,
        1264.5568340879572
      ],
      "voteCount": 20941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.202779279384053
      }
    },
    {
      "id": "6a0c04dd3be0e974fb20e342",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1272.427928272641,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.0696480217339,
        1279.7862085235486
      ],
      "voteCount": 21421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.094720463802897
      }
    },
    {
      "id": "c6cd3f9eb1753a793fbebd5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1275.632678481017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.049717865119,
        1279.215639096915
      ],
      "voteCount": 156876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.3418571887118405
      }
    },
    {
      "id": "cda60954fa961c15324241cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1219.751257234876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.3926493432527,
        1228.1098651264992
      ],
      "voteCount": 14995,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.18744626638542
      }
    },
    {
      "id": "a08e479ba2dc3155bf601298",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-70b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1286.7330676783763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.2547138224281,
        1306.2114215343245
      ],
      "voteCount": 2705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.76619447113517
      }
    },
    {
      "id": "a8d0d46bb43a97d167970f40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1165.4489753230987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.7464730563504,
        1175.1514775898472
      ],
      "voteCount": 10757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.50593762169978
      }
    },
    {
      "id": "a03d0a1766e6883237da3787",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1251.9542092239342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.3483196046675,
        1259.5600988432009
      ],
      "voteCount": 18374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.059267741939907
      }
    },
    {
      "id": "44b8ac65ae876bc3d4389160",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1195.9669049272443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.7815575045875,
        1204.1522523499011
      ],
      "voteCount": 15365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.44126790287615
      }
    },
    {
      "id": "80dc825f31fce9272c7cd5c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1264.5754684574156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.7197457094217,
        1269.4311912054095
      ],
      "voteCount": 61703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.137783718615057
      }
    },
    {
      "id": "897e37bc30948f11d650c1b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1110.3623002422598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.3003400143339,
        1116.4242604701858
      ],
      "voteCount": 67687,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.565991338237737
      }
    },
    {
      "id": "5194a9d17deae6604fe6d1e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1205.8785630371472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.1022162256531,
        1217.6549098486414
      ],
      "voteCount": 5360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.101478812554575
      }
    },
    {
      "id": "9b720a4127ba7d679da93bfb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1223.6805140693414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.1667434190995,
        1245.1942847195835
      ],
      "voteCount": 1624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.48608333320146
      }
    },
    {
      "id": "72196ba13fd8c04c867319c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1160.506591111558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.1532382600276,
        1174.8599439630884
      ],
      "voteCount": 3370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.630338810532976
      }
    },
    {
      "id": "cecd0c9738a3a078b7595e4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1244.332780034782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.1019054190317,
        1251.563654650532
      ],
      "voteCount": 19891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.610857267826672
      }
    },
    {
      "id": "cd832ce04fd901b23567d486",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1218.1900494985225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.0273547170223,
        1224.3527442800232
      ],
      "voteCount": 30221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.88655839946507
      }
    },
    {
      "id": "9eccd0a3ce277e964965ca69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1206.5093628991272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.5005271212622,
        1215.5181986769924
      ],
      "voteCount": 10764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.127161805128313
      }
    },
    {
      "id": "8ac170e8dca9a9fc45c614c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1186.8278451262818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.0089660958015,
        1194.6467241567618
      ],
      "voteCount": 15413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.914492943135587
      }
    },
    {
      "id": "d8db59d4dbabafc519d052b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1246.5512143541928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.9626802418877,
        1258.139748466498
      ],
      "voteCount": 5578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.95914680865816
      }
    },
    {
      "id": "9a3a5a5c552bac329161a8b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1244.3536366800688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.4706810453313,
        1252.2365923148063
      ],
      "voteCount": 17322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.176403923551828
      }
    },
    {
      "id": "02ac2ff559d92e844c294d7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1200.4772074465377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.42075540008,
        1208.5336594929956
      ],
      "voteCount": 12836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.89629450853952
      }
    },
    {
      "id": "4c022aa4f9e28ff789d2e716",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1236.567420673688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.524614417855,
        1248.610226929521
      ],
      "voteCount": 5400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.753673613329575
      }
    },
    {
      "id": "a177bb1b03162d74d1ebbb7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1242.788723891154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.2608410845903,
        1249.3166066977174
      ],
      "voteCount": 29645,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.092987306454384
      }
    },
    {
      "id": "a50250d2bf3ccec4a650d2ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1190.8711319938254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.2010475863208,
        1197.54121640133
      ],
      "voteCount": 25481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.581544428789764
      }
    },
    {
      "id": "d1362f5274bd38b05afe2b45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1190.5242576699616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.8403196010445,
        1196.2081957388787
      ],
      "voteCount": 37733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.41012580877993
      }
    },
    {
      "id": "88a6bcecc4f3ceb758558591",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1036.259824249805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1018.7355214963386,
        1053.7841270032711
      ],
      "voteCount": 1992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.9438966625849
      }
    },
    {
      "id": "8874c0eff9b2f6bb5d102dcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1096.3891625391443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1077.534979000674,
        1115.2433460776147
      ],
      "voteCount": 2422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.53782312785447
      }
    },
    {
      "id": "fca39f83c945a54c1dffad55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1206.0643040168302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.4304880655632,
        1214.6981199680972
      ],
      "voteCount": 11165,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.40480982870017
      }
    },
    {
      "id": "5167718c3514c2c8b14c0ac1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1191.9550364521301,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.138302825706,
        1199.7717700785543
      ],
      "voteCount": 14252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.905760659808266
      }
    },
    {
      "id": "c25a2aeb73a9a45db065b0c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1204.564310086253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.4665373569692,
        1212.662082815537
      ],
      "voteCount": 14815,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.070057557791635
      }
    },
    {
      "id": "ffe7b8fa8e3f071c3a3d334f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1222.6887130639252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.9547634110336,
        1226.4226627168168
      ],
      "voteCount": 104642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.6294492954656126
      }
    },
    {
      "id": "23598944bc0da5f65547694a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1170.3423015736034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.2818712741794,
        1179.4027318730277
      ],
      "voteCount": 10009,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.36984959164328
      }
    },
    {
      "id": "5a256fa847b15195fee94253",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3-8b-instruct",
      "organization": "meta",
      "license": "Llama 3 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1221.5898562475845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.5113373916756,
        1242.6683751034934
      ],
      "voteCount": 1744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.66021605266751
      }
    },
    {
      "id": "66b15075cf1743d2cf0057bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1321.1912573510044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.1581220849744,
        1332.2243926170345
      ],
      "voteCount": 3105,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.688501551220707
      }
    },
    {
      "id": "3b8c5aadc63c7898a8d21a2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1374.914168038783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.4211217039287,
        1382.407214373637
      ],
      "voteCount": 6249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.615734802052781
      }
    },
    {
      "id": "e15d27a63273f1c63673147d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1301.034277349806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.3930085617908,
        1308.6755461378214
      ],
      "voteCount": 6512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.19969142351668
      }
    },
    {
      "id": "fda3a71713f67ed927780eb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1360.4310110201736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.8375929777235,
        1365.024429062624
      ],
      "voteCount": 23318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.492572040351856
      }
    },
    {
      "id": "c247ea08ae11bca24300c133",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1285.845661702323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.2165805991974,
        1291.4747428054488
      ],
      "voteCount": 27059,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.248573144886969
      }
    },
    {
      "id": "7e491c0014ade3e1ae643b3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1307.718424244953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.8266424462513,
        1320.6102060436547
      ],
      "voteCount": 2128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.26430288671018
      }
    },
    {
      "id": "f55958398ef27f507c842951",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1343.6325465669288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.1705596628547,
        1374.0945334710032
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 241.55735866415353
      }
    },
    {
      "id": "750faf3f03686ce800ea3e2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1303.960437538898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.5831696840341,
        1323.337705393762
      ],
      "voteCount": 894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.74372889185322
      }
    },
    {
      "id": "c75aebafb76e8f400f80e32e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1360.4906891111273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.2183971634959,
        1367.7629810587587
      ],
      "voteCount": 6791,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.767225588019809
      }
    },
    {
      "id": "85c4cb3520d6a9d7f5e08424",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1340.6251535532738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.648282183004,
        1346.6020249235435
      ],
      "voteCount": 10652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.299329511046079
      }
    },
    {
      "id": "858c591b4c49c76d241b4c55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1314.0524105794116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.9277121708337,
        1323.1771089879894
      ],
      "voteCount": 4512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.674089176481267
      }
    },
    {
      "id": "9f8487e2be4c6d4911d397c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1295.0465596859294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.7629212313007,
        1302.3301981405582
      ],
      "voteCount": 7230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.81021940205552
      }
    },
    {
      "id": "a9fd4d7df5c1bf4934424ae9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1369.8080940976688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.041762212907,
        1382.5744259824307
      ],
      "voteCount": 2330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.42638992091011
      }
    },
    {
      "id": "ba40fa77433f67cf33a1e4d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1362.1407800465413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.795450488239,
        1369.486109604844
      ],
      "voteCount": 7177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.045150251102111
      }
    },
    {
      "id": "050d9df0d3df9145851e66e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1317.8992176673892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.3571451197654,
        1326.4412902150127
      ],
      "voteCount": 4366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.994607729695854
      }
    },
    {
      "id": "0a3167f03c075bf9f95a798f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1364.788299574421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.7610960979196,
        1378.8155030509224
      ],
      "voteCount": 1899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.22075923636197
      }
    },
    {
      "id": "cf2873a2205314de323f6573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1363.2563115264586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.0418243719078,
        1369.4707986810095
      ],
      "voteCount": 10298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.0534334472183
      }
    },
    {
      "id": "d1aac4b791e0a6723509b33c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1311.0911235773626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.9586244104453,
        1317.22362274428
      ],
      "voteCount": 11150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.789912579473299
      }
    },
    {
      "id": "66a97051edb7aa74a669daa5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1312.4782207907617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.2319865309287,
        1317.724455050595
      ],
      "voteCount": 16174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.16471923655147
      }
    },
    {
      "id": "69dee8f2a24e754d6bf507ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1274.021602091172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.7442232593603,
        1294.2989809229841
      ],
      "voteCount": 846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.03540281983848
      }
    },
    {
      "id": "e2305251088cb19714dc2ada",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1242.595099288415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.6946628984367,
        1268.4955356783933
      ],
      "voteCount": 586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.6296489181406
      }
    },
    {
      "id": "ad9480e81083c9912c6a11e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1326.2420285375606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.193268201561,
        1334.2907888735604
      ],
      "voteCount": 5486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.864047220127283
      }
    },
    {
      "id": "c7af1f45c14c724af2580db5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1315.333458184567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.3464944077302,
        1323.320421961404
      ],
      "voteCount": 5215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.606084654312774
      }
    },
    {
      "id": "98669d25c4cc0ccd2ad20ec8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1338.7459790910166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.122251814712,
        1346.3697063673212
      ],
      "voteCount": 6797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.129985845577822
      }
    },
    {
      "id": "d2cfdfa01cfec66a7d8394a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1334.617210005209,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.917915557367,
        1338.316504453051
      ],
      "voteCount": 41375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.562391281695949
      }
    },
    {
      "id": "404fb669ec79366990e8631d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1304.943179847908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.2342799967105,
        1313.6520796991053
      ],
      "voteCount": 4863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.743784889637254
      }
    },
    {
      "id": "81bf4510d43cfe96b42283cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-bf16",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1307.9127502568567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.702177396687,
        1338.1233231170265
      ],
      "voteCount": 348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.58648865972026
      }
    },
    {
      "id": "dee2df0e47445576810b05cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1313.8788863754367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.2563468389828,
        1323.5014259118905
      ],
      "voteCount": 5226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.103672967106235
      }
    },
    {
      "id": "ffbefedb3f3a222642f4de6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1367.6621517062417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.510897974564,
        1374.8134054379193
      ],
      "voteCount": 9714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.31276276068343
      }
    },
    {
      "id": "e6d850b9d32cdc2cc5b8cc8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1304.1424020758413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.393733602933,
        1311.8910705487492
      ],
      "voteCount": 8948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.62996400731736
      }
    },
    {
      "id": "303b2888107308f6c0394310",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1356.3203904790407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.5723707535035,
        1361.0684102045777
      ],
      "voteCount": 32442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.868523487131005
      }
    },
    {
      "id": "b9d9324f7bf1b1a2306b8208",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1281.2575404902104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.4611432351087,
        1287.0539377453124
      ],
      "voteCount": 38128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.746214057523273
      }
    },
    {
      "id": "9402d552fb325902ec2b7b1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1320.5382827325288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.0709195311501,
        1332.0056459339075
      ],
      "voteCount": 3123,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.231895988038396
      }
    },
    {
      "id": "5f01a8f81b6f9e6934806be5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1331.1713882386161,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.736098654908,
        1358.606677822324
      ],
      "voteCount": 545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 195.93991493208688
      }
    },
    {
      "id": "2c1b5be72d5d86217152dfb0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1302.8326914448994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.9754286833804,
        1318.6899542064182
      ],
      "voteCount": 1587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.45762795458411
      }
    },
    {
      "id": "579cd9cac71f38c7aec6395f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1352.2700280682632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.2103116528776,
        1359.329744483649
      ],
      "voteCount": 9964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.97413253454043
      }
    },
    {
      "id": "1064d8a0bda1706b5ae40129",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1335.2592030382687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.4028045289601,
        1341.1156015475774
      ],
      "voteCount": 16228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.92822365166879
      }
    },
    {
      "id": "cf05fb6f2d19530e9910c435",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1314.8715880075765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.3762151923581,
        1323.3669608227951
      ],
      "voteCount": 6667,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.78748742034267
      }
    },
    {
      "id": "e648afd04e14af97c9516c47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1303.4095716931151,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.0657861386649,
        1310.7533572475654
      ],
      "voteCount": 9523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.039246230942492
      }
    },
    {
      "id": "cac00a59f430a6337296d85e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1369.756936216204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.2109510428827,
        1381.3029213895256
      ],
      "voteCount": 3383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.70290320552529
      }
    },
    {
      "id": "4ebe820e907c84dbc1f13044",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1349.4946269594566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.1766445537405,
        1356.8126093651726
      ],
      "voteCount": 10001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.94076286901221
      }
    },
    {
      "id": "0a571bb866970cbb28266a42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1319.0062814322293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.1955931747916,
        1326.816969689667
      ],
      "voteCount": 7242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.881167520585553
      }
    },
    {
      "id": "e7f874867445a2c9fbf17ec7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1346.0464783801758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.8139147068357,
        1358.2790420535157
      ],
      "voteCount": 3064,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.95280959832843
      }
    },
    {
      "id": "840902a0a3664da99e912ae8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1354.1483289084763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.0723534284796,
        1360.2243043884732
      ],
      "voteCount": 15817,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.610275615775432
      }
    },
    {
      "id": "346c96822166980c504630d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1314.6754550384612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.4968149595704,
        1320.8540951173522
      ],
      "voteCount": 15999,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.937785358734894
      }
    },
    {
      "id": "f5f07cf717d8bcbd1a227ebc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1313.0053396926328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.7118703415251,
        1318.2988090437402
      ],
      "voteCount": 23585,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.294316841343018
      }
    },
    {
      "id": "ac4f898b70f50cbeffe420b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1238.244873151507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.1268823484693,
        1254.362863954545
      ],
      "voteCount": 1606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.62785692959004
      }
    },
    {
      "id": "37764bc25748f252b50d376c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1254.6567158770265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.8833999885726,
        1276.4300317654806
      ],
      "voteCount": 924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.41074235249492
      }
    },
    {
      "id": "1a5445b32ae1b1c6999c1b0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1318.1475522507635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.509221239833,
        1325.7858832616944
      ],
      "voteCount": 8047,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.188006264245779
      }
    },
    {
      "id": "49e92e0dfabe66f9f6a60952",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1318.753112603622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.2454809720257,
        1326.2607442352182
      ],
      "voteCount": 8482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.672689555360186
      }
    },
    {
      "id": "2ba09a833f85bca7ea33f07d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1328.8210755495309,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.627202024005,
        1336.0149490750566
      ],
      "voteCount": 11136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.471917497194337
      }
    },
    {
      "id": "341c091235b90fb91babf39d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1332.7876441412445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.2032596636823,
        1336.372028618807
      ],
      "voteCount": 59656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.3445138117265882
      }
    },
    {
      "id": "c12e5a217a5032abd5cb6803",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1313.3574957472035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.3848552994154,
        1321.3301361949916
      ],
      "voteCount": 7673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.546577401087987
      }
    },
    {
      "id": "c8ac3e75d271e0bc07013915",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-405b-instruct-fp8",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1305.6720467655941,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.516920835084,
        1330.8271726961045
      ],
      "voteCount": 652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.72397339547524
      }
    },
    {
      "id": "5f64d2de6f7d12c6b29bd4c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1276.1645805288583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.3595020439561,
        1285.9696590137605
      ],
      "voteCount": 4846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.026837090426532
      }
    },
    {
      "id": "a9b0aeff16f6e2ac451659bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1332.929085816346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.802189271877,
        1340.055982360815
      ],
      "voteCount": 9389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.222230596860834
      }
    },
    {
      "id": "d227c512826e239d7d597c73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1257.0501823319064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.2481198354274,
        1264.8522448283854
      ],
      "voteCount": 8250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.846110043154159
      }
    },
    {
      "id": "e3ff1881998318deab330bad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1320.7059385502844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.8928008036848,
        1325.5190762968841
      ],
      "voteCount": 29694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.030598282856567
      }
    },
    {
      "id": "4654eb81da7620c34d0a72b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1222.181887474324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.2410490218313,
        1228.122725926817
      ],
      "voteCount": 34840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.187541287307292
      }
    },
    {
      "id": "f26d2179a434c299c121bb9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1271.6528296816132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.1519227296212,
        1283.1537366336054
      ],
      "voteCount": 2924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.43245571339488
      }
    },
    {
      "id": "f68af39fbd656ebec091bce0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1302.3071839480965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.8400578931787,
        1330.7743100030143
      ],
      "voteCount": 501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.95560401716148
      }
    },
    {
      "id": "d4cc02cb6f384b67fe4090f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1255.8521437875092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.1362226603137,
        1272.5680649147048
      ],
      "voteCount": 1353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.7385173636015
      }
    },
    {
      "id": "05a0549a5ce1d5d0d773853c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1314.3358174084447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.2209267405078,
        1321.4507080763815
      ],
      "voteCount": 9133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.177720126529158
      }
    },
    {
      "id": "bb8ecd8e12a374ab49fe16b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1297.9962165630488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.132037865576,
        1303.8603952605217
      ],
      "voteCount": 14981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.951961585697873
      }
    },
    {
      "id": "2112626d977d73235fc13cce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1287.6717943637582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.1423595669667,
        1296.2012291605492
      ],
      "voteCount": 6381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.938445353311792
      }
    },
    {
      "id": "47020a13ad50e50f95668f90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1263.641103453932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.2779846748817,
        1271.0042222329823
      ],
      "voteCount": 8719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.113262873557796
      }
    },
    {
      "id": "1f82093eba681c588c8a1e76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1328.8162148320841,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.0584663816292,
        1340.5739632825391
      ],
      "voteCount": 3177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.98753886920394
      }
    },
    {
      "id": "b610dbcef011947530ce6415",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1318.3693948431228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.9638087352796,
        1325.774980950966
      ],
      "voteCount": 9381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.276530911965374
      }
    },
    {
      "id": "27f690a29e92ccb6991428aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1275.4436475595846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.5201484713893,
        1283.3671466477797
      ],
      "voteCount": 6524,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.343228114907816
      }
    },
    {
      "id": "77526abde1f0d761d1d34bf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1311.5297876151467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.978272176928,
        1324.0813030533657
      ],
      "voteCount": 2821,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.01060226057044
      }
    },
    {
      "id": "5bdb11c252b9b2bd6e13545c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1319.001063979533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.8976057611555,
        1325.1045221979102
      ],
      "voteCount": 14811,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.697410271014423
      }
    },
    {
      "id": "d11fdac34b5d957e28173143",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1262.9682065944075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.719789420672,
        1269.2166237681433
      ],
      "voteCount": 14962,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.163513133789131
      }
    },
    {
      "id": "fe6f18b1c48cdaedc798f563",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1271.6341323666834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.3438514853633,
        1276.924413248004
      ],
      "voteCount": 21910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.285532166190469
      }
    },
    {
      "id": "0335fef824335b5e9b060d98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1174.9949129950971,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.4676940793695,
        1191.5221319108248
      ],
      "voteCount": 1428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.10552991403141
      }
    },
    {
      "id": "e9ed3cfb7a64db721e2dfeb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1186.800584133574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.0308552287956,
        1209.570313038352
      ],
      "voteCount": 873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.96449619715196
      }
    },
    {
      "id": "61e1e0c4b33f18350db44bcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1293.0892257073474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.4115711952884,
        1300.7668802194062
      ],
      "voteCount": 7622,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.34478997639955
      }
    },
    {
      "id": "f11e4011e57e0449091ce5de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1269.0038748454263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.4729044698365,
        1276.5348452210158
      ],
      "voteCount": 7677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.764056428896092
      }
    },
    {
      "id": "b32e28a9499c8a74a9b80543",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1288.3816383887104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.2089874912026,
        1295.5542892862181
      ],
      "voteCount": 10405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.392547805112814
      }
    },
    {
      "id": "f8bd6e5f3c00ae86020a40f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1293.078228283226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.3539576067983,
        1296.8024989596536
      ],
      "voteCount": 55240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.610657492038942
      }
    },
    {
      "id": "3d28a35019dbec4c24f9ebf2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1269.3329855561299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.210512889122,
        1277.455458223138
      ],
      "voteCount": 7285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.17435102281563
      }
    },
    {
      "id": "0af96f233163bdfe86a106ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-70b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1285.128511323633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.9559330002826,
        1310.3010896469832
      ],
      "voteCount": 606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.95262061164073
      }
    },
    {
      "id": "a065b6ae5e36ea57a11c6139",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1202.7812755706996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.2694948228982,
        1213.2930563185007
      ],
      "voteCount": 4400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.764471948674696
      }
    },
    {
      "id": "30a9efd901de2797dfcfc1b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1259.434687026665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.961154555388,
        1266.9082194979421
      ],
      "voteCount": 8582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.5397074929831
      }
    },
    {
      "id": "a61a4e5004250e2272f5f39a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1177.421099195843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.992220378505,
        1185.849978013181
      ],
      "voteCount": 7346,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.494535912929578
      }
    },
    {
      "id": "64839bb90c2655bc435e2414",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1237.3871902313504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.2155492003988,
        1242.558831262302
      ],
      "voteCount": 26610,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.962425526714159
      }
    },
    {
      "id": "bef317ca89e7e1c02626a663",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1089.583517118443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1082.8663846019508,
        1096.3006496349349
      ],
      "voteCount": 31686,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.745503817729753
      }
    },
    {
      "id": "44b66c64de1895384a4b2dab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1195.2978629397344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.0563968853985,
        1207.5393289940703
      ],
      "voteCount": 2589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.00952688915701
      }
    },
    {
      "id": "cf50c10e56e1ab56747b1178",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1207.4307585458143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.7201884024284,
        1237.1413286892
      ],
      "voteCount": 478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 229.7871770718461
      }
    },
    {
      "id": "53bdaeb4ed51b221f4d7dc4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1167.1110492459502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.4791780583723,
        1184.742920433528
      ],
      "voteCount": 1295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.92833896867548
      }
    },
    {
      "id": "aee62ed47485b70828029006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1239.9039265011027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.3707090075054,
        1247.4371439947001
      ],
      "voteCount": 8195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.77286844782263
      }
    },
    {
      "id": "d1f050261a0c8d9c85caf181",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1222.0557575881414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.875205322829,
        1228.2363098534538
      ],
      "voteCount": 13535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.943937469400389
      }
    },
    {
      "id": "1b91d10900ea4af6bbcfa3d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1209.859316584813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.8181706818887,
        1218.9004624877375
      ],
      "voteCount": 5722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.27897839165091
      }
    },
    {
      "id": "07f5efe3d355f9ea2d6e6e7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1174.0593079116152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.1125368657536,
        1182.0060789574768
      ],
      "voteCount": 7706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.439371864445263
      }
    },
    {
      "id": "0fe7420ab92c6009e19d7c86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1246.2119491125968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.863846810424,
        1258.5600514147693
      ],
      "voteCount": 2882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.69211635005105
      }
    },
    {
      "id": "738fd3ff893df3ef3f51a029",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1228.4456839986938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.5329708811823,
        1236.3583971162052
      ],
      "voteCount": 8403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.29876351732557
      }
    },
    {
      "id": "1a7db628bc62d81de8ffef1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1194.295247351271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.0282540395806,
        1202.5622406629614
      ],
      "voteCount": 5985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.790943911038376
      }
    },
    {
      "id": "d02ac4184094a23889951217",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1229.2324414027216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.0599025993622,
        1242.4049802060808
      ],
      "voteCount": 2564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.16924080801522
      }
    },
    {
      "id": "df69196f08ea06b1913c7f16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1244.9799862134655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.420323045611,
        1251.5396493813205
      ],
      "voteCount": 13139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.201260480500347
      }
    },
    {
      "id": "03de5b597fdd78c3724de814",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1182.1190426607648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.4474652532608,
        1188.7906200682687
      ],
      "voteCount": 13505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.586729724796209
      }
    },
    {
      "id": "f0f2396aa28371ea49821fdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1190.6397225995152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.0823056648942,
        1196.197139534136
      ],
      "voteCount": 19781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.039883915671286
      }
    },
    {
      "id": "1419474625f2a1b056537345",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1087.1675672417557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.4060839957872,
        1105.9290504877245
      ],
      "voteCount": 1234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.63009940196602
      }
    },
    {
      "id": "535c1ac3c803759e6f610a88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1085.6092233284985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1061.599010325935,
        1109.619436331062
      ],
      "voteCount": 802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.07067766101815
      }
    },
    {
      "id": "622c9d58e047ce5ab0fdd069",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1222.6408089473891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.5301002386936,
        1230.7515176560846
      ],
      "voteCount": 6736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.12463905715418
      }
    },
    {
      "id": "f34941a15bdbb8f7c6a8d851",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1189.4140347277676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.519195556102,
        1197.3088738994334
      ],
      "voteCount": 7135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.22521246634237
      }
    },
    {
      "id": "724c88322480ee978a1b4791",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1198.362978003437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.6654951532873,
        1206.0604608535868
      ],
      "voteCount": 8930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.42415134301574
      }
    },
    {
      "id": "123c7529527e0d01e66c712e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1211.2702369640667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.1316224539473,
        1215.4088514741861
      ],
      "voteCount": 49605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.458756650234121
      }
    },
    {
      "id": "4d39669788e308478d787912",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1188.7899958255823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.3273791898027,
        1197.2526124613617
      ],
      "voteCount": 6589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.64288637909442
      }
    },
    {
      "id": "b83ebf6b9143e11ef91066b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-8b-instruct",
      "organization": "meta",
      "license": "Llama 3.1 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1186.5321539398365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.9342662687259,
        1214.1300416109473
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.2693136795415
      }
    },
    {
      "id": "928b09d4611967c7459d31c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1274.9786697903987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.806722959685,
        1303.1506166211127
      ],
      "voteCount": 403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.60343512133767
      }
    },
    {
      "id": "acb97c24a2503efda9eb6cce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1310.8141035017888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.1770526203334,
        1332.451154383244
      ],
      "voteCount": 665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.87088101131623
      }
    },
    {
      "id": "f31ca52dd11368ef4943d2e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1261.169726187984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.668478904193,
        1286.6709734717751
      ],
      "voteCount": 482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.2881906024319
      }
    },
    {
      "id": "9c56f45a9a63bda41b1f914c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1317.7345179607778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.1749670148058,
        1331.2940689067495
      ],
      "voteCount": 1794,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.86239562583261
      }
    },
    {
      "id": "9bd710b2378cc3e080ef927f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1204.9129543175845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.81858262259,
        1221.0073260125791
      ],
      "voteCount": 2408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.42980007002667
      }
    },
    {
      "id": "57f141ac1986711858892024",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1248.7561793798827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.4047617296146,
        1282.1075970301506
      ],
      "voteCount": 265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 289.555898215153
      }
    },
    {
      "id": "ec754bfc467c654d63435499",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1276.8945173672582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.5144268427616,
        1299.2746078917544
      ],
      "voteCount": 578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.38495927288028
      }
    },
    {
      "id": "6162c2695813a02072974296",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1280.354304469075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.9489352243768,
        1297.7596737137733
      ],
      "voteCount": 1002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.862456344006
      }
    },
    {
      "id": "1b1b939464bfab2855c815f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1292.4791967974031,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.2387231192554,
        1319.719670475551
      ],
      "voteCount": 421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.16708595506512
      }
    },
    {
      "id": "e1d54f85d97caa9934cc53d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1250.1679983042775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1226.3915946521367,
        1273.9444019564182
      ],
      "voteCount": 551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.162158184318
      }
    },
    {
      "id": "c95ad41b46fc5317c5a4aed7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1331.5567680837155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.7135281832147,
        1367.400007984216
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 334.4400933426357
      }
    },
    {
      "id": "f0ab6b02c37e2ad5c777911d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1302.337907192148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.7728443403194,
        1323.9029700439764
      ],
      "voteCount": 682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 121.06128361914341
      }
    },
    {
      "id": "94f35d391f7a7280c35501af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1275.2117777165647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.8154964795854,
        1300.6080589535443
      ],
      "voteCount": 422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.89743968964794
      }
    },
    {
      "id": "b9e09c8ad5bad9884ba52e7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1278.096386270869,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.8228411571226,
        1317.3699313846155
      ],
      "voteCount": 213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 401.51708447125094
      }
    },
    {
      "id": "75e19cf44c1bb8cc3a145ea6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1310.512752789436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.8324825721513,
        1328.1930230067208
      ],
      "voteCount": 1055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.37324114272876
      }
    },
    {
      "id": "b57ecb5de251dd18f1b8f5d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1268.0766492145212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.9948202685805,
        1286.1584781604618
      ],
      "voteCount": 1007,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.11155612783058
      }
    },
    {
      "id": "a71eff196fe78abdea0836cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1260.4859114092005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.8830987729002,
        1275.0887240455004
      ],
      "voteCount": 1484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.51071789241623
      }
    },
    {
      "id": "8ff5f1b2d522314ab8e722e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1268.9821309238525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.0437913191881,
        1291.920470528517
      ],
      "voteCount": 587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.97073127126166
      }
    },
    {
      "id": "a6115d356d82cb220fd06182",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1270.6559487604611,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.1904537019946,
        1293.1214438189277
      ],
      "voteCount": 507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.38198059111133
      }
    },
    {
      "id": "7b18a97b9c00d725dd61914d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1275.8041085963562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.6676753583733,
        1295.9405418343388
      ],
      "voteCount": 781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.55259407270387
      }
    },
    {
      "id": "704fe10b0f516e6edd10a1a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1285.67365550547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.702284630861,
        1295.6450263800793
      ],
      "voteCount": 3749,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.88293712362091
      }
    },
    {
      "id": "ea3d529ebfee58dc81e7c0db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-51b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1247.2297762425405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.030026978957,
        1269.4295255061243
      ],
      "voteCount": 605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.29211254617445
      }
    },
    {
      "id": "8c3eec2894da199eb57ad170",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1303.3051521791801,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.7643595583522,
        1324.845944800008
      ],
      "voteCount": 723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.7889420117938
      }
    },
    {
      "id": "2ff68aa1d6a929760e88ebd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1328.7437750307092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.3069998171045,
        1344.180550244314
      ],
      "voteCount": 1312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.03217062009305
      }
    },
    {
      "id": "07bf59de417a58dfb847499c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1276.8883880920541,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.1401331684958,
        1295.6366430156124
      ],
      "voteCount": 1001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.50093208996455
      }
    },
    {
      "id": "1314cf8fe8fadb6a51ac7ff1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1329.2607313324659,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.3160746741373,
        1339.2053879907944
      ],
      "voteCount": 3714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.744437378653462
      }
    },
    {
      "id": "096de26b7c5878fd875e68ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1233.0894970694053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.5546274817593,
        1244.6243666570517
      ],
      "voteCount": 4748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.63611680209636
      }
    },
    {
      "id": "a8dd1cf74aeda4b17160334f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1293.3144919803522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.1180292954277,
        1320.5109546652764
      ],
      "voteCount": 453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.54341048456925
      }
    },
    {
      "id": "50936bc00abdba8489d046ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1327.1911620895153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.4160071631295,
        1343.9663170159008
      ],
      "voteCount": 1136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.25493671526411
      }
    },
    {
      "id": "267b01e46ccefc5c216f7e9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1310.0934217589115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.1966647628692,
        1322.9901787549538
      ],
      "voteCount": 1953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.29770245588928
      }
    },
    {
      "id": "6aefba0e43180f6056c0fff6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1294.9481333413307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.7295894523565,
        1314.1666772303051
      ],
      "voteCount": 904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.14900131760062
      }
    },
    {
      "id": "464fe3e39cffbf1dd5aeee7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1268.4259429069148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.4002983425532,
        1287.451587471276
      ],
      "voteCount": 961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.2285647159459
      }
    },
    {
      "id": "b0f7e1a63f2f051dad58fd6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1326.534864676048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.924789461958,
        1353.1449398901382
      ],
      "voteCount": 489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.3299996045737
      }
    },
    {
      "id": "ff8fc6aa77d68d8205755d4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1316.5854930570242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.2423577631341,
        1332.928628350914
      ],
      "voteCount": 1299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.53037470960874
      }
    },
    {
      "id": "a7d91dd5f5574ed5969d81b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1300.0153476638707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.6981570469013,
        1318.3325382808403
      ],
      "voteCount": 874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.34168131412342
      }
    },
    {
      "id": "5031033a535709b989875923",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1334.4197894821546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.6451489023336,
        1365.1944300619755
      ],
      "voteCount": 392,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 246.54136540920467
      }
    },
    {
      "id": "c66428d9c11c9411a4833bf0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1325.0650216660226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.4310983580958,
        1337.6989449739494
      ],
      "voteCount": 2081,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.55088616093336
      }
    },
    {
      "id": "3b637f0a9267c3bbb1de960c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1265.303254520837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.4227920649478,
        1279.183716976726
      ],
      "voteCount": 1828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.154706058916545
      }
    },
    {
      "id": "456b5df9f314954b8a2ea2cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1279.9973320363356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.1000849301104,
        1290.8945791425608
      ],
      "voteCount": 2959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.912733947432113
      }
    },
    {
      "id": "77af80c939613998127db01f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1280.4270145628393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.735961010693,
        1298.1180681149858
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.47253176290927
      }
    },
    {
      "id": "363b1f7a6e9fcf95ccbc887c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1278.4541445166703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.58816623907,
        1295.3201227942704
      ],
      "voteCount": 1041,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.05031175346149
      }
    },
    {
      "id": "6d17a8e282a7aef642b91254",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1293.4147789861684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.652495000828,
        1310.1770629715088
      ],
      "voteCount": 1227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.14256836272187
      }
    },
    {
      "id": "c3f0f20eb362dd449f3c6c6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1298.8636242966577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.1045887385042,
        1306.6226598548114
      ],
      "voteCount": 7140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.671815214672646
      }
    },
    {
      "id": "7178364f8e8abc23816e846d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-70b-instruct",
      "organization": "nvidia",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1241.0638250996706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.5615011673497,
        1258.5661490319915
      ],
      "voteCount": 1069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.74349259757042
      }
    },
    {
      "id": "a518ded94b819d65a2a7b7ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1391.4231199419348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.5436256767498,
        1421.3026142071199
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.4075876419022
      }
    },
    {
      "id": "36978d1f65038cc0e5d3f2cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1332.0729225345813,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.0938628887907,
        1359.0519821803716
      ],
      "voteCount": 444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.47740776239695
      }
    },
    {
      "id": "19cd5bc90d4e56073c9565e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1375.3530756673524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.4656261652185,
        1390.2405251694863
      ],
      "voteCount": 1491,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.695829377273604
      }
    },
    {
      "id": "3064240e307ec37afce30b23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1303.8421127901809,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.2101685767352,
        1321.4740570036263
      ],
      "voteCount": 1699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.92900933137648
      }
    },
    {
      "id": "73432aefcdab776d37481892",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1397.0890377242836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.458267108782,
        1423.7198083397852
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.6168283140202
      }
    },
    {
      "id": "d1153d57bff621b06827c6d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1374.5159133338984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.27046525743,
        1395.7613614103666
      ],
      "voteCount": 713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.49938891401466
      }
    },
    {
      "id": "e7e86c2e631e9f57a80014f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1342.4956560793416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.840991461714,
        1377.1503206969692
      ],
      "voteCount": 254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 312.62752923204613
      }
    },
    {
      "id": "c2f3754cc7ed7bb5bc91e1b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1302.887820211691,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.1115170178532,
        1326.6641234055287
      ],
      "voteCount": 532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.16091462960043
      }
    },
    {
      "id": "2cb4448baea9e6f951bf8a6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1360.0021772603045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.9082908739556,
        1386.0960636466534
      ],
      "voteCount": 498,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.24800356460796
      }
    },
    {
      "id": "5740d40ba60e31daa0858a19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1387.399958923364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.7758741345237,
        1411.0240437122038
      ],
      "voteCount": 588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.28266686181942
      }
    },
    {
      "id": "a32b5763980717733d190e40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1320.2045340338032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.2591936738754,
        1341.149874393731
      ],
      "voteCount": 712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.20330225326978
      }
    },
    {
      "id": "87765eb0fd62da8db2910de2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1350.6475743659955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.97999358294,
        1372.315155149051
      ],
      "voteCount": 660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.21504353010259
      }
    },
    {
      "id": "6be76b1e3ba1b5a1357cb9c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1341.3703322081547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.1659248674582,
        1371.574739548851
      ],
      "voteCount": 321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.4895229614544
      }
    },
    {
      "id": "abf91d0c39c9f2f47621fb8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1379.6947522148662,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.420854200312,
        1416.96865022942
      ],
      "voteCount": 209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 361.67079696778313
      }
    },
    {
      "id": "3332a00071c4544dc9508515",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1342.5279905035204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.233783171816,
        1372.8221978352249
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.90377085715153
      }
    },
    {
      "id": "9810dd66415a23dadee07116",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1347.2874457908238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.6009032429022,
        1358.9739883387456
      ],
      "voteCount": 2549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.552971696233264
      }
    },
    {
      "id": "9ad194c29e711162a60c5a78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-nemotron-ultra-253b-v1",
      "organization": "nvidia",
      "license": "Nvidia Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1312.8653562273557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.0698755357696,
        1342.660836918942
      ],
      "voteCount": 303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.10248243719965
      }
    },
    {
      "id": "7ba3e788035d19575e45127b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1297.400146209046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.0183303216763,
        1333.7819620964156
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 344.5661112210695
      }
    },
    {
      "id": "e4e3ecd25967e0aafbc9e145",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1307.3293974741632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.644889594461,
        1331.0139053538658
      ],
      "voteCount": 450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.02679338427032
      }
    },
    {
      "id": "a8c89a84e0cdfbc4dd528cd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1247.0513853528614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.1038668435708,
        1271.998903862152
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.01623102624822
      }
    },
    {
      "id": "e32b6d34c397f5cae5f2e8be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1301.527819210275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.2009345263518,
        1314.8547038941979
      ],
      "voteCount": 1629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.23396050006097
      }
    },
    {
      "id": "2fa5597f4f4134583eab671e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1212.8179291646416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.163825588475,
        1230.472032740808
      ],
      "voteCount": 1728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.1325560485103
      }
    },
    {
      "id": "de996f8df33251d56b120213",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1290.3055722029226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.9704571203572,
        1313.6406872854882
      ],
      "voteCount": 499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.75021035841328
      }
    },
    {
      "id": "81a84cfd25e194685cc1bc8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1273.0449026446654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.406877278515,
        1291.6829280108159
      ],
      "voteCount": 779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.42814351619107
      }
    },
    {
      "id": "b90e07823863ee1ca4bc83c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1276.4587953161767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.9742757243364,
        1308.9433149080173
      ],
      "voteCount": 288,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 274.69877001622905
      }
    },
    {
      "id": "232f9527ef91fe5c9134b6fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1260.0779870363208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.620185174019,
        1282.5357888986227
      ],
      "voteCount": 551,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.29201379679824
      }
    },
    {
      "id": "b0f36caa57a497427190a2b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1307.006783406665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.4693930728831,
        1331.5441737404467
      ],
      "voteCount": 520,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.7330414031556
      }
    },
    {
      "id": "4183e106dff4e9c6e88c9dd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1273.220688051642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.6164757224178,
        1300.8249003808658
      ],
      "voteCount": 349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.3601995710557
      }
    },
    {
      "id": "6ea0b9b3b43bbd7b2b666ca5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1298.5882487189047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.7234200358319,
        1318.4530774019772
      ],
      "voteCount": 711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.72436515056086
      }
    },
    {
      "id": "2bbf76753fb22a77c118bbd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1277.3645854269798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.8389461307238,
        1296.8902247232363
      ],
      "voteCount": 758,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.24630400140937
      }
    },
    {
      "id": "3a43d6f89d0b32b0afd42438",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1271.3380237735332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.7882378046706,
        1286.887809742396
      ],
      "voteCount": 1170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.94375521478224
      }
    },
    {
      "id": "1d2fba9d99dafb26ff4ae1a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1271.972795245526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.8128145101896,
        1297.1327759808623
      ],
      "voteCount": 463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.78756122345004
      }
    },
    {
      "id": "3d6a46def833f91f6d41847a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1263.4879060064047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.8185350131357,
        1288.1572769996737
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.42363373130544
      }
    },
    {
      "id": "dd47ff52a13d4e9fa607e80a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1277.7680514952908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.607610923276,
        1300.9284920673053
      ],
      "voteCount": 537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.6360165570897
      }
    },
    {
      "id": "3e3d7f8a61260017c9f90e45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1285.977348290232,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.5090301315256,
        1296.4456664489383
      ],
      "voteCount": 2846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.52710134013589
      }
    },
    {
      "id": "9743c36262c934207676e31b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-70b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1276.319969829026,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.2557439242096,
        1303.3841957338423
      ],
      "voteCount": 366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.67556311708265
      }
    },
    {
      "id": "70120358fd7da2745484ea62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1220.601747445353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.084109435797,
        1257.119385454909
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 347.1436108108546
      }
    },
    {
      "id": "999d21621fd85642601ca949",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1252.9711747802994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.1002745213148,
        1277.8420750392838
      ],
      "voteCount": 476,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.02259807137204
      }
    },
    {
      "id": "f9ca98dd25c9a60eeda9dbc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1196.9219588812566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.7541599828191,
        1222.089757779694
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.88998866262378
      }
    },
    {
      "id": "f7aa6a19180f423c25f8c404",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1238.7114847024627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.910484598649,
        1252.5124848062762
      ],
      "voteCount": 1633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.582102205392964
      }
    },
    {
      "id": "29aa71c09a9705285882616b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1101.169593760489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1081.787002864863,
        1120.5521846561155
      ],
      "voteCount": 1763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.79743773469099
      }
    },
    {
      "id": "4971979cc9ecccc24ad5b8c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1225.1098488609678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.5407928851287,
        1250.6789048368066
      ],
      "voteCount": 452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.18967377019845
      }
    },
    {
      "id": "cdd6b2b46aa976116f58ee13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1222.5617110045646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.7809798955664,
        1242.3424421135624
      ],
      "voteCount": 728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.85644086529062
      }
    },
    {
      "id": "47cc0bafd3bc4e4a1f65adcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1244.4739547639506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.6684287408127,
        1276.2794807870882
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.3352413304541
      }
    },
    {
      "id": "f5fed9b9846da829c5e2fa77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1179.2307128176044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.2748459699337,
        1202.186579665275
      ],
      "voteCount": 563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.18013060277042
      }
    },
    {
      "id": "d37e38e8ba59ddbb92f4314e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1234.810008529927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.179106012217,
        1259.4409110476367
      ],
      "voteCount": 516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.9299394200713
      }
    },
    {
      "id": "97691845d56bbbe441240231",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1208.8771424249308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.5245774457926,
        1238.2297074040687
      ],
      "voteCount": 304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 224.2827818986847
      }
    },
    {
      "id": "b1ee4d6d563fe1ac4e93e535",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1244.351087880774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.3619724120779,
        1264.34020334947
      ],
      "voteCount": 761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.01380201406549
      }
    },
    {
      "id": "8a3b524c271f19a3bae575ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1200.0214098876536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.4803720424575,
        1219.5624477328497
      ],
      "voteCount": 816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.40290339970208
      }
    },
    {
      "id": "7f4d902c538b372bde712ca2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1207.7090214620096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.0929379611837,
        1223.3251049628354
      ],
      "voteCount": 1172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.481629060051134
      }
    },
    {
      "id": "f5ad7466e2cc44bc5f0e396b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1225.7189230175022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.8376851089733,
        1251.6001609260315
      ],
      "voteCount": 454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.37085933849684
      }
    },
    {
      "id": "101a1068d38413d51b3a8db6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1206.506994730264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.9255142480838,
        1232.0884752124443
      ],
      "voteCount": 363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.35511096326613
      }
    },
    {
      "id": "4c389722a844faeaa1550301",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1178.0833358390669,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.7130530593863,
        1203.4536186187474
      ],
      "voteCount": 520,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.55385866785088
      }
    },
    {
      "id": "40cd3777fe6870f30dc7fe7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1220.496022843608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.8173170254631,
        1231.1747286617529
      ],
      "voteCount": 2896,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.685274077694185
      }
    },
    {
      "id": "e3415909b1c3226a313fde00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.1-tulu-3-8b",
      "organization": "allenai",
      "license": "Llama 3.1",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1223.6695992797188,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.9067486839103,
        1248.4324498755275
      ],
      "voteCount": 418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.62653727459139
      }
    },
    {
      "id": "a1ffb0ca96ea351763072759",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1044.8339085901382,
      "unit": "Arena rating",
      "confidenceInterval": [
        1016.3566812527725,
        1073.311135927504
      ],
      "voteCount": 674,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.10534166222624
      }
    },
    {
      "id": "0226e2bf0c86fb9216a2ed49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1148.0149736329843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.7255021287356,
        1164.304445137233
      ],
      "voteCount": 1346,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.07450900118731
      }
    },
    {
      "id": "5e9168ec84c534746c163c7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1082.2408957465252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1061.551044440125,
        1102.9307470529254
      ],
      "voteCount": 1091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.43421472460349
      }
    },
    {
      "id": "b02679b8cbe97ed789674a7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1165.4606084134998,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.7375364946554,
        1175.1836803323445
      ],
      "voteCount": 4320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.60995469474858
      }
    },
    {
      "id": "dd34ccb24e29daec81948b3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 896.7478128242205,
      "unit": "Arena rating",
      "confidenceInterval": [
        880.661733954055,
        912.833891694386
      ],
      "voteCount": 5619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.36032988905754
      }
    },
    {
      "id": "3f1cc8c2a84cdab57736e685",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1079.367966671623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1051.3628795919597,
        1107.373053751286
      ],
      "voteCount": 487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 204.16329809772836
      }
    },
    {
      "id": "191222f50a39b9f92dd9d4de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1066.0765561131702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1026.0624080726698,
        1106.0907041536707
      ],
      "voteCount": 247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 416.8031256203267
      }
    },
    {
      "id": "7e86b07f6b4b62f10cbec3fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1153.6616342560492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.4883527414215,
        1168.8349157706766
      ],
      "voteCount": 1437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.93256277586152
      }
    },
    {
      "id": "0b6ee88b436390cc02e21d7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1113.177985193201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.2573772885737,
        1126.0985930978281
      ],
      "voteCount": 2247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.457997708004065
      }
    },
    {
      "id": "94faea62797b4f3a653b40f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1071.0898780124078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.1832327830753,
        1091.99652324174
      ],
      "voteCount": 1044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.78172593977872
      }
    },
    {
      "id": "eef764eef0e6f9569cb045e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1080.5378811584144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1061.488172887518,
        1099.5875894293108
      ],
      "voteCount": 1151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.46707673953085
      }
    },
    {
      "id": "d3fc273cf1233070b61a723a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1150.0165514301416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.0543592294903,
        1179.978743630793
      ],
      "voteCount": 489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.69584404566237
      }
    },
    {
      "id": "3987bf528bd2aaecba98332f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1131.029770984205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.6211254168109,
        1149.4384165515992
      ],
      "voteCount": 1407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.2160261097654
      }
    },
    {
      "id": "68bc63ed06ac0ba031bddcc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1141.3307964308058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1123.286255202756,
        1159.3753376588556
      ],
      "voteCount": 976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.76088989337443
      }
    },
    {
      "id": "9b7abb1813e312c16a59a7b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1098.271194905765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.8527711101374,
        1130.6896187013926
      ],
      "voteCount": 445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 273.5820557886412
      }
    },
    {
      "id": "9628eb6eca21ee4ae019b61c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1126.296733354451,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.6407282667024,
        1139.9527384421995
      ],
      "voteCount": 2184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.5457435992807
      }
    },
    {
      "id": "21b5b06a887c1f2d1d7730d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1074.8200626695839,
      "unit": "Arena rating",
      "confidenceInterval": [
        1059.627200394666,
        1090.012924944502
      ],
      "voteCount": 2047,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.087345687833036
      }
    },
    {
      "id": "eb4dc91aaa76956be6333b75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1084.3937615834059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.9879232962826,
        1095.7995998705292
      ],
      "voteCount": 3248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.86555813931673
      }
    },
    {
      "id": "0b54a1e6140c5843822f7021",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1100.0214605198923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.8605270810158,
        1119.182393958769
      ],
      "voteCount": 1057,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.57342337532036
      }
    },
    {
      "id": "ddb764108c1fe229d6c3e62f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1123.4991580018027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.4047861030026,
        1139.5935299006023
      ],
      "voteCount": 1162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.42980177777227
      }
    },
    {
      "id": "96569c343b6798dcbd5ce4ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1074.9764532102847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1056.2591510989785,
        1093.693755321591
      ],
      "voteCount": 1236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.1990508498034
      }
    },
    {
      "id": "3c356de6e1dc1429e6cd388c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1110.4354048086207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.557530032594,
        1118.313279584647
      ],
      "voteCount": 8045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.155558053214
      }
    },
    {
      "id": "a5f3ce1df5d62701bfec46bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-1b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 987.7725704076745,
      "unit": "Arena rating",
      "confidenceInterval": [
        963.6558948255026,
        1011.8892459898462
      ],
      "voteCount": 953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.4044711354288
      }
    },
    {
      "id": "da87fa7773d762384d189aa0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1127.472913986419,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.7840792770266,
        1153.1617486958107
      ],
      "voteCount": 721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.78792212257034
      }
    },
    {
      "id": "9958a3ed99bc0969c62e1d35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1175.3594416805254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.0080760721446,
        1191.710807288906
      ],
      "voteCount": 1351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.60042258389346
      }
    },
    {
      "id": "130aef82bfdf5848a1e3074f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1144.0930419665647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.413967729139,
        1163.7721162039902
      ],
      "voteCount": 1070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.81221247404558
      }
    },
    {
      "id": "e40f08cb60faf2df46d56e91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1223.8549229525938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.1634851691038,
        1233.5463607360837
      ],
      "voteCount": 4157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.45007761251663
      }
    },
    {
      "id": "c781159f1b3ef2b3e336ca0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1008.7853277868477,
      "unit": "Arena rating",
      "confidenceInterval": [
        995.0504844440093,
        1022.5201711296861
      ],
      "voteCount": 5442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.107885951052516
      }
    },
    {
      "id": "e66bcf04a1aed1a75f54be8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1174.5621706535003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.638669054917,
        1199.4856722520835
      ],
      "voteCount": 499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.70443597839562
      }
    },
    {
      "id": "da2d714b2605322b57203f4a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1110.4030620391986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1069.4281914195458,
        1151.3779326588515
      ],
      "voteCount": 232,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 437.0579252998259
      }
    },
    {
      "id": "01fffedeb7ec0f767d860e25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1208.085390372602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.8210379183674,
        1223.3497428268365
      ],
      "voteCount": 1377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.65415945419221
      }
    },
    {
      "id": "d149579ac320769efb2cf4d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1167.1159418974314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.5168851948856,
        1179.7149985999772
      ],
      "voteCount": 2216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.321861616437026
      }
    },
    {
      "id": "f9676c6100e264722c974bac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1146.9091133312595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.8988795015312,
        1166.9193471609876
      ],
      "voteCount": 1012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.23369782421534
      }
    },
    {
      "id": "2822e7c5877f81e366b7ae28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1141.1569479439622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.9375930511565,
        1159.3763028367678
      ],
      "voteCount": 1149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.41115477323292
      }
    },
    {
      "id": "0b5f3ee61bbc0f9eae110c4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1189.1048972447707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.8223558013399,
        1217.3874386882012
      ],
      "voteCount": 506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.22874533764653
      }
    },
    {
      "id": "29e8cb45a2d305c4feaa5fd1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1185.452152157486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.8786860182358,
        1203.0256182967357
      ],
      "voteCount": 1355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.39308152509656
      }
    },
    {
      "id": "cbce64647bad7627ebd46951",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1173.3763388044035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.4309005000766,
        1190.3217771087302
      ],
      "voteCount": 980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.74969607349858
      }
    },
    {
      "id": "96f71edb82c5f5e6ccd322d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1202.8713998961884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.0086422134416,
        1233.7341575789355
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 247.955231656459
      }
    },
    {
      "id": "4d39ad939434e2ef8f58dccc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1173.840361593717,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.5930596848107,
        1187.0876635026234
      ],
      "voteCount": 2165,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.68342810818004
      }
    },
    {
      "id": "b7328308213b57aa38f69f84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1141.3721931683854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.2761368728184,
        1155.4682494639528
      ],
      "voteCount": 2118,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.72482964476932
      }
    },
    {
      "id": "45b66cd6b21f84f37e35996e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1144.5245145411332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.4989910732397,
        1155.5500380090266
      ],
      "voteCount": 3171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.644792620502873
      }
    },
    {
      "id": "2e04f9e9ea8abe9fd9f180d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1157.4128528319857,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.9939883409959,
        1175.8317173229755
      ],
      "voteCount": 1046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.31399345213997
      }
    },
    {
      "id": "98726ba5a9dd08f7b418d19d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1164.681949701943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.8446825212789,
        1180.5192168826075
      ],
      "voteCount": 1136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.29265142725767
      }
    },
    {
      "id": "4d35d6da7c10a38fdd7fe7fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1148.2690753018353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.1159730098266,
        1165.422177593844
      ],
      "voteCount": 1299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.59301634449004
      }
    },
    {
      "id": "25e532c82a07ea540fe2d91d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1165.9936230525254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.2943111409484,
        1173.6929349641025
      ],
      "voteCount": 7936,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.43148232968446
      }
    },
    {
      "id": "a13ed63e6befe4b2527586f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.2-3b-instruct",
      "organization": "meta",
      "license": "Llama 3.2",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1004.684547525881,
      "unit": "Arena rating",
      "confidenceInterval": [
        980.934333182445,
        1028.4347618693168
      ],
      "voteCount": 933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.83814344708452
      }
    },
    {
      "id": "14c6e979a6fc831b2d3d3083",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1291.036764454661,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.201965448978,
        1301.871563460344
      ],
      "voteCount": 3408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.559450191460922
      }
    },
    {
      "id": "7e3132ae615bd792907cf811",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1345.0563921234527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.549512912493,
        1351.5632713344123
      ],
      "voteCount": 8748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.021718321678902
      }
    },
    {
      "id": "461f0a757cd331e156c291fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1286.3356683002435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.3690170482025,
        1293.3023195522846
      ],
      "voteCount": 8069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.634322514694047
      }
    },
    {
      "id": "9ff1034e526a280828fc3a6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1343.7210283458007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.4889822777584,
        1347.9530744138428
      ],
      "voteCount": 30161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.662346977546309
      }
    },
    {
      "id": "b540ffcc701bf17d0450d3e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1262.5726050251246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.560715365655,
        1267.5844946845946
      ],
      "voteCount": 36933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.538931986822976
      }
    },
    {
      "id": "4d3e8713e9ebcb693525c4da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1294.1341966295854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.0232180020002,
        1305.245175257171
      ],
      "voteCount": 2894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.13723010581461
      }
    },
    {
      "id": "fdc69803282b42f0610b1686",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1329.0066684649728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.3427189432225,
        1354.6706179867228
      ],
      "voteCount": 537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.45525588009085
      }
    },
    {
      "id": "d7c061c3bb5f79ac5c8d53dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1290.9584351673038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.828507819529,
        1308.0883625150786
      ],
      "voteCount": 1183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.3861919745961
      }
    },
    {
      "id": "b7dbd8a3b6de2d6c9375ddbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1337.525930549722,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.4338100815326,
        1343.6180510179115
      ],
      "voteCount": 10093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.661416022214881
      }
    },
    {
      "id": "1a6a868e8fd9c75e051585b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1320.4234770019898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.4714410317656,
        1325.3755129722138
      ],
      "voteCount": 17022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.3836842707484225
      }
    },
    {
      "id": "67e927ccdd642410bae7a9fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1304.6007920214738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.0982648873069,
        1312.1033191556405
      ],
      "voteCount": 6671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.652744185537934
      }
    },
    {
      "id": "c755a07b9bf63c3e8bc158a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1285.226193676388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.9599084797796,
        1291.4924788729963
      ],
      "voteCount": 9756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.221723568583661
      }
    },
    {
      "id": "31eaa9649f5d51907be2d0af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1342.6699551944685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.006885003861,
        1353.333025385076
      ],
      "voteCount": 3174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.598408104054126
      }
    },
    {
      "id": "6f9f3cfa24e2377e7d91598b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1340.299798404943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.8298355237703,
        1346.7697612861157
      ],
      "voteCount": 9380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.897011171445625
      }
    },
    {
      "id": "e5e526317352a9044da462cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1301.8196227321769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.879421041113,
        1309.7598244232408
      ],
      "voteCount": 5232,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.412203237774882
      }
    },
    {
      "id": "e452d7ea81b09f2ad8f0ff4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1340.7193238518253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.9325906850795,
        1352.5060570185715
      ],
      "voteCount": 2748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.16518755730587
      }
    },
    {
      "id": "c5cf411358bd180744296ee4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1338.7253694684632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.4075363048378,
        1344.043202632089
      ],
      "voteCount": 14966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.361617259519701
      }
    },
    {
      "id": "de40f60e937368df81772d83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1291.347946179617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.7782041536764,
        1296.9176882055576
      ],
      "voteCount": 13835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.075584740987724
      }
    },
    {
      "id": "8b468cb544dd3463618433cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1291.750540439351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.7652906206572,
        1296.7357902580447
      ],
      "voteCount": 18789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.4696035841651
      }
    },
    {
      "id": "8144a5a9a562eaf6c65968c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1213.0760960878877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.466376896717,
        1231.6858152790583
      ],
      "voteCount": 1121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.15367977096795
      }
    },
    {
      "id": "61d856910eb8b6e058b804f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1212.5786202462523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.7089188146592,
        1234.4483216778451
      ],
      "voteCount": 846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.50578361805599
      }
    },
    {
      "id": "0b7cb53394391b6b4563234d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1311.6807188111925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.0296354760264,
        1318.3318021463583
      ],
      "voteCount": 8307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.51565371285932
      }
    },
    {
      "id": "2329d7653ed588b1bfb65c73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1295.912635994524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.2464993439712,
        1303.578772645077
      ],
      "voteCount": 5779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.298784625350011
      }
    },
    {
      "id": "dcea32531bbf204fe8312f31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1316.7924984541073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.209566093122,
        1323.3754308150924
      ],
      "voteCount": 9141,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.280870234989541
      }
    },
    {
      "id": "3c6fdc99704f98175a1fab66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1318.1968447565064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.7369615658217,
        1321.6567279471906
      ],
      "voteCount": 54745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.1162098181799918
      }
    },
    {
      "id": "ac7656e8e5f5bb9241d8f698",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1292.6109522282613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.5149231341097,
        1300.7069813224127
      ],
      "voteCount": 5439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.062707203901287
      }
    },
    {
      "id": "965bc25e1a86014d5616f92a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-70b-instruct",
      "organization": "meta",
      "license": "Llama-3.3",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1300.279105376753,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.6593125701283,
        1324.8988981833777
      ],
      "voteCount": 590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.78750368892392
      }
    },
    {
      "id": "3f03f62a5bf8cd3e29810c0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1306.888253433812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.0524715493993,
        1345.7240353182247
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 392.61593706245975
      }
    },
    {
      "id": "8eef55c161724690fd464b77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1362.9601070862082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.6755794158473,
        1394.2446347565692
      ],
      "voteCount": 286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.7786445829265
      }
    },
    {
      "id": "fc0e316529e8c0341e6ce2d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1298.190447758213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.9628019664758,
        1325.4180935499498
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.98519910369296
      }
    },
    {
      "id": "cecc727dd4780442e08971c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1374.5386481106427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.8895376534292,
        1390.1877585678562
      ],
      "voteCount": 1250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.75043168048694
      }
    },
    {
      "id": "a2a4f4f78a31916c8ba971dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1278.8704191196648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.7432150166744,
        1297.9976232226554
      ],
      "voteCount": 1430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.23724029699454
      }
    },
    {
      "id": "eea09c7d07a62c82b40b6b6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1387.394305000104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.3517282098646,
        1416.4368817903435
      ],
      "voteCount": 344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 219.57056055713284
      }
    },
    {
      "id": "c5c15bbc04b2f1fc8c356cfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1360.73109894288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.5572638016615,
        1384.9049340840984
      ],
      "voteCount": 510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.12301698686775
      }
    },
    {
      "id": "e9239659e27ee4f274090500",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1319.4495420911467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.4959585900253,
        1354.4031255922682
      ],
      "voteCount": 241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 318.0440183266382
      }
    },
    {
      "id": "7e01fe754f15445744ae89ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1305.7019820401424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.8738126012054,
        1332.5301514790797
      ],
      "voteCount": 410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.3638919586969
      }
    },
    {
      "id": "8eae2ab96c258efc92e92024",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1360.9087191152084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.6309758864388,
        1389.1864623439783
      ],
      "voteCount": 395,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.15809811746175
      }
    },
    {
      "id": "21b95a5d332190ef90966671",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1366.6091534745428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.493777624402,
        1403.7245293246838
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 358.601039031394
      }
    },
    {
      "id": "8e68b510b830ad2f492e191d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1348.6690387419699,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.2732011469147,
        1373.064876337025
      ],
      "voteCount": 493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.9299158846015
      }
    },
    {
      "id": "abbd71dbd41c85dbb8090971",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1311.153371104326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.5316821852994,
        1333.7750600233526
      ],
      "voteCount": 614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.21522719245223
      }
    },
    {
      "id": "c770f1bcbc74b61467a9cc8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1325.3377944631852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8554372568587,
        1344.8201516695115
      ],
      "voteCount": 803,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.80679711316353
      }
    },
    {
      "id": "ef52f5faafb61a97c1b28101",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1337.572247516573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.3877527530763,
        1367.7567422800696
      ],
      "voteCount": 317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.1764911859527
      }
    },
    {
      "id": "bf3d8392517b93946f100efc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1331.3945637735626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.692506668929,
        1363.096620878196
      ],
      "voteCount": 301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 261.62467738853655
      }
    },
    {
      "id": "fade8b4f78f63b0cb15d3935",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1327.8249448437023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.672902496005,
        1339.9769871913995
      ],
      "voteCount": 2218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.44168065129614
      }
    },
    {
      "id": "d3c93a5be371593d87d3b2a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-3.3-nemotron-49b-super-v1",
      "organization": "nvidia",
      "license": "Nvidia",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1288.3554353183224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.3074950320124,
        1323.4033756046324
      ],
      "voteCount": 263,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 319.7634481191193
      }
    },
    {
      "id": "adc2557e92dee1ab89b4c1cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1330.4763598333516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.0701621253615,
        1343.8825575413414
      ],
      "voteCount": 2145,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.78590748325123
      }
    },
    {
      "id": "c03f91aa2ce62d6a8f133091",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1373.0000432562226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.5291063256343,
        1380.4709801868112
      ],
      "voteCount": 6997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.529610032561665
      }
    },
    {
      "id": "28662f35166cb67dfa417daa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1307.2079853349783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.6813557534986,
        1315.7346149164582
      ],
      "voteCount": 5185,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.925990206665972
      }
    },
    {
      "id": "1023da2c5f22e4ba18c60a81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1340.2878989426736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.0703073587138,
        1345.5054905266336
      ],
      "voteCount": 20436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.0866988838606755
      }
    },
    {
      "id": "32049eec5ac3138257cd3a0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1278.881605667728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.8808677944842,
        1284.882343540972
      ],
      "voteCount": 28534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.373744898527248
      }
    },
    {
      "id": "65701194c9e26351d65f6e32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1324.5400254495125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.1242546590624,
        1337.9557962399626
      ],
      "voteCount": 1993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.852748995334814
      }
    },
    {
      "id": "eff2248ecd2d1bcad229d172",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1298.1446408685515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.8364759907886,
        1324.4528057463144
      ],
      "voteCount": 563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.17101615331046
      }
    },
    {
      "id": "7dca1482d447d23d0036e7ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1334.4686837092681,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.1544581709495,
        1353.7829092475868
      ],
      "voteCount": 990,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.10876142559576
      }
    },
    {
      "id": "b28f26a51fc64a5ead9a95e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1351.2440253888976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.300353624893,
        1358.1876971529023
      ],
      "voteCount": 8707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.551111391980108
      }
    },
    {
      "id": "1819bb10d628d99eb521bbfa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1338.4812644868657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.772152959286,
        1344.190376014446
      ],
      "voteCount": 15994,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.48478558686143
      }
    },
    {
      "id": "2806c3cdc0c560f0c56253a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1318.6496575888577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.553234950364,
        1326.7460802273517
      ],
      "voteCount": 6184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.064366065304135
      }
    },
    {
      "id": "ff2018a3cec806ac98faa7e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1295.2607823812896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.7035625921053,
        1302.8180021704738
      ],
      "voteCount": 6974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.86715688174921
      }
    },
    {
      "id": "e748cac34b49e1d51db9c6c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1341.0378107502634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.9963744161364,
        1353.0792470843903
      ],
      "voteCount": 2625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.74508481198041
      }
    },
    {
      "id": "fe01e555d973f7b22cf6c704",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1342.3854940831443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.52627306785,
        1350.2447150984385
      ],
      "voteCount": 6765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.079140204366617
      }
    },
    {
      "id": "455c408bfe481c13bd27c9ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1320.1679163236283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.7131621086087,
        1331.622670538648
      ],
      "voteCount": 2593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.15665773108631
      }
    },
    {
      "id": "488b71119cfaf5aeebf9f78a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1344.8549672184358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.6752017053302,
        1358.0347327315412
      ],
      "voteCount": 2317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.21881584274225
      }
    },
    {
      "id": "a26ad35d8d0b191ed571c158",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1359.1413732557508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.0234238866262,
        1365.259322624875
      ],
      "voteCount": 12591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.743513136607351
      }
    },
    {
      "id": "36848bdbe5ff2e14166f08a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1311.7605138506588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.8707173960022,
        1318.6503103053153
      ],
      "voteCount": 8773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.357101143679735
      }
    },
    {
      "id": "bdf9b5051fab52eacb616794",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1313.6548494543322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.2130731204759,
        1320.0966257881882
      ],
      "voteCount": 10494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.80227181191836
      }
    },
    {
      "id": "04470fb16f78aa1af20a5240",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1253.916693864709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.0693291131493,
        1275.7640586162686
      ],
      "voteCount": 862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.25158484490734
      }
    },
    {
      "id": "67f9a5552333806da5ec243e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1263.199162275775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.8237147751856,
        1285.5746097763645
      ],
      "voteCount": 767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.33086497102386
      }
    },
    {
      "id": "a14ee267870e5279b5e10b68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1334.5669734708508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.0910629323303,
        1342.0428840093714
      ],
      "voteCount": 7067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.548961993002626
      }
    },
    {
      "id": "597bec6ec6b37b7b3569309d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1318.657948609019,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.8657905672376,
        1329.4501066508005
      ],
      "voteCount": 2839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.319386627640824
      }
    },
    {
      "id": "d171559ddec3d882f3f9f8f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1324.3287527897337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.5544501176312,
        1332.1030554618364
      ],
      "voteCount": 6837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.733549377613835
      }
    },
    {
      "id": "f7d7c4b05dd1ee951a314ac9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1327.0306102503923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.78360700302,
        1331.2776134977646
      ],
      "voteCount": 39987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.695361170090926
      }
    },
    {
      "id": "a79cc46d815f25f5a2d1e7fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1327.0723229142777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.8903252567497,
        1338.2543205718057
      ],
      "voteCount": 2655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.54937185305283
      }
    },
    {
      "id": "8d7695cf148a5d9abf219b8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-maverick-17b-128e-instruct",
      "organization": "meta",
      "license": "Llama 4",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1317.572760194475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.0066792408738,
        1340.1388411480762
      ],
      "voteCount": 746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.5611007102948
      }
    },
    {
      "id": "5ac05b0f50dc6afb7c39fd5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1314.5202493557208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.0303214937733,
        1330.0101772176686
      ],
      "voteCount": 1622,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.46009038956435
      }
    },
    {
      "id": "874b91de8381637baaf0aac6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1362.1188911636684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.612575506302,
        1370.6252068210347
      ],
      "voteCount": 5255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.83591870696729
      }
    },
    {
      "id": "f587f079a1af63e5ccf10265",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1289.8975624478612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.8730031629543,
        1299.9221217327686
      ],
      "voteCount": 3786,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.15979854196627
      }
    },
    {
      "id": "250a30d0812f477f17424797",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1341.334715294769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.5018790200495,
        1347.1675515694885
      ],
      "voteCount": 14442,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.856525761621162
      }
    },
    {
      "id": "e03a0cd7f3c8d6bf18619cca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1270.1094549699746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.4610522756786,
        1276.7578576642704
      ],
      "voteCount": 21761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.506373086028207
      }
    },
    {
      "id": "fe770a4e85f1aa98a2880755",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1308.1635859716112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.495927377223,
        1323.8312445659994
      ],
      "voteCount": 1503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.901641873111814
      }
    },
    {
      "id": "69d6f0bc03fb0fa009966eb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1335.7842637297886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.2297453863582,
        1366.3387820732187
      ],
      "voteCount": 398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 243.02709849960718
      }
    },
    {
      "id": "f3626dafd58e9792d03987f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1310.6757348772617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.6606370418986,
        1332.6908327126248
      ],
      "voteCount": 766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.16679113926757
      }
    },
    {
      "id": "67bf04618861a4ca30a7ac61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1350.280271630664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.5793606564494,
        1357.9811826048785
      ],
      "voteCount": 6656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.437892894570385
      }
    },
    {
      "id": "9183670d814e9f30b01597d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1329.778142524257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.6296380834506,
        1335.926646965063
      ],
      "voteCount": 12994,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.841080855783423
      }
    },
    {
      "id": "e5e6c08d5f5248e546dc0bd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1317.8895797751466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.9618650274422,
        1326.8172945228507
      ],
      "voteCount": 4966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.74839125881199
      }
    },
    {
      "id": "27145ca8187cd42265fe7f8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1290.172249316088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.6455185990858,
        1298.6989800330903
      ],
      "voteCount": 5319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.92643917685745
      }
    },
    {
      "id": "e7afabd2bf8ef517e4ff243f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1342.793595210775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.0626024453834,
        1356.524587976167
      ],
      "voteCount": 1994,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.08035491818017
      }
    },
    {
      "id": "a3563d043cab63f5067817cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1335.2256766142805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.2994762284827,
        1344.151877000078
      ],
      "voteCount": 5024,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.741352971998335
      }
    },
    {
      "id": "d38e4c6101a2c3ab647990e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1313.64267869166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.9851953627397,
        1327.3001620205805
      ],
      "voteCount": 1817,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.556254169616935
      }
    },
    {
      "id": "01c9ea169ff723f831ab4b58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1340.9546868731063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.1721643881604,
        1355.737209358052
      ],
      "voteCount": 1832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.8854128647003
      }
    },
    {
      "id": "d2e1ea0ffec23d4019b6b4f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1350.1610783968677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.4054449585963,
        1356.9167118351388
      ],
      "voteCount": 9733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.880534266417694
      }
    },
    {
      "id": "b3bd94806169dffccedaa9f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1306.6757875010665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.9810315931488,
        1314.370543408984
      ],
      "voteCount": 6739,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.413224831012087
      }
    },
    {
      "id": "5042224af72dc629ac21a8fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1300.301130089561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.0148291847468,
        1307.5874309943747
      ],
      "voteCount": 7475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.820317580782968
      }
    },
    {
      "id": "0c7c40226ad744a00f7ecb4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1261.0259681324633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.0748356842741,
        1283.9771005806524
      ],
      "voteCount": 715,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.12355259847243
      }
    },
    {
      "id": "5822244efc3739e6be146e50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1273.6226045716903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.2927784034964,
        1298.9524307398842
      ],
      "voteCount": 637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.01990667050603
      }
    },
    {
      "id": "f5a7b96d870a29768e80990b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1327.013304292027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.6944047598413,
        1335.3322038242127
      ],
      "voteCount": 5759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.015054347008437
      }
    },
    {
      "id": "ecb4caa4bd2c474e73b4cd94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1309.2238630907143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.9980580199226,
        1322.449668161506
      ],
      "voteCount": 1944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.53528436339541
      }
    },
    {
      "id": "465d0a827f074d9b942f4645",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1320.65086204591,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.0177350644444,
        1329.2839890273751
      ],
      "voteCount": 5347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.40171298377662
      }
    },
    {
      "id": "3bfb71b423074b28209c1e02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1322.6827244460592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.9805129519987,
        1327.3849359401197
      ],
      "voteCount": 30299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.755832345712735
      }
    },
    {
      "id": "2703658f3812bfd5eb3ff941",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1309.6187281493715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.2289152277676,
        1323.0085410709753
      ],
      "voteCount": 1915,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.67161576995688
      }
    },
    {
      "id": "989163e415cd4f4870522394",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama-4-scout-17b-16e-instruct",
      "organization": "meta",
      "license": "Llama",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1302.7308207237559,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.1816189004799,
        1328.2800225470319
      ],
      "voteCount": 638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.9254747415293
      }
    },
    {
      "id": "1b8f44591da8d2d52b6c4357",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1143.914651434682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.1533348277217,
        1171.6759680416421
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.62448557306843
      }
    },
    {
      "id": "dd4fd28dc2c188efd42e7a28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1119.672319844475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1094.2700156678657,
        1145.0746240210842
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.9770856854801
      }
    },
    {
      "id": "a53f6dc8d2ddd626a3f567d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1178.0591999297455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.2871630928028,
        1191.8312367666883
      ],
      "voteCount": 2751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.37421107219789
      }
    },
    {
      "id": "45780a25fb7b643149d7b34c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1008.8452728071306,
      "unit": "Arena rating",
      "confidenceInterval": [
        991.1680929557308,
        1026.5224526585307
      ],
      "voteCount": 2540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.34479688169004
      }
    },
    {
      "id": "26e75421de73fcc442a6737e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1154.9076956185486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.1589146046704,
        1177.6564766324266
      ],
      "voteCount": 645,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.71627883385014
      }
    },
    {
      "id": "ade97c51e4b8a1c66c2b737f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1144.5081081265546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1123.9824619050457,
        1165.0337543480637
      ],
      "voteCount": 787,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.67243760130107
      }
    },
    {
      "id": "5099d818356547d0f706a4fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1173.723107035162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.0406248138738,
        1209.4055892564502
      ],
      "voteCount": 282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.4468791422525
      }
    },
    {
      "id": "77aadc4d0e1401283f3a947f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1109.5619884908906,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.895318828279,
        1134.2286581535018
      ],
      "voteCount": 591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.38894041156303
      }
    },
    {
      "id": "979681c601012d321acdbba7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1179.9056200108835,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.7648940077152,
        1204.0463460140518
      ],
      "voteCount": 642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.70659875894228
      }
    },
    {
      "id": "32b43c0c4032f706c5a7983c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1114.1907895231384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.4040117591767,
        1143.9775672871
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.96749723828142
      }
    },
    {
      "id": "62df8f49ba1a02c0c6779edc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1157.0566485734225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.5300046371012,
        1177.5832925097438
      ],
      "voteCount": 877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.68309982101476
      }
    },
    {
      "id": "18b32a6312f02abeabc109a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1127.1449267868038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.2994385374848,
        1148.9904150361226
      ],
      "voteCount": 836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.23024145938935
      }
    },
    {
      "id": "8b2cbbf6f2b86926dc5999bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1122.3889539765537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.0083591845664,
        1140.7695487685412
      ],
      "voteCount": 1076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.94738683315785
      }
    },
    {
      "id": "8f8d91f64962c58433d381f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1054.8856889079896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1011.5610331221071,
        1098.210344693872
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 488.6231732730193
      }
    },
    {
      "id": "a9146de01381c10112234def",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1113.9709422740698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.363086695658,
        1140.5787978524818
      ],
      "voteCount": 440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.2992497193289
      }
    },
    {
      "id": "002520307be80634184cde84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1110.62401958273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1082.611760119314,
        1138.636279046146
      ],
      "voteCount": 451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 204.2678880269629
      }
    },
    {
      "id": "888d210a133b1eceeb2c20ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "llama2-70b-steerlm-chat",
      "organization": "nvidia",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1154.0428518111921,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.438779954242,
        1166.646923668142
      ],
      "voteCount": 3585,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.35476515311353
      }
    },
    {
      "id": "771e549589109c5c1f81ed6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1482.905429676131,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.8283330276886,
        1499.9825263245734
      ],
      "voteCount": 1300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.91575064380086
      }
    },
    {
      "id": "6db645d60db0ccd2497265df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1502.5671781588367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.573360287955,
        1510.5609960297186
      ],
      "voteCount": 6475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.634598243924927
      }
    },
    {
      "id": "d139adc985f44e4be4fbe705",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1388.8727699145752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.3207325927376,
        1399.4248072364128
      ],
      "voteCount": 3503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.98521026481648
      }
    },
    {
      "id": "d70f148b2a1e40f47b051065",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1460.9108903578745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.605532795517,
        1467.2162479202318
      ],
      "voteCount": 11383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.349592653447322
      }
    },
    {
      "id": "2d05ee3af589bddc45a76a0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1430.6024678547626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.0116355146058,
        1437.1933001949192
      ],
      "voteCount": 17418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.307962147621561
      }
    },
    {
      "id": "698afec4d410b6da93e4fec7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1466.5785470506842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.3193921300817,
        1479.8377019712866
      ],
      "voteCount": 2135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.76521509523014
      }
    },
    {
      "id": "59a30fb23b31f45892c3cc38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1441.5016669825782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.4651531667173,
        1465.5381807984388
      ],
      "voteCount": 753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.39963289666835
      }
    },
    {
      "id": "9deab1b54e974f10a8796617",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1390.6536538383168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.6873517751692,
        1420.6199559014642
      ],
      "voteCount": 380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.75995975860562
      }
    },
    {
      "id": "575007a5b20288fdbf67f03e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1476.297259610466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.7529949857033,
        1483.841524235229
      ],
      "voteCount": 7410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.816227736670937
      }
    },
    {
      "id": "610ca9071a912850f35dd4b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1459.0800393161344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.1539884734784,
        1465.0060901587904
      ],
      "voteCount": 14738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.141859962304038
      }
    },
    {
      "id": "407d766cf48f37ed552e032d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1432.8046946655738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.543072477051,
        1442.0663168540966
      ],
      "voteCount": 4580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.32944554835537
      }
    },
    {
      "id": "f6d7715647eee1d9e1b3bed6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1397.1836657416436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.7460498782864,
        1406.6212816050008
      ],
      "voteCount": 4468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.186137699687194
      }
    },
    {
      "id": "0466640e26a7f4324b9a7779",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1424.9120973301951,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.0426046945813,
        1439.7815899658092
      ],
      "voteCount": 1746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.5567308048416
      }
    },
    {
      "id": "4fd9c11a6b78e2c0df808639",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1455.5103786378693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.535157004961,
        1465.4856002707777
      ],
      "voteCount": 3853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.90293200322816
      }
    },
    {
      "id": "bb005beccbbb313e9948360f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1440.9357667963504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.3203169381736,
        1457.5512166545275
      ],
      "voteCount": 1338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.86675345896609
      }
    },
    {
      "id": "113f127441767ef7b6a16537",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1463.4710702042285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.928581851392,
        1479.013558557065
      ],
      "voteCount": 1603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.88468924792688
      }
    },
    {
      "id": "102da431daae43ecd340e5d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1488.5548191491043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.6376109448079,
        1495.472027353401
      ],
      "voteCount": 9141,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.455624692324886
      }
    },
    {
      "id": "9f9f8e44fa31c2bf48d34a0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1393.8678777174082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3284787984007,
        1402.4072766364159
      ],
      "voteCount": 5376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.982719144382514
      }
    },
    {
      "id": "f365d8d1756b3997e43574b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1416.319140374509,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.890488168133,
        1423.747792580885
      ],
      "voteCount": 7470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.365603323927902
      }
    },
    {
      "id": "86e94ea52a00fca02f0e1b00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1405.3147607759242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.8219814896938,
        1449.8075400621549
      ],
      "voteCount": 189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 515.3269893065061
      }
    },
    {
      "id": "416e12dfce480afb55f90ac5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1385.3999044431478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.2795907946984,
        1415.5202180915971
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.16894951304758
      }
    },
    {
      "id": "235fc861f44364d55289e83b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1435.167433077431,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.8855185917973,
        1442.4493475630647
      ],
      "voteCount": 8548,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.80368267659852
      }
    },
    {
      "id": "c7560d1b4a39874de851b33f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1440.0486656595997,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.8659988731772,
        1455.2313324460222
      ],
      "voteCount": 1513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.006727003228555
      }
    },
    {
      "id": "e6822b64cbbf9e263ca7b5bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1428.3596241558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.6815625909771,
        1438.037685720623
      ],
      "voteCount": 4202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.382631709579588
      }
    },
    {
      "id": "aaf360eee597a98c2358c737",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1435.8247592826701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.9140063677582,
        1440.735512197582
      ],
      "voteCount": 23731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.27769170956699
      }
    },
    {
      "id": "76e8234b584c35fa6c2a0e2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1404.0557845039195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.5008186673283,
        1416.6107503405105
      ],
      "voteCount": 2496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.03315290244017
      }
    },
    {
      "id": "95cd3a558ee94df1a5acbd34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat-2602-exp",
      "organization": "meituan",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1417.5326276372882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.5845429682354,
        1441.480712306341
      ],
      "voteCount": 686,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.29504286928565
      }
    },
    {
      "id": "96a00ec255bc2c80103dabba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1420.8093205239936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.187399824228,
        1443.4312412237593
      ],
      "voteCount": 682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.2179570400851
      }
    },
    {
      "id": "eb44adf06aafde142ab00006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1474.4152452174983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.8389669255034,
        1486.9915235094932
      ],
      "voteCount": 2233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.17258131876104
      }
    },
    {
      "id": "2cdaf2627dc1909c7089227a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1330.3839778493125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.5078749974996,
        1346.2600807011254
      ],
      "voteCount": 1382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.61326140046943
      }
    },
    {
      "id": "d4698919bdbbc74ff8be2730",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1423.2191680673611,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.9238209404552,
        1431.514515194267
      ],
      "voteCount": 5378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.91319057884128
      }
    },
    {
      "id": "fd788d8037ea2d5e10a6118e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1381.7210659899786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.9589333219997,
        1390.4831986579575
      ],
      "voteCount": 8082,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.985888818506144
      }
    },
    {
      "id": "2b6e838325fdb4d25eec31ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1423.243420668394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.2308675073623,
        1449.2559738294256
      ],
      "voteCount": 515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.144780808356
      }
    },
    {
      "id": "e61c600e4653e99c32d2ea58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1433.966447897521,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.295032823748,
        1480.637862971294
      ],
      "voteCount": 164,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 567.0296329233636
      }
    },
    {
      "id": "0391724f6f34eec94fa68feb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1383.3412243356695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.9483653072211,
        1419.7340833641179
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 344.7753184622705
      }
    },
    {
      "id": "61694334f694afd320307257",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1440.0105984569477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.8765589882328,
        1451.1446379256624
      ],
      "voteCount": 2860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.27077021445211
      }
    },
    {
      "id": "388a0bd63e1d9e328d54a617",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1426.615256506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.4088344670126,
        1434.821678544987
      ],
      "voteCount": 5586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.531194742784134
      }
    },
    {
      "id": "346ba5229d502ccdabaff956",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1416.679217947437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.0126400579934,
        1429.345795836881
      ],
      "voteCount": 2173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.76595478911196
      }
    },
    {
      "id": "dcef375b92ed159ccc51ce05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1340.5745987517296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.508490885742,
        1353.6407066177171
      ],
      "voteCount": 1963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.44227642007424
      }
    },
    {
      "id": "bcd7d9f20c24a8753c3646e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1392.3576665755288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.1461268539854,
        1413.5692062970722
      ],
      "voteCount": 778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.12462331623146
      }
    },
    {
      "id": "1742d9455d417f9d4ce7cf7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1406.1917347196331,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.8886299546434,
        1420.494839484623
      ],
      "voteCount": 1706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.25549887875881
      }
    },
    {
      "id": "e78f252881c50c1b08ce7e5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1422.5266334156058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.1922172684845,
        1446.8610495627272
      ],
      "voteCount": 545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.15076325464332
      }
    },
    {
      "id": "f25805b27d99e08af43897ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1442.494090998775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.0199956571864,
        1465.9681863403637
      ],
      "voteCount": 668,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.4437222488364
      }
    },
    {
      "id": "3ea84f6ccca49f3ae3d7893c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1452.7121566887172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.1510327082008,
        1462.2732806692338
      ],
      "voteCount": 3912,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.796972982855333
      }
    },
    {
      "id": "6b9ff49ec91151a586fcb383",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1355.5196890392647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.747064012019,
        1367.2923140665102
      ],
      "voteCount": 2506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.0786634716773
      }
    },
    {
      "id": "2ef1baad8b8b5257d5b9760a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1389.4644007605698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.7014729998514,
        1400.227328521288
      ],
      "voteCount": 2955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.155370495813532
      }
    },
    {
      "id": "dc608e891b2498db4508beae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1286.3201140354017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.4498864137317,
        1330.190341657072
      ],
      "voteCount": 163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 501.0067688892676
      }
    },
    {
      "id": "4d9e20b2bb899a0f3933a6ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1325.8723020100938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.4542719768797,
        1361.2903320433077
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 326.5522058120042
      }
    },
    {
      "id": "fd6f3527039a94af7e804ff7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1386.0215147875824,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.8965004884367,
        1398.1465290867282
      ],
      "voteCount": 2343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.27087016070766
      }
    },
    {
      "id": "4db7d926ccd1733439a498fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1417.260544685982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.530426852919,
        1438.9906625190451
      ],
      "voteCount": 689,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.92153660350398
      }
    },
    {
      "id": "d243cc1dc6482660aa98becc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1392.6529084541742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.5686772581391,
        1405.7371396502092
      ],
      "voteCount": 2026,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.565649140645895
      }
    },
    {
      "id": "26f91fd83c73d555fa42c5ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1401.2439737227871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.8788187691453,
        1407.609128676429
      ],
      "voteCount": 11405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.546825952061301
      }
    },
    {
      "id": "e3ff65373be158b7ef8da778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1372.2680440604395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.795550925522,
        1393.7405371953564
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.02418428781961
      }
    },
    {
      "id": "60784861e1930a24ee2799f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "longcat-flash-chat",
      "organization": "meituan",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1409.0872479596471,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.2490717220362,
        1440.9254241972583
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.8761765911681
      }
    },
    {
      "id": "83f1828fbcabdc7dbe839bc7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1285.2964560340984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.5491605810826,
        1313.0437514871142
      ],
      "voteCount": 556,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.42188160638233
      }
    },
    {
      "id": "14bda3f8081deff834cc1b76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1386.3455791407932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9894060774432,
        1398.7017522041433
      ],
      "voteCount": 2250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.744019107791075
      }
    },
    {
      "id": "55908dcf0d3f5277e276d82c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1282.0213212896756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.423948848102,
        1298.618693731249
      ],
      "voteCount": 1352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.71045814166156
      }
    },
    {
      "id": "13392cedfd7e396ab412dffa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1327.2023836285903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.3422155453673,
        1336.0625517118133
      ],
      "voteCount": 5002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.435616292452305
      }
    },
    {
      "id": "fcf613d001602dad98f8239b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1248.744985801947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.7126495388202,
        1257.7773220650738
      ],
      "voteCount": 8762,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.23753037015619
      }
    },
    {
      "id": "1c8f1ddc79a0ac1ff1371cf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1287.8285060321668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.8583047004477,
        1314.7987073638858
      ],
      "voteCount": 553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.35300203010488
      }
    },
    {
      "id": "9d2418b61c0ddf93b8adeb40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1330.9359675076817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.769351313756,
        1380.1025837016077
      ],
      "voteCount": 163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 629.2807656660003
      }
    },
    {
      "id": "e91401d5a014c17baca44116",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1304.314271771457,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.5649118616413,
        1338.0636316812725
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 296.5069645381381
      }
    },
    {
      "id": "fbf37544583a9366d7497a53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1354.285906060817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.8070543227705,
        1365.764757798864
      ],
      "voteCount": 2781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.30052055074494
      }
    },
    {
      "id": "b8ff5e81b533805ca8995f44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1332.0127708825225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.7162289682324,
        1340.309312796813
      ],
      "voteCount": 5661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.918351061000557
      }
    },
    {
      "id": "88f6cd71f806847646cbe3ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1293.8148823136567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.4162259406703,
        1307.213538686643
      ],
      "voteCount": 2234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.733285707570616
      }
    },
    {
      "id": "8fe69f08c7fedaee1b577f4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1288.0085882591388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.4311350270318,
        1301.5860414912459
      ],
      "voteCount": 1974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.98886175141734
      }
    },
    {
      "id": "1416b5ffc3e0183d1699ee07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1305.4477189338484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.102171073286,
        1327.7932667944106
      ],
      "voteCount": 853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.98278323297464
      }
    },
    {
      "id": "2ade3d1271edf117d5f13fb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1311.085891735171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.2853559022785,
        1325.8864275680633
      ],
      "voteCount": 1951,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.02413358192653
      }
    },
    {
      "id": "658392abe5d71ff1422fcdb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1291.722604754786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.5830528519878,
        1317.8621566575841
      ],
      "voteCount": 582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.8689309379643
      }
    },
    {
      "id": "5787d5d9bd74b8d242d756bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1335.162207109323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.6534605786755,
        1358.6709536399705
      ],
      "voteCount": 781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.86752253206942
      }
    },
    {
      "id": "f51bc07187a4557dee316a80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1349.53758491506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.9325699059877,
        1359.1425999241324
      ],
      "voteCount": 4073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.01595790315781
      }
    },
    {
      "id": "7dd22e962a483ceb5b812176",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1291.075112045296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.6660272913605,
        1303.4841967992315
      ],
      "voteCount": 2412,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.0851321380384
      }
    },
    {
      "id": "11552eae7a2ee97e8787796f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1301.1506418083911,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.3273494886216,
        1311.9739341281606
      ],
      "voteCount": 3113,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.494575656550097
      }
    },
    {
      "id": "54fa632254c2a04085ad211f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1225.727326207752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.4162541963108,
        1263.0383982191934
      ],
      "voteCount": 295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 362.3925596035445
      }
    },
    {
      "id": "4dbbb8b9c4f1283213c9017b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1195.2576226118267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.8043607625614,
        1245.710884461092
      ],
      "voteCount": 178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 662.6471218479907
      }
    },
    {
      "id": "727da54ba83320a5ac229964",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1335.2319347258692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.9271403609932,
        1347.5367290907452
      ],
      "voteCount": 2386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.414183889267555
      }
    },
    {
      "id": "dbd803a1282ba267d9ac5298",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1285.221753996786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.560203053681,
        1310.8833049398909
      ],
      "voteCount": 553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.42320861494545
      }
    },
    {
      "id": "51f49b15c90faa7f44570f0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1312.6390816006774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.6135305243486,
        1327.6646326770062
      ],
      "voteCount": 1654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.77121054406425
      }
    },
    {
      "id": "865af3c0bb496fdb020bba3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1303.7978809388464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.3721558196823,
        1310.2236060580105
      ],
      "voteCount": 11641,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.74850603229831
      }
    },
    {
      "id": "59787dcbc58a4f02709ab19b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1277.13265126118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.9773718023678,
        1298.287930719992
      ],
      "voteCount": 764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.50413810750305
      }
    },
    {
      "id": "6f7630db2bb03aa56bc3a0b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "magistral-medium-2506",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1320.3770123050867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.1089730431177,
        1361.6450515670556
      ],
      "voteCount": 232,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 443.3344580847755
      }
    },
    {
      "id": "94bb6bb06eb367da4aa763f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1396.3825961385776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.5604434138586,
        1417.2047488632963
      ],
      "voteCount": 768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.86390517995312
      }
    },
    {
      "id": "437ab49310fca34ca4c636fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1299.541459283228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.021785578696,
        1326.0611329877604
      ],
      "voteCount": 530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.0796908732124
      }
    },
    {
      "id": "84c9544ce16ae76a12291c01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1364.5894701240372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.024135067646,
        1380.1548051804284
      ],
      "voteCount": 1396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.0697000088994
      }
    },
    {
      "id": "612e637d603a03b914a4598b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1298.6063256601024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.682410383667,
        1314.5302409365381
      ],
      "voteCount": 2172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.00905790401805
      }
    },
    {
      "id": "74d9c051b1ce938d3fb0d265",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1349.8408227352784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.843626244965,
        1387.8380192255922
      ],
      "voteCount": 229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 375.8433992174399
      }
    },
    {
      "id": "0716468989fa00e389f57b31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1371.0277505933545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.2572194178006,
        1390.7982817689085
      ],
      "voteCount": 865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.75142340662288
      }
    },
    {
      "id": "2ca3c500eff0c9cc415f424e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1358.6143814093643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.721322958343,
        1372.507439860386
      ],
      "voteCount": 1759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.24577436147661
      }
    },
    {
      "id": "38ef2a8f4fc3395b68252b58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1337.517982115787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.320165309479,
        1362.7157989220948
      ],
      "voteCount": 478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 165.28355539928
      }
    },
    {
      "id": "8ad9375fa0251b134862fe3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1311.3010641293513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.322003347987,
        1334.2801249107154
      ],
      "voteCount": 659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.45747619343533
      }
    },
    {
      "id": "185d4f35efa3042a95e32b8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1321.8508137706572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.5803253983393,
        1349.1213021429749
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.59299963297508
      }
    },
    {
      "id": "cd2a37b27519d56780bd1743",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1345.638004108098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.7087859780063,
        1383.5672222381893
      ],
      "voteCount": 229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 374.4998072633545
      }
    },
    {
      "id": "a321cea1b5ac6debebf3b5c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1383.6620988972302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.9006810324968,
        1401.4235167619634
      ],
      "voteCount": 1087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.12191755544106
      }
    },
    {
      "id": "cfc28d84bbab6a75ec86d037",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1308.639997776887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.1196813348315,
        1331.1603142189424
      ],
      "voteCount": 696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.0239722259143
      }
    },
    {
      "id": "80d0b9c99b64f925fc1ffd79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1322.237314627974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.1151708888901,
        1342.3594583670579
      ],
      "voteCount": 836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.40283979490711
      }
    },
    {
      "id": "407572a2903f93b1a283f882",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1324.0437142564153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.6047646238671,
        1344.4826638889635
      ],
      "voteCount": 844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.74792144885274
      }
    },
    {
      "id": "0a1d04a1f8d804d12bfa858f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1344.2676946837846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.6300792969823,
        1369.9053100705871
      ],
      "voteCount": 540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.1035711695683
      }
    },
    {
      "id": "311985c87c876f24c0acd6ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1346.5676192844876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.9668436027357,
        1357.1683949662395
      ],
      "voteCount": 3123,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.253585760035836
      }
    },
    {
      "id": "0af6eef1f052943f3c67a276",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury-2",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1304.7113712575865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.242323409687,
        1335.1804191054862
      ],
      "voteCount": 360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 241.66935533877293
      }
    },
    {
      "id": "211a2a3546441f1ff20866f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1367.2920697045217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.6931353315786,
        1395.8910040774647
      ],
      "voteCount": 394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.91365740063102
      }
    },
    {
      "id": "2edbcc4a55cc6af1b4bd36ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1219.9101307224914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.2151393318882,
        1258.6051221130942
      ],
      "voteCount": 298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 389.7744134735494
      }
    },
    {
      "id": "ba7c5f134bb1d9c1b7f58bb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1325.4289874204856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.7941151040811,
        1345.0638597368898
      ],
      "voteCount": 943,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.35984475601836
      }
    },
    {
      "id": "12445ad85e28225d1bcadd59",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1246.5529077664642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.788398648998,
        1267.31741688393
      ],
      "voteCount": 1430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.23987006358682
      }
    },
    {
      "id": "87c8b4b90281e65b7c9458b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1343.2423001759203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.2414082148055,
        1369.2431921370348
      ],
      "voteCount": 519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.98688788011077
      }
    },
    {
      "id": "453a3baee37cd85ce82bd6d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1319.586197595942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.8351035884566,
        1338.3372916034273
      ],
      "voteCount": 1031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.5286465088338
      }
    },
    {
      "id": "ee323a374552dcbaff6c8a47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1327.7105153095517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.37272532415,
        1360.0483052949535
      ],
      "voteCount": 351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.2227960655289
      }
    },
    {
      "id": "1723ecbfeda0b3fa18072f74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1236.6134718213532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.6861174002634,
        1269.540826242443
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 282.23930537309474
      }
    },
    {
      "id": "ffad83d7abe373f787719e4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1331.004780748509,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.426735785179,
        1366.5828257118385
      ],
      "voteCount": 288,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 329.50952814951364
      }
    },
    {
      "id": "44ec9c67526ea08455ff83b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1357.881492974014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.224830106506,
        1380.538155841522
      ],
      "voteCount": 676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.62745671686199
      }
    },
    {
      "id": "22c7b6c102867bdd3f5b5741",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1258.6916372440503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.570043966447,
        1287.8132305216536
      ],
      "voteCount": 456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.7669623991739
      }
    },
    {
      "id": "f736cdd59833b8f20fa13a1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1269.2502345088894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.3635749956366,
        1295.1368940221423
      ],
      "voteCount": 569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.4439214459683
      }
    },
    {
      "id": "e6c1d6496217fa35f8b48abc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1296.8540235364294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.5793013724287,
        1324.12874570043
      ],
      "voteCount": 493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.65311561221012
      }
    },
    {
      "id": "73b27ae052974fcabd99109d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1301.1596705723694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.7632728957492,
        1333.5560682489895
      ],
      "voteCount": 337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 273.2104211993281
      }
    },
    {
      "id": "9645ffc1c6ab93bb72a08b0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mercury",
      "organization": "inception-ai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1306.0868453684416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.2748920434524,
        1319.8987986934308
      ],
      "voteCount": 1957,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.66083552008724
      }
    },
    {
      "id": "ba0cbee7279ef0c3292ec294",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1442.7149355813228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.396811848266,
        1456.0330593143797
      ],
      "voteCount": 2193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.17319306235888
      }
    },
    {
      "id": "1a49a4368e0234505b51e401",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1445.4564430172563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.1997320438916,
        1451.7131539906213
      ],
      "voteCount": 11214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.190511998551486
      }
    },
    {
      "id": "3b93fe75ad2115fb765e8580",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1358.2655165270462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.517857590857,
        1366.0131754632355
      ],
      "voteCount": 6822,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.62589156706529
      }
    },
    {
      "id": "ba99d66912bfcc8712945be5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1416.4160720074942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.5442589113882,
        1421.2878851036005
      ],
      "voteCount": 20160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.178528509932712
      }
    },
    {
      "id": "f87d75e934700351928967e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1371.6892141568455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.5634566725396,
        1376.8149716411517
      ],
      "voteCount": 31628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.839430282679044
      }
    },
    {
      "id": "23830c4ebab4a8925bf783c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1419.261757179804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.7331293361633,
        1429.7903850234445
      ],
      "voteCount": 3436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.856746731923153
      }
    },
    {
      "id": "7e72532f330e2f51ec4f8392",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1399.2583720467662,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.541741385151,
        1418.9750027083817
      ],
      "voteCount": 1165,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.19736870596151
      }
    },
    {
      "id": "4ac0be837f4ef8b7ec0a0095",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1352.3526914122626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.6210109483081,
        1375.0843718762173
      ],
      "voteCount": 736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.51381905532617
      }
    },
    {
      "id": "44d6eba6121b360acba32211",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1433.1369222620206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.1858337121544,
        1439.0880108118865
      ],
      "voteCount": 12426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.219272308103847
      }
    },
    {
      "id": "a6af9f2205a0461073d39bf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1414.274551265123,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.705764684175,
        1418.843337846071
      ],
      "voteCount": 26280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.433823918612303
      }
    },
    {
      "id": "7b41e8cc1d6cd039d666bb6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1389.7438646996004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.7406667509576,
        1396.7470626482432
      ],
      "voteCount": 8387,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.767228232063118
      }
    },
    {
      "id": "a69bb8c582126b3e93579f07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1356.8797306379909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.7961162363422,
        1363.9633450396395
      ],
      "voteCount": 8420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.062119193087618
      }
    },
    {
      "id": "b8e7f507a2f2ed4d6b3d875d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1393.140314953047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.1366409398174,
        1404.1439889662765
      ],
      "voteCount": 3149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.519494921344954
      }
    },
    {
      "id": "0afd87c5204bf9089c4d1263",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1404.0967661304342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.6293618338036,
        1411.5641704270645
      ],
      "voteCount": 7088,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.51587262342682
      }
    },
    {
      "id": "2dfeaf2cbb36be96120a8322",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1403.3068729182557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.0849815267459,
        1416.5287643097656
      ],
      "voteCount": 2138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.508339443111424
      }
    },
    {
      "id": "32c8dfe80b225eefe866dda7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1399.1584489760771,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.5483184021468,
        1410.7685795500074
      ],
      "voteCount": 2985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.08956837375493
      }
    },
    {
      "id": "7642ead532c102b2622c05c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1437.6678885639888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.3818585662116,
        1442.9539185617662
      ],
      "voteCount": 16744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.273828626478097
      }
    },
    {
      "id": "8094e013082a3febc5e241fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1370.29084825003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.8040415256164,
        1376.7776549744437
      ],
      "voteCount": 10014,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.953823389494037
      }
    },
    {
      "id": "907b0e9825656b86eb6c5857",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1383.4273135126873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.6374258026613,
        1389.2172012227134
      ],
      "voteCount": 13061,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.726580515225677
      }
    },
    {
      "id": "8f08980dd002e357c495b9ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1317.1116789425078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.3027682060936,
        1350.920589678922
      ],
      "voteCount": 365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 297.55426220507644
      }
    },
    {
      "id": "21aa8bec1d370e2bdcd892e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1322.7639499754305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.4413455928336,
        1347.0865543580273
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.0011520533298
      }
    },
    {
      "id": "48fc62bfa75dd019a3da6214",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1403.7900917345053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.9526438228725,
        1409.627539646138
      ],
      "voteCount": 14001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.870535833277176
      }
    },
    {
      "id": "74f5fd5608a10be283172de8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1379.708301174787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.2468783332533,
        1391.169724016321
      ],
      "voteCount": 2746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.19643934350374
      }
    },
    {
      "id": "e475c6f08d996fb42d8fd7d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1388.4026554252625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.1165148519967,
        1395.6887959985281
      ],
      "voteCount": 7840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.819709368586922
      }
    },
    {
      "id": "31997c9c09490ff2e940e96b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1393.2375684115434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.6135667238116,
        1396.8615700992752
      ],
      "voteCount": 44619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.418854358644464
      }
    },
    {
      "id": "76a18abfdc2194418b0d9f33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1369.644614336918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.9229742872906,
        1378.3662543865455
      ],
      "voteCount": 4968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.801593276358858
      }
    },
    {
      "id": "1c9f8ca7f078feb744606187",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (non-thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1386.8388051605837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.3750028375807,
        1405.3026074835864
      ],
      "voteCount": 1247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.74545117766536
      }
    },
    {
      "id": "081b2bbb06038815e93c6714",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1425.8783392211596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.0420560513942,
        1452.7146223909251
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.4772392425916
      }
    },
    {
      "id": "67a17c544f0eaca52abef9df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1431.9306960578624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.9652214764742,
        1443.8961706392506
      ],
      "voteCount": 2444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.27036749335183
      }
    },
    {
      "id": "70f438d077683ad010447923",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1337.6396898247417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.4052051966323,
        1351.874174452851
      ],
      "voteCount": 1709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.74573074592256
      }
    },
    {
      "id": "34c9368a9e14f770e7284934",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1405.0636890899943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.4333022734,
        1413.6940759065885
      ],
      "voteCount": 4923,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.389398684374054
      }
    },
    {
      "id": "5413301733ceca4b11ced3b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1359.884846088482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.0094218572378,
        1368.760270319726
      ],
      "voteCount": 7637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.506052247703526
      }
    },
    {
      "id": "6b7c9c2229d02036e5ff1822",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1417.7885395163444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.1289144046705,
        1439.4481646280183
      ],
      "voteCount": 711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.1253127720583
      }
    },
    {
      "id": "1c8882980992d36d47f845b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1428.7421965028698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.0625654278247,
        1462.4218275779149
      ],
      "voteCount": 303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 295.2830167644965
      }
    },
    {
      "id": "fe4b61f56548f458fb64038d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1381.1946045165612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.7902405634113,
        1418.5989684697108
      ],
      "voteCount": 242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 364.2070650875497
      }
    },
    {
      "id": "d5ab4a4d8fb340b15e0684ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1424.6640751221073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.5534740819162,
        1435.7746761622984
      ],
      "voteCount": 2770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.13504588654943
      }
    },
    {
      "id": "a3e7bda007d3400943f03fb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1412.7561671945311,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.8329414869356,
        1420.679392902127
      ],
      "voteCount": 6001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.342100369609014
      }
    },
    {
      "id": "1857e4aded44eda9054374d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1389.0816387959396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.4652847891412,
        1401.697992802738
      ],
      "voteCount": 2088,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.43540145930773
      }
    },
    {
      "id": "8d8fed8aa9e5bb1eb88881eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1346.1207977867598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.969564709042,
        1359.2720308644775
      ],
      "voteCount": 2021,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.02324235072924
      }
    },
    {
      "id": "bd14eaa4eaf609d397368cb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1403.3237077749147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.2890934443549,
        1423.3583221054746
      ],
      "voteCount": 856,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.48784956693733
      }
    },
    {
      "id": "98b619855f53d876a9e31b0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1399.6960462331397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.5981658474834,
        1413.7939266187957
      ],
      "voteCount": 1700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.73821734013876
      }
    },
    {
      "id": "bcf27fbf9db82dc954ccade9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1390.6644138110082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.7893964503705,
        1417.539431171646
      ],
      "voteCount": 426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.01882093429916
      }
    },
    {
      "id": "8e666b12a9a174f8a70054d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1404.8798620919647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.61900363955,
        1427.1407205443793
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.99938335116423
      }
    },
    {
      "id": "b6c6fbce31db3745816325d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1426.662167524503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.9549875690866,
        1436.3693474799197
      ],
      "voteCount": 3733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.529572510115962
      }
    },
    {
      "id": "01ffbff3da40141a04af014d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1356.0335340332413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.1392877297435,
        1367.9277803367393
      ],
      "voteCount": 2443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.82796086896743
      }
    },
    {
      "id": "8ed9766e3a25c5baf5f8755a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1379.7325393085985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.0226574151798,
        1390.4424212020172
      ],
      "voteCount": 2977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.858857149027397
      }
    },
    {
      "id": "4597e0b398eaac30b0a845e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1268.0015832982162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.6298843643556,
        1315.3732822320771
      ],
      "voteCount": 154,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 584.1733478415518
      }
    },
    {
      "id": "49d59a88d8270d469973dcc7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1402.6831134302124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.6363346225753,
        1413.7298922378495
      ],
      "voteCount": 2814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.76692181820939
      }
    },
    {
      "id": "b7d050ed32d1fee55b1ab282",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1374.2549085063529,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.9710755439146,
        1396.5387414687912
      ],
      "voteCount": 633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.2657905956988
      }
    },
    {
      "id": "7439f24f6281f522c5e8bbb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1376.339560206518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.8306377121949,
        1389.8484827008408
      ],
      "voteCount": 1901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.505647066821744
      }
    },
    {
      "id": "62c8fecfeae0fa6b6e2674e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1387.4642844353357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.2122020018855,
        1393.7163668687854
      ],
      "voteCount": 10974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.175440263496007
      }
    },
    {
      "id": "0f47a8e1e51b6f6627af5813",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1364.8627334139692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.717053417804,
        1381.0084134101346
      ],
      "voteCount": 1282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.8604131155231
      }
    },
    {
      "id": "09c7636be1a8d9ae982322dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-flash (thinking)",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1371.4328206929297,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.7320399486282,
        1404.1336014372312
      ],
      "voteCount": 321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.3684821834569
      }
    },
    {
      "id": "476f0d5f8cd14f50f295f233",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1464.2303470228205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.3692145700024,
        1485.0914794756386
      ],
      "voteCount": 848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.2868703081362
      }
    },
    {
      "id": "9c464fb81ecaf406fe369b0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1384.9024773362112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.5592204702725,
        1412.2457342021496
      ],
      "voteCount": 470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.62754410096747
      }
    },
    {
      "id": "308f50f280758917271c3d2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1430.6731632297249,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.5371097868915,
        1446.8092166725583
      ],
      "voteCount": 1356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.77951628879535
      }
    },
    {
      "id": "60e15ca1778ffbaaa2ca94e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1402.0567964503343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.1036193087552,
        1417.0099735919134
      ],
      "voteCount": 2231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.206404666609906
      }
    },
    {
      "id": "0e5b6b92c5f3772cd2dbfd92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1447.3530835434333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.7557463215123,
        1481.9504207653542
      ],
      "voteCount": 283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 311.5940580695918
      }
    },
    {
      "id": "2366318cec72bf948ed6eb5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1448.3960722218023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.7001768325656,
        1468.091967611039
      ],
      "voteCount": 930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.9846293532983
      }
    },
    {
      "id": "b3b36c6f829f2038c88e76d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1442.0630071227577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.1799430906437,
        1455.9460711548716
      ],
      "voteCount": 1917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.173508533132896
      }
    },
    {
      "id": "53addf6c91cf4a41533258ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1440.6992916881077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.8809615527066,
        1465.5176218235085
      ],
      "voteCount": 595,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.34260406270744
      }
    },
    {
      "id": "30c26d4d10dae8a2bac27209",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1384.1932308882233,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.8666653790087,
        1408.519796397438
      ],
      "voteCount": 620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.05131672534313
      }
    },
    {
      "id": "7bdae684f010d9c7e44c3f86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1409.2230712400287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.2238797160114,
        1450.222262764046
      ],
      "voteCount": 199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 437.57691650051885
      }
    },
    {
      "id": "58b70744bdb7f531087fd9cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1423.702323715606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.689252956405,
        1451.7153944748075
      ],
      "voteCount": 463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 204.27972028038562
      }
    },
    {
      "id": "bfba97c2feafcd9392e46f3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1462.936590347108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.6700044823958,
        1480.2031762118202
      ],
      "voteCount": 1217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.60983557012585
      }
    },
    {
      "id": "3134fed3b2ee5d03847d74b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1389.3204281636326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.2897724340792,
        1412.3510838931861
      ],
      "voteCount": 683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.07543646592262
      }
    },
    {
      "id": "96b51a543859bc3bc51d4bce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1405.4342979501516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.0254608257226,
        1424.8431350745807
      ],
      "voteCount": 958,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.06247472790741
      }
    },
    {
      "id": "233a97a0e47762a4e1ee121f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1435.3104934770897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.1507340571202,
        1452.470252897059
      ],
      "voteCount": 1255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.65247946039955
      }
    },
    {
      "id": "2c613a5c41b19d4cb9e0f2f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1408.3616302712335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.3008687473177,
        1436.422391795149
      ],
      "voteCount": 482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 204.97586309145592
      }
    },
    {
      "id": "c912f885d71839061a1889a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1414.3808259450332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.3108267940704,
        1425.4508250959962
      ],
      "voteCount": 2968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.90061039888371
      }
    },
    {
      "id": "cb3e0d1dadb5c3bab91a1d32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-omni",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1421.4657687361143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.579101087757,
        1453.3524363844715
      ],
      "voteCount": 360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.6805865103803
      }
    },
    {
      "id": "f77bd2b39de1f589ff46736a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1480.2229114583204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.8375488579893,
        1498.6082740586517
      ],
      "voteCount": 1140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.99301872630211
      }
    },
    {
      "id": "ef1b58bf9f5056720821c80e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1503.0891865414778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.9786576537529,
        1511.1997154292028
      ],
      "voteCount": 6196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.12387973138143
      }
    },
    {
      "id": "7ab7b9174991d91521605844",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1422.5921013446507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.9220773218867,
        1433.2621253674147
      ],
      "voteCount": 3366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.637025401144047
      }
    },
    {
      "id": "da04581674a61bd6a2bd14a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1465.3993528290673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.9186879072195,
        1471.8800177509152
      ],
      "voteCount": 10141,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.933090731838544
      }
    },
    {
      "id": "c6188044107d2dda26a18f66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1449.5968484355715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.0533233856925,
        1456.1403734854507
      ],
      "voteCount": 16660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.146213476956964
      }
    },
    {
      "id": "d94a7f87154dc94b6d739978",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1493.4006511769367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.3004406453135,
        1507.5008617085596
      ],
      "voteCount": 1869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.75532169317089
      }
    },
    {
      "id": "1a3440909872da9e1184140c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1479.9329896590432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.648233456613,
        1503.217745861473
      ],
      "voteCount": 785,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.1390559455843
      }
    },
    {
      "id": "f72e3596ccecf745e70e68b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1433.6021033586676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.3347751586753,
        1461.86943155866
      ],
      "voteCount": 419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.0047921538559
      }
    },
    {
      "id": "3f9d9fdb3fedc6b30a19ea24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1489.169084295128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1481.3916348373127,
        1496.9465337529432
      ],
      "voteCount": 6721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.746288816897994
      }
    },
    {
      "id": "4b8e78cd67b1c54e5ef7fee9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1475.0591475444576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1469.1617167893314,
        1480.9565782995835
      ],
      "voteCount": 14249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.05377127151445
      }
    },
    {
      "id": "9ab4c06fba95c5e0c9718129",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1453.4885473994887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.1417182012863,
        1462.835376597691
      ],
      "voteCount": 4399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.742197727004065
      }
    },
    {
      "id": "e10195079d663ce8557d7515",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1424.3681060930212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.8010605343602,
        1433.935151651682
      ],
      "voteCount": 4298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.82645890369172
      }
    },
    {
      "id": "b692349b54a1c4d3ef4b215c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1457.360707704489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.2157785666977,
        1472.50563684228
      ],
      "voteCount": 1593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.70879535479886
      }
    },
    {
      "id": "d2989319585d9f7d12768481",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1481.0591167911384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.9546543089164,
        1491.1635792733607
      ],
      "voteCount": 3589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.578486668818947
      }
    },
    {
      "id": "afffe80ffd27837aa32fd818",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1473.1400538022012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.306834856096,
        1489.9732727483065
      ],
      "voteCount": 1309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.76293052031686
      }
    },
    {
      "id": "1131b68f8e7d718e46017f54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1470.7518063117682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.645084135044,
        1485.8585284884925
      ],
      "voteCount": 1600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.407913914197714
      }
    },
    {
      "id": "5e74e4fa1da5772f1f06772f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1490.5719144777074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.6629010959214,
        1497.4809278594937
      ],
      "voteCount": 8901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.426129795418506
      }
    },
    {
      "id": "b03e0c349bf5afe547311718",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1431.096623896795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.475783421106,
        1439.7174643724843
      ],
      "voteCount": 5216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.34652796664693
      }
    },
    {
      "id": "79de0c56c3d153b93e36c992",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1445.8886997733377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.4056239010424,
        1453.3717756456329
      ],
      "voteCount": 7241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.576864447660107
      }
    },
    {
      "id": "1587ff00808cdfec434305e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1414.002724356676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.6118632561488,
        1462.3935854572035
      ],
      "voteCount": 143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 609.5797319070049
      }
    },
    {
      "id": "427a196138a3cc426ebe1e39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1415.346110116562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.7223565565234,
        1444.9698636766007
      ],
      "voteCount": 421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 228.4462273182282
      }
    },
    {
      "id": "314c827b48bb3807bc0424d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1464.9193517317162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.5313111137016,
        1472.307392349731
      ],
      "voteCount": 8191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.208962459624104
      }
    },
    {
      "id": "52b1680bbd2a63c9dc4444b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1453.021456250944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.9250800530656,
        1468.1178324488226
      ],
      "voteCount": 1538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.32656965634028
      }
    },
    {
      "id": "c438bfa65438407c64224cd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1468.9978089213091,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.2175941023695,
        1478.7780237402487
      ],
      "voteCount": 4042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.900072178131715
      }
    },
    {
      "id": "fa0f393618b36a469c8d81da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1448.3316456069479,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.4596846590887,
        1453.2036065548068
      ],
      "voteCount": 22638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.178903532584327
      }
    },
    {
      "id": "1f7edf237af8ad8c17cfb2c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1441.9388968957694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.0080153968966,
        1453.8697783946425
      ],
      "voteCount": 2614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.05517616727393
      }
    },
    {
      "id": "16626666c281a5ad8a7446eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2-pro",
      "organization": "xiaomi",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1464.5785440375055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.5801569426842,
        1488.576931132327
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.92288347602994
      }
    },
    {
      "id": "13c3fd0883c0c5a7a4705d99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1512.6108203074045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1491.9738024927942,
        1533.2478381220146
      ],
      "voteCount": 849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.86582576032514
      }
    },
    {
      "id": "dc560e060e0312cb2c3238e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1519.5805227990902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1509.7482954695606,
        1529.4127501286196
      ],
      "voteCount": 4275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.16562034682387
      }
    },
    {
      "id": "d93e5f0f4c17528e8cc6c4d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1440.0075493819538,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.2779863389046,
        1452.7371124250028
      ],
      "voteCount": 2424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.18235384797986
      }
    },
    {
      "id": "5c7b0d402ce9cb57ad1ca090",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1478.867413022172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1471.3545939741757,
        1486.3802320701686
      ],
      "voteCount": 7172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.69297282164807
      }
    },
    {
      "id": "460ad208e6e043bfd7ca8d11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1470.1691518562059,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.7929495854517,
        1477.5453541269603
      ],
      "voteCount": 11919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.163463017221815
      }
    },
    {
      "id": "607ff13a8611294be9ca76ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1519.7044473597125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1503.1834828445049,
        1536.22541187492
      ],
      "voteCount": 1373,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.05172312205761
      }
    },
    {
      "id": "2d0d6c414e2698ba61b85aea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1493.9544555289963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.0688330413327,
        1521.84007801666
      ],
      "voteCount": 537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.42516653711883
      }
    },
    {
      "id": "7659243220aaea86702b2595",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1429.4565261497423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.0142620322663,
        1468.8987902672184
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 404.9743265064159
      }
    },
    {
      "id": "4454c3584df7906cdab3c2d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1504.5336161181374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.3742609354715,
        1513.6929713008033
      ],
      "voteCount": 4871,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.83904377948516
      }
    },
    {
      "id": "498aa6b1487dd2600b844703",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1494.8688366535432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.0222463024593,
        1501.7154270046271
      ],
      "voteCount": 10143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.202603652298011
      }
    },
    {
      "id": "f59ea56fedfaa8397e7bbdf0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1460.2152019418143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.0242824170034,
        1471.4061214666253
      ],
      "voteCount": 3074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.60133341431092
      }
    },
    {
      "id": "017eb75ceca1c7d4129a8942",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1443.8457484083615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.5857125145158,
        1455.1057843022072
      ],
      "voteCount": 3135,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.00527592478118
      }
    },
    {
      "id": "36a324e4497a2a591ecb2970",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1474.3511783877877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1456.7115036602042,
        1491.9908531153715
      ],
      "voteCount": 1217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.9999895921644
      }
    },
    {
      "id": "ab8babcb76ba5b8ddf366fcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1489.808060830028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.7175593294614,
        1501.8985623305944
      ],
      "voteCount": 2583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.05331082757402
      }
    },
    {
      "id": "f7fc9229fed8a3a0bd34cb35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1513.686866949224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1492.6198223352328,
        1534.753911563215
      ],
      "voteCount": 839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.53432940033355
      }
    },
    {
      "id": "e41e4b38cd0b2a77e699d33d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1482.6725570380645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.081380427957,
        1501.263733648172
      ],
      "voteCount": 1104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.97411240913932
      }
    },
    {
      "id": "929b7fc50194552cd69f46e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1504.1382717979004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1495.9178931389786,
        1512.3586504568225
      ],
      "voteCount": 6229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.590875875599888
      }
    },
    {
      "id": "ce988f6f57e92da46bd384e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1451.017193251545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.7430070935845,
        1461.2913794095055
      ],
      "voteCount": 3669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.47885793797275
      }
    },
    {
      "id": "d28edc5fe668737d571b5210",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1473.9836783999606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1465.031464039132,
        1482.9358927607889
      ],
      "voteCount": 5073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.862423809021124
      }
    },
    {
      "id": "aa1770e8522612a249978670",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1474.3983588571282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.1264412204484,
        1512.6702764938077
      ],
      "voteCount": 254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 381.2977694042086
      }
    },
    {
      "id": "6f83fb2504b1f4a059ba6d5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1488.4920419460502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.096648676091,
        1496.8874352160094
      ],
      "voteCount": 6318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.347880700316864
      }
    },
    {
      "id": "ff3fa420d75f6f459e5eadf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1486.467707147943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.4009753296843,
        1506.5344389662018
      ],
      "voteCount": 866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.82312701015945
      }
    },
    {
      "id": "6370f637d56674e688081407",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1480.2332229940805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.1176733062832,
        1492.348772681878
      ],
      "voteCount": 2691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.21114610073122
      }
    },
    {
      "id": "5fff78bc02f6ba328ed8533c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1464.7672400023976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.0778467159294,
        1470.456633288866
      ],
      "voteCount": 15722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.426276963776418
      }
    },
    {
      "id": "b332e0ad39f1c1522489e297",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1459.624056928545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.084703359466,
        1474.1634104976242
      ],
      "voteCount": 1827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.02930320843539
      }
    },
    {
      "id": "84b062c2a12b1d18d640e900",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5-pro",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1465.3277042040158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.349203420671,
        1492.3062049873606
      ],
      "voteCount": 511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.46955791795264
      }
    },
    {
      "id": "64121e469ee37b657c3893f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1492.30661768967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.3600633479807,
        1514.2531720313593
      ],
      "voteCount": 766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.38237944346632
      }
    },
    {
      "id": "68a114a6b2d19709dcfd795d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1489.9948814353472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.5746831006516,
        1499.4150797700431
      ],
      "voteCount": 4584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.100634630510374
      }
    },
    {
      "id": "c5e1089c6b0b509377a851ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1400.2395507741749,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.848107199181,
        1412.6309943491685
      ],
      "voteCount": 2523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.97124036448976
      }
    },
    {
      "id": "beffee8b09393bd3dcecd48b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1454.7993010275986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.347418246216,
        1462.2511838089815
      ],
      "voteCount": 7441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.455590852184294
      }
    },
    {
      "id": "ee20e72a686209723931320b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1427.850470290467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.517786568428,
        1435.1831540125063
      ],
      "voteCount": 12121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.996831172003262
      }
    },
    {
      "id": "a0bfacbdc666436c5bf2bf8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1476.6432854632105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.921471636868,
        1492.3650992895527
      ],
      "voteCount": 1495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.34415713598739
      }
    },
    {
      "id": "d7be5c6a178a3fa568ef4edf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1442.2872050849164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.1672474852953,
        1469.4071626845375
      ],
      "voteCount": 566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.4616645746957
      }
    },
    {
      "id": "037176755b2f04821f9b5420",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1410.4274611381911,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.9662293891017,
        1448.8886928872803
      ],
      "voteCount": 232,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 385.07931926492995
      }
    },
    {
      "id": "8d2c322aba111c043629861d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1472.9113052944952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.012741786318,
        1481.8098688026723
      ],
      "voteCount": 5176,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.613115018308097
      }
    },
    {
      "id": "923d3596a7d52a5cec78d830",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1463.7346414193496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.0320426707692,
        1470.43724016793
      ],
      "voteCount": 10546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.694731632279872
      }
    },
    {
      "id": "5b6ad29d61f99542725705e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1438.4540963740055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.2696031262055,
        1449.6385896218055
      ],
      "voteCount": 3215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.56390216555288
      }
    },
    {
      "id": "2600b433544f7c4aee642253",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1415.013969993751,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.9511047229973,
        1426.0768352645048
      ],
      "voteCount": 3199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.859507992001195
      }
    },
    {
      "id": "f313ffb14ad6f6d05625c5f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1414.0402008927597,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.7141350036468,
        1432.3662667818724
      ],
      "voteCount": 1208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.4263415666183
      }
    },
    {
      "id": "81149203df46071ce1c71164",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1449.560367660831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.5297231568534,
        1461.5910121648085
      ],
      "voteCount": 2637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.677458990678836
      }
    },
    {
      "id": "1d44a52f5ee51c4de67ce0e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1460.779937135194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.6064953919029,
        1480.953378878485
      ],
      "voteCount": 914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.94093826480824
      }
    },
    {
      "id": "ed73605f866cbe604e26da31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1441.0913745138637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.72834048033,
        1459.4544085473976
      ],
      "voteCount": 1147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.77941783475679
      }
    },
    {
      "id": "453b58972c29a90052969a09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1480.0679563978076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.023697071984,
        1488.1122157236312
      ],
      "voteCount": 6501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.845191142620838
      }
    },
    {
      "id": "9a1f54ae7eb8e3504ac27266",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1415.3145010772732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.2384725422949,
        1425.3905296122514
      ],
      "voteCount": 3735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.429113463554465
      }
    },
    {
      "id": "33c81cf8ee0cd9ff9069cd97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1432.3320413346357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.626452159752,
        1441.0376305095192
      ],
      "voteCount": 5296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.728776597468975
      }
    },
    {
      "id": "d41e5e8c5499790d0ec196d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1386.2095381862227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.787009332026,
        1422.6320670404193
      ],
      "voteCount": 259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 345.33771414868016
      }
    },
    {
      "id": "1815591223d25fe31aaa42d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1454.3335974666834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.1541142433512,
        1462.5130806900156
      ],
      "voteCount": 6653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.41628608391152
      }
    },
    {
      "id": "3f05444d5cca534c3ba24158",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1442.370518995542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.480680633318,
        1461.2603573577658
      ],
      "voteCount": 914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.8881474477114
      }
    },
    {
      "id": "11cf74cf0da8bb122cc975a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1453.9798046405851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.1168911944078,
        1465.8427180867623
      ],
      "voteCount": 2793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.63418560505672
      }
    },
    {
      "id": "5e953ce85ebf275e7db39e20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1433.8836385295615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.2270362475126,
        1439.5402408116104
      ],
      "voteCount": 15979,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.329426624310114
      }
    },
    {
      "id": "484a388e0bf8cea10d147073",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1405.8785990978504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.4489076136792,
        1420.3082905820218
      ],
      "voteCount": 1808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.20232418129638
      }
    },
    {
      "id": "8577cf20e79a9b8d8f61d8dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mimo-v2.5",
      "organization": "xiaomi",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1414.1217736207552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.9220678319746,
        1442.321479409536
      ],
      "voteCount": 492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 207.01078514492755
      }
    },
    {
      "id": "b4e0e4b5cf62b37ea3352d94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1385.8328519871984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.6966314498588,
        1399.9690725245382
      ],
      "voteCount": 1822,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.02001125296322
      }
    },
    {
      "id": "29f75f905948e2d1d576b598",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1416.0177099226783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.3942047576916,
        1423.6412150876647
      ],
      "voteCount": 6489,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.1291042578648
      }
    },
    {
      "id": "5347cb94e9bf73b72c04acf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1317.721141592307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.643388835885,
        1326.798894348729
      ],
      "voteCount": 4546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.45164088778053
      }
    },
    {
      "id": "c919e6089a60e354c46cf863",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1384.8339202444145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.4571681817251,
        1390.2106723071038
      ],
      "voteCount": 16873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.525646920356929
      }
    },
    {
      "id": "7fdf7cd8c61e6ac27ea18712",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1329.3100411115083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.3900310216936,
        1335.230051201323
      ],
      "voteCount": 24825,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.123231850022803
      }
    },
    {
      "id": "96920a1a8294950d9697bc57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1363.7559236389984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.0223132351184,
        1378.4895340428786
      ],
      "voteCount": 1594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.509593273239275
      }
    },
    {
      "id": "afee6af0d3d35024ebf4bba8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1411.685446124693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.6952022670916,
        1440.6756899822947
      ],
      "voteCount": 425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.7799682755265
      }
    },
    {
      "id": "2d25093275669ef0f0d41dc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1359.3938729592671,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.5570982060885,
        1380.2306477124457
      ],
      "voteCount": 828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.02247463276214
      }
    },
    {
      "id": "83920256f047f1a943f20035",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1394.2949651380336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.356878570416,
        1401.2330517056507
      ],
      "voteCount": 8158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.530928344314464
      }
    },
    {
      "id": "a3935f7e84bb930fd0a51e5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1380.7215891500978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.2375241296686,
        1386.2056541705274
      ],
      "voteCount": 15829,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.82904895043578
      }
    },
    {
      "id": "0c44576b191c5aac882c9bee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1351.9856149174113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.0566622934386,
        1359.914567541384
      ],
      "voteCount": 6116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.36573308414231
      }
    },
    {
      "id": "e43ae1f3eed39151fd7e7358",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1325.1994781274072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.5345621036922,
        1332.8643941511223
      ],
      "voteCount": 6296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.293913170201884
      }
    },
    {
      "id": "5e3cdbc399c131b5af896f28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1365.0551617880888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.765893999655,
        1377.344429576523
      ],
      "voteCount": 2408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.31477853211816
      }
    },
    {
      "id": "c9dd63cd44a7b8a49b18aedd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1383.3769141534547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.3961560597288,
        1391.3576722471803
      ],
      "voteCount": 5885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.58028960442193
      }
    },
    {
      "id": "b523eff4341a99ab75c10984",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1381.5659431121517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.8681884123107,
        1395.2636978119924
      ],
      "voteCount": 1785,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.84302880099756
      }
    },
    {
      "id": "b68a5bd53693fa8aa3035ab8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1393.1632427608695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.9701034545383,
        1406.3563820672007
      ],
      "voteCount": 2116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.310631424342326
      }
    },
    {
      "id": "eb6c6a520e22a7255b902a21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1402.405455036251,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.2928595845785,
        1408.5180504879236
      ],
      "voteCount": 11668,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.726467183385148
      }
    },
    {
      "id": "c8fff2b61a82489ddcfc320c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1331.5989464831782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.501363856311,
        1338.6965291100455
      ],
      "voteCount": 7800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.113684539278033
      }
    },
    {
      "id": "9a79d0dd940bd61cbb519949",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1345.6418132758522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.9563499344547,
        1352.32727661725
      ],
      "voteCount": 8684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.635012159546148
      }
    },
    {
      "id": "acc742f01e1effa6ac0f2e8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1225.3319752893894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.0714220214745,
        1248.5925285573046
      ],
      "voteCount": 773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.84579936529036
      }
    },
    {
      "id": "799d99764760e3ebf4dda8d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1272.4382372355383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.4577038144012,
        1297.4187706566754
      ],
      "voteCount": 635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.44533109215928
      }
    },
    {
      "id": "fa4a2236445976a312704824",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1364.5564724709966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.1543370161244,
        1371.958607925869
      ],
      "voteCount": 6963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.263229634823226
      }
    },
    {
      "id": "638768af8d9c21a97d7a1fee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1370.795259197328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.3345008312563,
        1384.2560175634
      ],
      "voteCount": 1799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.1675017869992
      }
    },
    {
      "id": "71736c8b528e7e4828c90991",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1357.345849513566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.2182576770317,
        1365.4734413501005
      ],
      "voteCount": 5695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.196006034333973
      }
    },
    {
      "id": "0d505d663e4f081405db2cb3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1363.6356716716004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.3672370211534,
        1367.9041063220475
      ],
      "voteCount": 35214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.742868586014168
      }
    },
    {
      "id": "3654f7fe1293e8f4934ea883",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1348.3014721421819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.3647151834139,
        1361.2382291009494
      ],
      "voteCount": 1930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.56669911666197
      }
    },
    {
      "id": "942ca1c5ffcfdee71bfca43a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m1",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1353.5392396650577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.3751870967517,
        1376.7032922333638
      ],
      "voteCount": 716,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.67957394120626
      }
    },
    {
      "id": "243eedc3b42520344b4971e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1414.687303129325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.6730422686464,
        1435.701563990004
      ],
      "voteCount": 821,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.95610915877661
      }
    },
    {
      "id": "0c7f655ded4c99bcfcc4f2c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1439.2812451887078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.068611901331,
        1449.4938784760843
      ],
      "voteCount": 3426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.15059135882865
      }
    },
    {
      "id": "ce8576fbe8b5361e25f32577",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1346.5716281313844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.8858526131585,
        1358.25740364961
      ],
      "voteCount": 2717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.54830491133323
      }
    },
    {
      "id": "6820c9063ea95a5cea8d4274",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1402.3136487538602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.01043909617,
        1409.61685841155
      ],
      "voteCount": 7643,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.8845354834596
      }
    },
    {
      "id": "0f5fdda3ee12ff17995ec582",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1357.8685396538965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.323913247055,
        1365.413166060738
      ],
      "voteCount": 12084,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.817648782845012
      }
    },
    {
      "id": "96481af510a2a7365d139f5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1432.8266209481556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.5195638515129,
        1451.1336780447984
      ],
      "voteCount": 1055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.24506891347576
      }
    },
    {
      "id": "4951990458d87610079d3bf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1408.707258786549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.3865155479357,
        1439.0280020251623
      ],
      "voteCount": 398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 239.32248488239668
      }
    },
    {
      "id": "398f05924a53dfe04cab30a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1378.7907784593333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.806272385331,
        1415.7752845333353
      ],
      "voteCount": 266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.07662437228254
      }
    },
    {
      "id": "05c251a1473dee67b2a4fa2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1425.086078867076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.6870737758732,
        1434.4850839582784
      ],
      "voteCount": 4200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.996809500743087
      }
    },
    {
      "id": "953855614aeb400ca50ceabe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1407.8752982275028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.042876231421,
        1414.7077202235844
      ],
      "voteCount": 9070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.152151698480449
      }
    },
    {
      "id": "5e86accd80842b2e55780c88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1381.5037885442152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.5042914413073,
        1392.5032856471232
      ],
      "voteCount": 3147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.495570345595652
      }
    },
    {
      "id": "8208470dd021f485308dad50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1351.0404036890063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.39850617656,
        1361.682301201453
      ],
      "voteCount": 3200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.4809831242578
      }
    },
    {
      "id": "26d6cc9dd37a431c7798a9ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1399.614910485438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.0455225401665,
        1417.184298430709
      ],
      "voteCount": 1184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.35577294452578
      }
    },
    {
      "id": "5a073af7478dfdf380cdfd88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1406.632523664991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.9693816945517,
        1418.2956656354302
      ],
      "voteCount": 2654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.410735080596815
      }
    },
    {
      "id": "c1a9ef75da83d2a95627478a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1420.4598200319483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.5258687104142,
        1442.3937713534824
      ],
      "voteCount": 652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.23841671391217
      }
    },
    {
      "id": "a33f18d2734785602039a950",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1376.665308483961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.08324110976,
        1395.2473758581623
      ],
      "voteCount": 1133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.88596364465435
      }
    },
    {
      "id": "258f2fc09a2e9b43d1871cd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1423.120341888635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.9675018922171,
        1431.273181885053
      ],
      "voteCount": 5792,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.30300990059355
      }
    },
    {
      "id": "07193aca7f4004aa664656b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1365.0247781622177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.4273978126187,
        1374.622158511817
      ],
      "voteCount": 3923,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.97779434174113
      }
    },
    {
      "id": "193014e0f4e01a815157f9a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1385.7703445270963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.7918782625788,
        1394.748810791614
      ],
      "voteCount": 4471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.984959158956407
      }
    },
    {
      "id": "c91ff6f9033a2c25d84ffd54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1282.8956865088617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.1741380308767,
        1335.6172349868464
      ],
      "voteCount": 146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 723.5693010537746
      }
    },
    {
      "id": "3a0466615fe6ddc3bdca7eca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1278.9708833940947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.7001569955055,
        1318.241609792684
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 401.4594516970988
      }
    },
    {
      "id": "096c7744d611a1abf33c7bb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1410.2656323818267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.032111217498,
        1419.4991535461556
      ],
      "voteCount": 4255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.194149949706404
      }
    },
    {
      "id": "4d3dbe928e264b49d220c8c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1392.7996836354755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.4110516349274,
        1411.1883156360234
      ],
      "voteCount": 1010,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.02431644717724
      }
    },
    {
      "id": "9d4ce4a6f83600b94d0b3020",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1391.3534703998328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.0954334337894,
        1402.6115073658764
      ],
      "voteCount": 2873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.99355850075239
      }
    },
    {
      "id": "d766a6c8d58753b690e67cbe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1384.9797643551258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.7436575377606,
        1390.215871172491
      ],
      "voteCount": 17138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.137084082526714
      }
    },
    {
      "id": "a4a4515bf73a3852932e7b8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1383.3061548007327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.4523814560885,
        1396.1599281453766
      ],
      "voteCount": 1914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.00956925672026
      }
    },
    {
      "id": "989be4ce4ae850a235b06f12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.1-preview",
      "organization": "minimax",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1378.9671984133024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.9628517736242,
        1408.9715450529804
      ],
      "voteCount": 410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 234.35388983586495
      }
    },
    {
      "id": "e9e401def15d961c7316d757",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1434.2642351181946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.7797987938557,
        1448.7486714425338
      ],
      "voteCount": 1893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.614381001206596
      }
    },
    {
      "id": "7d4cd126d1454ef45f6da17f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1444.0035411545568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.025745572962,
        1450.9813367361517
      ],
      "voteCount": 9266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.674776289734112
      }
    },
    {
      "id": "6a9da8aeae085d69078d14a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1359.6955614711842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.2214288772143,
        1368.169694065154
      ],
      "voteCount": 5746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.693659511155996
      }
    },
    {
      "id": "df39fb9545d465da4f531ac8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1414.9648982575122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.4888639384785,
        1420.4409325765457
      ],
      "voteCount": 16738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.806136486923307
      }
    },
    {
      "id": "abfcfa2baca7bdaf67733bba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1370.0207644377824,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.2802644623293,
        1375.7612644132355
      ],
      "voteCount": 26800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.578340028182883
      }
    },
    {
      "id": "e74965f01e456bdf7874b56c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1422.4437045936397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.013014190927,
        1433.8743949963527
      ],
      "voteCount": 3005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.013297859343204
      }
    },
    {
      "id": "d6fe37fc41ce9fe6b4889ecb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1409.382257795434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.1549951187528,
        1430.609520472115
      ],
      "voteCount": 1025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.29832383401704
      }
    },
    {
      "id": "2b93c013b53a5d5b88d8ce47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1382.8034751409953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.6184950052793,
        1408.9884552767114
      ],
      "voteCount": 563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.48770915210673
      }
    },
    {
      "id": "fd775968c08eb80b42465419",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1430.2457031969518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.6487454210123,
        1436.8426609728915
      ],
      "voteCount": 10603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.328990867502455
      }
    },
    {
      "id": "0241960cc8c03e277d9f52fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1415.9358415545394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.785849898588,
        1421.0858332104906
      ],
      "voteCount": 22075,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.904255725322729
      }
    },
    {
      "id": "66c1112ab67dbc3b6e998523",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1400.0371465477863,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.1712480425504,
        1407.9030450530222
      ],
      "voteCount": 6917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.106474696894878
      }
    },
    {
      "id": "91633f2d64240b2139f662b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1360.895395275826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.1340187616631,
        1368.656771789989
      ],
      "voteCount": 6961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.681273236638956
      }
    },
    {
      "id": "20c9e122e118880b7564150c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1404.692286047376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.5075059705546,
        1416.8770661241974
      ],
      "voteCount": 2768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.6490842282868
      }
    },
    {
      "id": "422305dfcbbda756477c1365",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1406.9797244001277,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.5980748973661,
        1415.361373902889
      ],
      "voteCount": 5897,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.287856688373264
      }
    },
    {
      "id": "b4b400df61a2c6cc2d489176",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1400.6253477013327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.7374678115866,
        1414.513227591079
      ],
      "voteCount": 1925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.208323669382395
      }
    },
    {
      "id": "3d5fa86b7b9fe49bbb6ad375",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1410.0656769346342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.457769428142,
        1422.6735844411264
      ],
      "voteCount": 2650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.37993900544765
      }
    },
    {
      "id": "2f20cfe99f26a05ffc2e0bb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1435.5645662001918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.609040247576,
        1441.5200921528078
      ],
      "voteCount": 13625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.233026052814088
      }
    },
    {
      "id": "4d086626c16bec1106f851c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1372.368957224588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.3030214133264,
        1379.4348930358497
      ],
      "voteCount": 8495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.997002237771666
      }
    },
    {
      "id": "05c3598e543c7f1c789dab68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1382.3427189526676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.003814165787,
        1388.6816237395485
      ],
      "voteCount": 11221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.460014221857577
      }
    },
    {
      "id": "4a73624236e722785c222616",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1197.6551750258986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.7233978306185,
        1242.5869522211788
      ],
      "voteCount": 277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 525.5463343900933
      }
    },
    {
      "id": "13c11cd0d883a06f7a0fa9b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1273.0478080714158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.0575099148741,
        1300.0381062279575
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.6352996561333
      }
    },
    {
      "id": "7b4205cf890d9cca7ce96c34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1403.0951492989818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.7613783565632,
        1409.4289202414006
      ],
      "voteCount": 12634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.443078065790303
      }
    },
    {
      "id": "9fd73bec79f1f6c616957dcd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1398.312528392029,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.687770751547,
        1410.9372860325109
      ],
      "voteCount": 2188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.490619298661805
      }
    },
    {
      "id": "659a46a2040aafce4b5f8324",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1394.9922387399415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.957246595728,
        1403.0272308841552
      ],
      "voteCount": 6414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.80640136236229
      }
    },
    {
      "id": "b6e7ac938ef81f9808e64c83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1391.0088419917251,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.8519201813115,
        1395.165763802139
      ],
      "voteCount": 36265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.498290817229463
      }
    },
    {
      "id": "ba351fb10ce83cfe168a5919",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1389.370687885282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.392532477409,
        1399.348843293155
      ],
      "voteCount": 3925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.91817067185766
      }
    },
    {
      "id": "dbefbd1ea0709ed5f97d281e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.5",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1373.742336422083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.0231642618596,
        1393.4615085823068
      ],
      "voteCount": 1130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.22345932482911
      }
    },
    {
      "id": "c5767da4ef016b7a5a0ee0e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1437.078792464846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.9367719175868,
        1455.220813012105
      ],
      "voteCount": 1180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.67914557982913
      }
    },
    {
      "id": "2557046d02dbf8008cfeae85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1474.9647931585444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.9689733450446,
        1482.960612972044
      ],
      "voteCount": 6572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.642931103554897
      }
    },
    {
      "id": "ba8230852515749dd2266d12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1355.902901338047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.8840832918104,
        1366.9217193842835
      ],
      "voteCount": 3320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.606313331280308
      }
    },
    {
      "id": "a354d1d971db554b43d7f61a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1432.2924178130042,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.7883091095787,
        1438.7965265164298
      ],
      "voteCount": 10475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.01233463654125
      }
    },
    {
      "id": "bfceb009a40d5000af26fbca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1400.4385674609987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.8009212360614,
        1407.0762136859362
      ],
      "voteCount": 17205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.469170818669658
      }
    },
    {
      "id": "cbbf2d752db6d730fdded872",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1447.5260680597942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.576212756362,
        1461.475923363226
      ],
      "voteCount": 1911,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.657438246735126
      }
    },
    {
      "id": "cf9028fe2554d375cc496827",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1439.936472377987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.3798627392098,
        1463.4930820167642
      ],
      "voteCount": 803,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.45393887457124
      }
    },
    {
      "id": "193401a8fc7362e3af5de13f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1396.4770329584062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.5510020996242,
        1427.403063817188
      ],
      "voteCount": 393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.9729629603356
      }
    },
    {
      "id": "ceb27a60d9e5a02e5fa4ce01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1451.134151910487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.3750768643854,
        1458.8932269565885
      ],
      "voteCount": 6947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.671974731765449
      }
    },
    {
      "id": "0695aa2a458bed559b1b49c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1438.1800276053223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.2104433778466,
        1444.149611832798
      ],
      "voteCount": 14569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.276667410035431
      }
    },
    {
      "id": "b5663a57e10ce99ef0b0399b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1422.0776698495943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.7511047666324,
        1431.4042349325562
      ],
      "voteCount": 4570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.643693530732257
      }
    },
    {
      "id": "609559540f75c733ed147ab7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1368.0862704080212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.3537782956153,
        1377.818762520427
      ],
      "voteCount": 4281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.657664480945208
      }
    },
    {
      "id": "1431b12aa87def21997aef99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1418.2531916978571,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.1576284823739,
        1433.3487549133404
      ],
      "voteCount": 1690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.320180022514734
      }
    },
    {
      "id": "74da377aab2ffd63502c2639",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1421.2611620562386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.0448328029859,
        1431.4774913094914
      ],
      "voteCount": 3735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.170246586687774
      }
    },
    {
      "id": "b8f39361dbf09d6c4e3d96c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1438.6869674050592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.397910944973,
        1455.9760238651454
      ],
      "voteCount": 1242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.81196863800737
      }
    },
    {
      "id": "6e42358ef1cbf932250b7d37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1423.541622631663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3468200682669,
        1439.7364251950587
      ],
      "voteCount": 1539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.27396630012177
      }
    },
    {
      "id": "3c18980bff3dc8a3e3980c3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1466.8666776190748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.0118342952885,
        1473.721520942861
      ],
      "voteCount": 9343,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.232039750244338
      }
    },
    {
      "id": "dfe8d0351e033102ac9bd159",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1377.991675606293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.1914453879822,
        1386.7919058246039
      ],
      "voteCount": 5089,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.160063015142835
      }
    },
    {
      "id": "a3e880299590dc6ef47a0e28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1406.0885647800314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.4809794409389,
        1413.6961501191242
      ],
      "voteCount": 7143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.065983365434091
      }
    },
    {
      "id": "b2d4f22ea1354eaa36d516e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1242.497631169117,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.1935877470164,
        1289.8016745912178
      ],
      "voteCount": 184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 582.5059250994777
      }
    },
    {
      "id": "307fe0685f93d38ae0bde781",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1322.0504988048851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.3036948418126,
        1352.797302767958
      ],
      "voteCount": 399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 246.09555850264064
      }
    },
    {
      "id": "ed007c6bfcca5e978773b5cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1429.487365491001,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.138668009507,
        1436.836062972495
      ],
      "voteCount": 8393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.058032949252631
      }
    },
    {
      "id": "f45fcc3d166f8a40dc913ff8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1414.6083343018931,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.6285933893578,
        1430.5880752144285
      ],
      "voteCount": 1378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.47269476277113
      }
    },
    {
      "id": "4b91b8c073c1c8e745ae886c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1423.3403785996325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.5694192763121,
        1433.1113379229525
      ],
      "voteCount": 4130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.852966165787517
      }
    },
    {
      "id": "cdb83edd419c05043ef93fe6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1413.1093581682635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.139549018238,
        1418.0791673182891
      ],
      "voteCount": 23278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.429589419161087
      }
    },
    {
      "id": "a4cf74d43f8749e84bc5f6d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1396.3488586088436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.4082435989262,
        1408.289473618761
      ],
      "voteCount": 2660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.11566190609361
      }
    },
    {
      "id": "f097fdb68a4825a2687573e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2.7",
      "organization": "minimax",
      "license": "Modified MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1422.925065369615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.0008192030143,
        1445.8493115362153
      ],
      "voteCount": 737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.80247188278852
      }
    },
    {
      "id": "3bb0686f53f35119a0462d67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1388.5351118684744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.6809855255174,
        1423.3892382114318
      ],
      "voteCount": 278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 316.23666420334587
      }
    },
    {
      "id": "d7a92b67062113b377b6a73c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1384.320353230827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.1775262028482,
        1399.4631802588056
      ],
      "voteCount": 1547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.69222139360218
      }
    },
    {
      "id": "5b62b69eeff3cc9b64aaeeed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1287.922649763419,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.5426918266621,
        1308.3026077001757
      ],
      "voteCount": 899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.12108235197067
      }
    },
    {
      "id": "4245ee24cc5f7db06eb5eb90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1370.8299075829827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.489915409085,
        1381.1698997568806
      ],
      "voteCount": 3370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.83198861336483
      }
    },
    {
      "id": "34abb3039f7df8afaa83f08e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1303.788075661896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.0792831289168,
        1314.4968681948753
      ],
      "voteCount": 5011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.852783243858696
      }
    },
    {
      "id": "ed13d2bb7af46e807459b6ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1339.0245646388125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.5661949224202,
        1374.4829343552046
      ],
      "voteCount": 258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 327.29648855566325
      }
    },
    {
      "id": "cb2685e297f29b1821d70865",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1387.4292709273936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9327585837557,
        1400.9257832710314
      ],
      "voteCount": 1905,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.4184037742863
      }
    },
    {
      "id": "58f00fc41b545c6c8e177f0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1368.7559888832488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.8220421739388,
        1378.6899355925589
      ],
      "voteCount": 3698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.689016030003557
      }
    },
    {
      "id": "f1825fccafe8f50e3a68bd47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1349.4125878838383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.8577597786104,
        1365.9674159890662
      ],
      "voteCount": 1315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.34329596799458
      }
    },
    {
      "id": "45ea7e1976165b90f455bec6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1301.9135212993256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.6851931455165,
        1319.1418494531347
      ],
      "voteCount": 1181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.26629513151948
      }
    },
    {
      "id": "f7044dc3d92ff86e5adc629c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1356.2168673963256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.0892134330697,
        1384.3445213595817
      ],
      "voteCount": 429,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.95428830699035
      }
    },
    {
      "id": "0ce0e52cd7fa21b1f6b3342a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1356.9477599378524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.7402467722939,
        1375.1552731034112
      ],
      "voteCount": 1111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.29886487084289
      }
    },
    {
      "id": "4daeef1b26071c02909b19dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1372.5370180746115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.916175257533,
        1407.1578608916898
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 312.0175988632022
      }
    },
    {
      "id": "3873ae9f82af2a954eb815a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1364.084858641851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.7693932662316,
        1397.4003240174702
      ],
      "voteCount": 325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 288.9319617888108
      }
    },
    {
      "id": "2c8f8c897c4c17386d62b0a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1385.5853027515245,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.5701481241904,
        1397.6004573788591
      ],
      "voteCount": 2470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.580499351199855
      }
    },
    {
      "id": "d75cd288da4410b570097085",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1302.3757652053757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.6446117403036,
        1318.1069186704478
      ],
      "voteCount": 1477,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.4206279157598
      }
    },
    {
      "id": "9ca8f325fecfe606dd61f9d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1339.3661571584285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.3088941025476,
        1352.4234202143093
      ],
      "voteCount": 1986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.38212837061392
      }
    },
    {
      "id": "2a6bd0e71108ea31a8d44edc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1343.037005164399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.0970040053803,
        1357.9770063234178
      ],
      "voteCount": 1588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.10387278631555
      }
    },
    {
      "id": "8b0a54a258d56389be19f34d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1356.73991925449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.4445806194435,
        1390.035257889536
      ],
      "voteCount": 318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 288.582964588982
      }
    },
    {
      "id": "50addcff18b3078b4e8d6383",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1364.7243857867693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.1441682386098,
        1382.3046033349287
      ],
      "voteCount": 1120,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.4548645362718
      }
    },
    {
      "id": "c232a6cb3c570a2cd6f3eca9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1346.3265183404928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.5951287348398,
        1354.057907946146
      ],
      "voteCount": 6875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.560334764593698
      }
    },
    {
      "id": "73c8d92d94575c207cf27eca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1334.0990399614489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.0839841795344,
        1366.1140957433634
      ],
      "voteCount": 324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 266.81629156027026
      }
    },
    {
      "id": "6b22d678a0eec762ba44df6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "minimax-m2",
      "organization": "minimax",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1310.7663039511092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.06699265815,
        1358.4656152440684
      ],
      "voteCount": 173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 592.281319160807
      }
    },
    {
      "id": "eba56282b228141414713648",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1254.6097866455848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.0290262126282,
        1280.1905470785414
      ],
      "voteCount": 478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.34552103049077
      }
    },
    {
      "id": "eeb62650a38c313b01e42857",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1274.1981983430533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.423940689683,
        1292.9724559964234
      ],
      "voteCount": 838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.75492095251388
      }
    },
    {
      "id": "120685243a4756ec78850588",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1221.0794501140251,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.0232338676708,
        1243.1356663603794
      ],
      "voteCount": 678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.63852401209424
      }
    },
    {
      "id": "f07a9043b7906c5823910906",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1257.221406052795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.2415014712865,
        1269.201310634303
      ],
      "voteCount": 2322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.36031556785195
      }
    },
    {
      "id": "e09476f43657f1621cc04e58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1126.3631789733017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1111.2568200052197,
        1141.469537941384
      ],
      "voteCount": 3020,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.40505727751672
      }
    },
    {
      "id": "ef977a11c66383e25d591b19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1235.2927679089562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.1252387819577,
        1265.4602970359545
      ],
      "voteCount": 332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.9099490864378
      }
    },
    {
      "id": "d0fe3597b93b358668c668b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1266.4043313034563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.1913026138004,
        1286.617359993112
      ],
      "voteCount": 703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.35712834089946
      }
    },
    {
      "id": "5281323c3543b8f724648b5f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1250.4736676596285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.1881150903093,
        1265.759220228948
      ],
      "voteCount": 1257,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.82275725324637
      }
    },
    {
      "id": "de30e9acc97235a0fcaaa4bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1236.0192829985403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.3726783729887,
        1259.665887624092
      ],
      "voteCount": 572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.55978247246273
      }
    },
    {
      "id": "c054480671c08af614cb3142",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1189.255391908201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.963843112972,
        1209.5469407034302
      ],
      "voteCount": 773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.1850491513957
      }
    },
    {
      "id": "2bc8a80c48ad02f0576201de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1270.3448510959938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.5715616610328,
        1304.1181405309553
      ],
      "voteCount": 324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 296.92758207194913
      }
    },
    {
      "id": "a2511ba1ccbf0a13453b56ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1249.0072936115193,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.7692281702198,
        1269.245359052819
      ],
      "voteCount": 827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.62076880790866
      }
    },
    {
      "id": "a4a3c8f79b72fc8e602746d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1216.4530758537912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.4812244574105,
        1238.4249272501725
      ],
      "voteCount": 543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.67159413085125
      }
    },
    {
      "id": "be2bbdd2d863f99ca3a48471",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1254.3440433138032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.8123464131556,
        1288.8757402144508
      ],
      "voteCount": 280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 310.41282661016004
      }
    },
    {
      "id": "8c8304c1216874725b8fe74a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1276.874487025932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.1870333466068,
        1292.5619407052573
      ],
      "voteCount": 1252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.06321515546293
      }
    },
    {
      "id": "c68efd46fc9c5d6f2fcfb846",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1224.9444566902525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.3379089770679,
        1240.5510044034368
      ],
      "voteCount": 1350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.40412403012365
      }
    },
    {
      "id": "b7624e0eadd6d297707903ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1210.0801610818953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.2599505607213,
        1222.9003716030693
      ],
      "voteCount": 1946,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.785255674697794
      }
    },
    {
      "id": "60150179b5ce862d00560e19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1258.2598977485586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.8354963938405,
        1278.6842991032768
      ],
      "voteCount": 720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.59316477671895
      }
    },
    {
      "id": "a7584d561b1f688dc248a8fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1213.376367403398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.662856051903,
        1233.0898787548936
      ],
      "voteCount": 683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.1653509630267
      }
    },
    {
      "id": "2ef2c6820d81c9c88b3a71f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1207.2396687665512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.192777321357,
        1226.2865602117454
      ],
      "voteCount": 916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.4391416538625
      }
    },
    {
      "id": "bea6026446205de692425a22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1237.034884527326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.9425144922702,
        1246.127254562382
      ],
      "voteCount": 4781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.520780701599353
      }
    },
    {
      "id": "f197fcd9e107308329667c25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ministral-8b-2410",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1243.9205257524764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.0132684670093,
        1263.8277830379434
      ],
      "voteCount": 760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.16364462763525
      }
    },
    {
      "id": "59a7405fe339a9535806dfdc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1099.596518619882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.3072589672543,
        1114.88577827251
      ],
      "voteCount": 1998,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.85226254832834
      }
    },
    {
      "id": "06c16b97fa4dd9044c058496",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1184.1597357644387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.4122291366093,
        1195.907242392268
      ],
      "voteCount": 3114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.924870840072366
      }
    },
    {
      "id": "5304f168e7ae31f53bb76645",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1103.8845702978351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.3168775246768,
        1116.4522630709935
      ],
      "voteCount": 2952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.1163854704438
      }
    },
    {
      "id": "cecde9f0b79548d08237bfc9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1188.703651960317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.9230595472359,
        1196.4842443733985
      ],
      "voteCount": 12723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.759017895071485
      }
    },
    {
      "id": "1c4a1830af323f3d46adafd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 998.819947109528,
      "unit": "Arena rating",
      "confidenceInterval": [
        988.5754491115495,
        1009.0644451075066
      ],
      "voteCount": 12729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.320282249341755
      }
    },
    {
      "id": "4cab8fb494198591db1e4c91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1135.4854367783082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.7756196335304,
        1156.195253923086
      ],
      "voteCount": 798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.64938795117219
      }
    },
    {
      "id": "0d093e3411a442b5a86e8e1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1118.4576633931747,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.779690029195,
        1151.1356367571543
      ],
      "voteCount": 473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.9803176398515
      }
    },
    {
      "id": "57a2eb9b12aaed9ecfcd3458",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1050.2476967618463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1022.6833316947952,
        1077.8120618288976
      ],
      "voteCount": 564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.7879386488874
      }
    },
    {
      "id": "ea933f54e63783009c88eeba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1174.2227297573716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.0718292970273,
        1185.3736302177158
      ],
      "voteCount": 3709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.368583624185725
      }
    },
    {
      "id": "9b2c1771ddd98e353c09bb47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1154.9438903377845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.2034839739383,
        1164.684296701631
      ],
      "voteCount": 5150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.69778294166771
      }
    },
    {
      "id": "7d86dad62ca1ee0207f702a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1131.0394565214633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.3364310779016,
        1146.7424819650248
      ],
      "voteCount": 1743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.19045982030993
      }
    },
    {
      "id": "605b7b4c98c0efa08497c3c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1108.2599627258915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1095.9757676079587,
        1120.544157843824
      ],
      "voteCount": 2920,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.28232912000186
      }
    },
    {
      "id": "80aee59c97124b69e211809b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1185.3792439924214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.8507139170915,
        1205.907774067751
      ],
      "voteCount": 976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.7032577268569
      }
    },
    {
      "id": "0a9848beb907bbde2380585f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1171.949928112374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.3600865846229,
        1184.539769640125
      ],
      "voteCount": 3284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.261436629234744
      }
    },
    {
      "id": "eccfd3f8bab8f2dd9b7b350d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1134.4453373064644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.5151441447456,
        1147.3755304681831
      ],
      "voteCount": 2193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.52250095685052
      }
    },
    {
      "id": "481b7c92d67478606bd189fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1177.1021834107578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.3661441783297,
        1195.8382226431859
      ],
      "voteCount": 1091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.38173347792291
      }
    },
    {
      "id": "421c98cda20b30434dc773c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1176.1056262211312,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.025504386444,
        1186.1857480558183
      ],
      "voteCount": 5226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.450591024108544
      }
    },
    {
      "id": "bd0947639ed7ee13dad1dc82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1112.6361646382225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.0515968390341,
        1123.220732437411
      ],
      "voteCount": 4703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.16420056153898
      }
    },
    {
      "id": "c3366db385be033a0a03b915",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1121.268603195298,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.2323148335342,
        1130.304891557062
      ],
      "voteCount": 6659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.256119398462097
      }
    },
    {
      "id": "240934223c21f9d5ff520d22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 943.6959884398569,
      "unit": "Arena rating",
      "confidenceInterval": [
        896.8703889676701,
        990.5215879120437
      ],
      "voteCount": 167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 570.782316894254
      }
    },
    {
      "id": "b71d594d51ca695f74fe2642",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1132.3096037579983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.904187516709,
        1147.7150199992875
      ],
      "voteCount": 1592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.78039662663816
      }
    },
    {
      "id": "a58c8da9da612588728b0a69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1126.9286810968924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.746783129983,
        1139.1105790638017
      ],
      "voteCount": 2605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.630802776475754
      }
    },
    {
      "id": "d2fe4fb0a1fc214959ddbe77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1111.6672453104188,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.4728484876405,
        1124.8616421331974
      ],
      "voteCount": 2566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.319269486660616
      }
    },
    {
      "id": "84fd70259f77c39bf2ff16f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1148.5711326656808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.9194069496207,
        1155.222858381741
      ],
      "voteCount": 19402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.517878250664499
      }
    },
    {
      "id": "e7ca8cfdf112ffb7d1a7fdee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1085.979346382573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.5766504854041,
        1103.3820422797423
      ],
      "voteCount": 1203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.83823271978328
      }
    },
    {
      "id": "99e80cb2dcc4bcf08c5cb3aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct-v0.2",
      "organization": "mistral",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1092.2553588912438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1046.2468881158354,
        1138.2638296666519
      ],
      "voteCount": 202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 551.0352920323921
      }
    },
    {
      "id": "7807b46326838fa37556f206",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1037.7699905787372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1003.4371096372162,
        1072.1028715202578
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 306.8487178346629
      }
    },
    {
      "id": "8fd096d74240249562def4b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1142.8555610142212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1123.119330055869,
        1162.5917919725732
      ],
      "voteCount": 1032,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.39866926154585
      }
    },
    {
      "id": "5ef9760b7cbf5bae468412ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1090.5274668577772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1073.6390899014013,
        1107.415843814153
      ],
      "voteCount": 1689,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.24712577528345
      }
    },
    {
      "id": "a529f06f06fd572c9cf1cdc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1141.6214604431375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.445614549311,
        1151.797306336964
      ],
      "voteCount": 7073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.955342875755765
      }
    },
    {
      "id": "ef1733c8abedba7ff97361ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 939.2430221245936,
      "unit": "Arena rating",
      "confidenceInterval": [
        925.4159994831952,
        953.070044765992
      ],
      "voteCount": 5974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.76925799537717
      }
    },
    {
      "id": "00b19462696c7d5bc5e01edf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1079.0953286279127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1039.612200049314,
        1118.5784572065115
      ],
      "voteCount": 183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 405.81391474410816
      }
    },
    {
      "id": "09ee2880854152303a16de08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1059.0868566812337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1010.7613050775476,
        1107.41240828492
      ],
      "voteCount": 175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 607.9354346374486
      }
    },
    {
      "id": "06814a8b8c60f0d1ae129b46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1021.947201942443,
      "unit": "Arena rating",
      "confidenceInterval": [
        976.4416470519348,
        1067.4527568329513
      ],
      "voteCount": 174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 539.0544640847894
      }
    },
    {
      "id": "3557d0bd61280cf93fc0dd05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1131.165057968488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.590460069633,
        1147.7396558673431
      ],
      "voteCount": 1616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.51379419423047
      }
    },
    {
      "id": "9c90f101079d1a35480857ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1112.8318193743182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1097.4936198605,
        1128.1700188881364
      ],
      "voteCount": 1917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.24245379342029
      }
    },
    {
      "id": "7da81d6c6a93227574f1161c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1072.2183346189142,
      "unit": "Arena rating",
      "confidenceInterval": [
        1048.3839687806376,
        1096.052700457191
      ],
      "voteCount": 747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.88053742826784
      }
    },
    {
      "id": "0bd346162c0fd490489618ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1078.5301465886532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1061.09330777492,
        1095.9669854023864
      ],
      "voteCount": 1497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.147886781505
      }
    },
    {
      "id": "5b5bb68093796ea9bfe41add",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1150.6685033167523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.1211583450026,
        1180.2158482885022
      ],
      "voteCount": 487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 227.26928378782824
      }
    },
    {
      "id": "e55e75fff0b6abf7f7d9e549",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1127.6700700964611,
      "unit": "Arena rating",
      "confidenceInterval": [
        1109.7857098474367,
        1145.5544303454858
      ],
      "voteCount": 1577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.26272815781375
      }
    },
    {
      "id": "901c823a001318861ede2208",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1072.400259866257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1051.3730471799604,
        1093.4274725525538
      ],
      "voteCount": 814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.09785578668841
      }
    },
    {
      "id": "39d8cad028a6ae742fe40c50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1140.719270636921,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.9798414307386,
        1168.4586998431034
      ],
      "voteCount": 477,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.30826011712037
      }
    },
    {
      "id": "31f9663450c7e68e8d69019c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1130.096130906853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.1843676405742,
        1146.0078941731317
      ],
      "voteCount": 2096,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.9083494213669
      }
    },
    {
      "id": "587e2cb782b1456def1063c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1093.599979232944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.4839801972134,
        1108.7159782686747
      ],
      "voteCount": 2336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.48089970854415
      }
    },
    {
      "id": "3020d18e3da233a9e6adfaa9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1084.1209844890363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.4614736234064,
        1097.7804953546663
      ],
      "voteCount": 2768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.570672183998035
      }
    },
    {
      "id": "328b133dbd91690b553dc4a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1095.7046944663834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.7096907701434,
        1122.6996981626235
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.7014281747098
      }
    },
    {
      "id": "93c14f31280d73457268bd10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1081.1885058203836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.3435514973055,
        1100.0334601434618
      ],
      "voteCount": 974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.44724986397998
      }
    },
    {
      "id": "26219d40bd0a7bc16adfae49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1079.140269583908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1059.8057391627776,
        1098.4748000050388
      ],
      "voteCount": 1259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.3130479993212
      }
    },
    {
      "id": "b96dfa9c5dfc29ee02df4ff5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1108.7876043237925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.5011001331955,
        1118.07410851439
      ],
      "voteCount": 8977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.44958597952572
      }
    },
    {
      "id": "04c22e255c0169994c786d63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-7b-instruct",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1085.2925387605353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1043.0994963853168,
        1127.4855811357538
      ],
      "voteCount": 175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 463.4314483046598
      }
    },
    {
      "id": "d7ac2d8bd4c75df90035a08b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1208.62761203157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.9334924133104,
        1219.3217316498292
      ],
      "voteCount": 7840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.77103224263507
      }
    },
    {
      "id": "bcfdfc3c09dcab2096e47f6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1293.8951081834168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.3585018209087,
        1302.4317145459252
      ],
      "voteCount": 10418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.970305706738902
      }
    },
    {
      "id": "e23984917fa4b6bc7c542d05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1210.4968358917113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.056892503996,
        1219.9367792794264
      ],
      "voteCount": 9056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.197575536463926
      }
    },
    {
      "id": "a1ef0b95ab334bcd2e5725c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1265.3591915929878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.5582369013855,
        1271.1601462845902
      ],
      "voteCount": 36796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.759972943805455
      }
    },
    {
      "id": "8133867cb82699e60f3984fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1141.0274567332276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.0496810250015,
        1148.0052324414537
      ],
      "voteCount": 41750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.674704092106143
      }
    },
    {
      "id": "39df630f48bb95906123a075",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1224.0957944796742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.3681892408122,
        1237.823399718536
      ],
      "voteCount": 2940,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.05614101050709
      }
    },
    {
      "id": "cc2f2dbda2056be350133b44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1289.0622364382673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.3594209164548,
        1312.76505196008
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.25263210801884
      }
    },
    {
      "id": "0c387c4d07a710d523b193b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1245.159814496318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.175802894845,
        1262.1438260977907
      ],
      "voteCount": 1690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.09039235954728
      }
    },
    {
      "id": "60592aa036cbca6e6c96e667",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1272.397921034481,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.0895131204024,
        1280.706328948559
      ],
      "voteCount": 11296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.969642599018414
      }
    },
    {
      "id": "1ad78ce5bcd16c37f5a8bec1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1260.7074288074145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.7182333968929,
        1267.6966242179365
      ],
      "voteCount": 17187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.716224425811324
      }
    },
    {
      "id": "a9c84387a7aab2ae324dc522",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1221.4952623580543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.2398493773735,
        1231.7506753387356
      ],
      "voteCount": 6461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.378529957875802
      }
    },
    {
      "id": "b857ceb9272a6ed4d8daa41d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1211.847496656149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.8484064783534,
        1220.8465868339445
      ],
      "voteCount": 9175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.08147654527337
      }
    },
    {
      "id": "bf7d10d099d882d160ca9983",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1270.5337483554438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.9986193837276,
        1284.06887732716
      ],
      "voteCount": 3306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.69014190496802
      }
    },
    {
      "id": "1833d92ef693e7ea615e53a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1251.4656580070732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.4548660772211,
        1260.4764499369255
      ],
      "voteCount": 10875,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.136337780244425
      }
    },
    {
      "id": "1a9cd76d4874e0ce87afda68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1241.023976679604,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.651061425489,
        1250.3968919337185
      ],
      "voteCount": 7028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.869317220727766
      }
    },
    {
      "id": "a9f575d234261ab7bb74a50f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1249.22481819838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.5799058425,
        1262.86973055426
      ],
      "voteCount": 3434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.46690850795127
      }
    },
    {
      "id": "5c30a0558050ed41d1af71be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1269.5824497303215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.2686872713793,
        1276.896212189264
      ],
      "voteCount": 17516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.924689500164158
      }
    },
    {
      "id": "a111038755c6a04906671ab9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1224.7044145529576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.983529665616,
        1232.425299440299
      ],
      "voteCount": 15192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.518079517720187
      }
    },
    {
      "id": "3db4597fe43ed2262ab0d48d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1235.319532096697,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.6776447903135,
        1241.9614194030803
      ],
      "voteCount": 21532,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.483831807085767
      }
    },
    {
      "id": "4901a22438a4905d9fd40786",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1079.8852241972684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1057.515582988138,
        1102.2548654063987
      ],
      "voteCount": 945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.2632336261264
      }
    },
    {
      "id": "10ac7e0de506468468b4e1a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1109.907918321995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.9439858678315,
        1132.8718507761587
      ],
      "voteCount": 1090,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.2765447643405
      }
    },
    {
      "id": "1218cde05fc5ca56ea3118a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1244.4994219774194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.49414828902,
        1254.5046956658189
      ],
      "voteCount": 6217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.05924109885164
      }
    },
    {
      "id": "63435eed59de268041101af9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1243.9652261943806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.9583904977,
        1252.972061891061
      ],
      "voteCount": 7987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.117781825483537
      }
    },
    {
      "id": "3a9b572da8b5d6a9c7fb0411",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1224.6931708496536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.4740553819995,
        1233.9122863173077
      ],
      "voteCount": 9521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.1249514762679
      }
    },
    {
      "id": "f5f0ab735e2feadd34db5ee6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1241.4895928920862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.7717750931351,
        1246.2074106910372
      ],
      "voteCount": 62436,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.794102142705535
      }
    },
    {
      "id": "d016cc86ff5e27e7fd941e74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1236.2194852231592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.6202442145131,
        1246.818726231805
      ],
      "voteCount": 5462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.245116296485833
      }
    },
    {
      "id": "00a34363285654cd1955937f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2402",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1256.474089405243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.5851746344993,
        1281.363004175987
      ],
      "voteCount": 886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.25594660244755
      }
    },
    {
      "id": "6e235588a7eb2434ac43d52b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1302.8509691990103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.2769465098331,
        1313.4249918881876
      ],
      "voteCount": 3933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.10611854770099
      }
    },
    {
      "id": "1a5f0d4d5ce040212a0b3660",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1353.3574940348756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.5058433311974,
        1361.2091447385537
      ],
      "voteCount": 7589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.048178999203653
      }
    },
    {
      "id": "7355de8abc16a69800807e89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1286.9269354202754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.2973797015748,
        1295.5564911389763
      ],
      "voteCount": 6692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.385664503545645
      }
    },
    {
      "id": "7dea07b288528a1f57a899b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1336.566456547716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.4776454109588,
        1341.6552676844728
      ],
      "voteCount": 24863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.741188697918448
      }
    },
    {
      "id": "b86e5b1d958f74ff8308206a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1254.020585335024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.828439130798,
        1260.21273153925
      ],
      "voteCount": 28276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.98127961386864
      }
    },
    {
      "id": "dbd157f70e88970d4f837dfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1299.2225948069633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.723848283023,
        1311.7213413309037
      ],
      "voteCount": 2505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.66649467336564
      }
    },
    {
      "id": "bc2d24174fac3794f4b1042e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1330.7931843787928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.526451725355,
        1360.0599170322305
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 222.97301108463537
      }
    },
    {
      "id": "ddb0677392656300eef49ab3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1301.9963607342952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.6099689046632,
        1319.382752563927
      ],
      "voteCount": 1230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.69057953323727
      }
    },
    {
      "id": "bd5f882ce60b12a069e6231d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1333.6015591301061,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.9359705580282,
        1341.267147702184
      ],
      "voteCount": 7818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.296597178087943
      }
    },
    {
      "id": "5e5b2b90f9208121275a3a07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1319.3584222167071,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.0224696358637,
        1325.6943747975504
      ],
      "voteCount": 12682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.450273445711732
      }
    },
    {
      "id": "0e5fd2192d0a57ec7942bc11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1291.1075815271977,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.7395333825862,
        1300.4756296718094
      ],
      "voteCount": 5167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.845572511930396
      }
    },
    {
      "id": "a827c78957d21754740903a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1289.9431379319772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.6995349793751,
        1298.186740884579
      ],
      "voteCount": 7002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.69041210960276
      }
    },
    {
      "id": "12730a114159e8ec88955d30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1339.1411508832803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.8800682622918,
        1351.4022335042691
      ],
      "voteCount": 2735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.13465015656366
      }
    },
    {
      "id": "f63624f4b92ec6b992535834",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1330.7832244678991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.5746469312885,
        1338.9918020045097
      ],
      "voteCount": 7485,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.540405434405674
      }
    },
    {
      "id": "4e2439f86590df688ebedf9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1297.7086058413918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.3376906376845,
        1306.0795210450992
      ],
      "voteCount": 5745,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.241044514176657
      }
    },
    {
      "id": "426ac1e4820288e485ddc07d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1322.8407666464384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.4776066226016,
        1336.203926670275
      ],
      "voteCount": 2423,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.4859976789758
      }
    },
    {
      "id": "8d1629093abd905e777557a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1343.1739261562334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.4875534561222,
        1349.8602988563448
      ],
      "voteCount": 12143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.638177570445748
      }
    },
    {
      "id": "538ebcbcaff8cd218d75d1e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1302.0171196731412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.1767501570384,
        1308.857489189244
      ],
      "voteCount": 12224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.180439072980558
      }
    },
    {
      "id": "6a1a2022ae4194de98a7e475",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1298.2488596605585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.584760055502,
        1303.9129592656152
      ],
      "voteCount": 18321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.35152108443128
      }
    },
    {
      "id": "48892114ab5a56d918267cee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1233.6707287641293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.455917369229,
        1250.8855401590295
      ],
      "voteCount": 1249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.14510169041493
      }
    },
    {
      "id": "d537b94fb672dab759d1627e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1227.1822207537932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.1984763590285,
        1251.165965148558
      ],
      "voteCount": 751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.73998734404475
      }
    },
    {
      "id": "569b4aa052b1e0ca2fedb782",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1303.4547638294327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.7384680743226,
        1312.1710595845427
      ],
      "voteCount": 5885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.777333361293632
      }
    },
    {
      "id": "bd5dfe77d492efbb44302e31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1288.0356474515593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.9925386703217,
        1296.078756232797
      ],
      "voteCount": 6664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.840372859999224
      }
    },
    {
      "id": "f689f34d0db8c98430a9bbd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1296.0468885133703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.152027663405,
        1303.9417493633355
      ],
      "voteCount": 8296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.22530157151379
      }
    },
    {
      "id": "50fe369a3f80bd269b0fcb1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1313.7635971014902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.8471972755146,
        1317.6799969274657
      ],
      "voteCount": 45459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.992802816022409
      }
    },
    {
      "id": "12f88a384a3fd70f9224fa42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1303.0270867774932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.226370892829,
        1311.8278026621574
      ],
      "voteCount": 5748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.162288260215025
      }
    },
    {
      "id": "88ea317ac6d42c2489f215f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2407",
      "organization": "mistral",
      "license": "Mistral Research",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1283.9620581374327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.1302322762526,
        1309.7938839986127
      ],
      "voteCount": 584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.70568278062777
      }
    },
    {
      "id": "14a33faae050221954bfa72e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1296.537829778577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.0275769266514,
        1310.0480826305024
      ],
      "voteCount": 1914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.5150042321637
      }
    },
    {
      "id": "d2d56da56b44c2eabd250fb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1345.7436029504129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.8843745964618,
        1354.602831304364
      ],
      "voteCount": 4212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.43128162786559
      }
    },
    {
      "id": "b1530f918a2a16b4b3a1689b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1276.1460275122822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.13241012539,
        1285.1596448991747
      ],
      "voteCount": 4439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.149595033953666
      }
    },
    {
      "id": "4c8ad3aef3e93b53c9fb19aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1321.2064209738546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.8355679516294,
        1326.5772739960803
      ],
      "voteCount": 16289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.509142628564066
      }
    },
    {
      "id": "66867b183226bb5dfdddaf92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1236.8100327920513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.9435038751499,
        1243.6765617089527
      ],
      "voteCount": 18034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.273779719477943
      }
    },
    {
      "id": "89e88ec8d589ea86c1f55586",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1268.6520420578822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.7134559899896,
        1283.5906281257746
      ],
      "voteCount": 1510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.092866310488255
      }
    },
    {
      "id": "3fee19d685969874ac56b65c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1376.592231132985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.4596168910857,
        1416.7248453748844
      ],
      "voteCount": 204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 419.27476020634975
      }
    },
    {
      "id": "6b1a7fa54ed8cd95562f368e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1284.6327665758783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.1993061141447,
        1307.066227037612
      ],
      "voteCount": 648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.0075603510528
      }
    },
    {
      "id": "cb666da825a9f78bdec265a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1323.7610384767754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.198674689443,
        1332.3234022641077
      ],
      "voteCount": 4452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.08495627538046
      }
    },
    {
      "id": "5519a5d7a87a03cc5f42b8ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1312.878280100732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8616195537834,
        1319.8949406476804
      ],
      "voteCount": 6954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.816361577503294
      }
    },
    {
      "id": "d8f63eb382a000d0fbaf232d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1294.5437756772947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.8473407170452,
        1305.2402106375441
      ],
      "voteCount": 3021,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.783924857529527
      }
    },
    {
      "id": "2ced1080b71819b846ed49f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1271.1508529389107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.8459048377172,
        1279.4558010401042
      ],
      "voteCount": 5130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.954679766957888
      }
    },
    {
      "id": "16227c807d9ff43be4136f2c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1326.3465704521313,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.5033388555498,
        1341.1898020487129
      ],
      "voteCount": 1593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.35360822895524
      }
    },
    {
      "id": "64e4afee3b91aa4cb17f7209",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1314.5620734737918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8756696981714,
        1323.2484772494122
      ],
      "voteCount": 4869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.64191576039882
      }
    },
    {
      "id": "a1666ff38e0053ceb001b374",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1283.5009937492262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.5741725741411,
        1293.4278149243112
      ],
      "voteCount": 3037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.652176228277472
      }
    },
    {
      "id": "81dd82e281d428f6ab4f2c66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1317.133250701021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.432442055227,
        1333.8340593468151
      ],
      "voteCount": 1230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.60705436197588
      }
    },
    {
      "id": "4b933d74aa62b203974035fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1333.6290222825337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.331212649775,
        1340.9268319152925
      ],
      "voteCount": 6815,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.864010502750666
      }
    },
    {
      "id": "934366d199014a41967d86d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1297.392795139961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.2564379050127,
        1304.529152374909
      ],
      "voteCount": 7416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.2573579366379
      }
    },
    {
      "id": "2bb79aa0c37aa4c48b7440ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1293.8791401653145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.8367160030696,
        1299.9215643275595
      ],
      "voteCount": 10971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.5044334615267
      }
    },
    {
      "id": "20b8ba8b600ea224241b8295",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1213.9866776261154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.3952878268565,
        1236.5780674253745
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.85861358520165
      }
    },
    {
      "id": "79838c167f6c1e118868be51",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1259.631733755401,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.7598589089177,
        1289.5036086018845
      ],
      "voteCount": 408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.2890725879819
      }
    },
    {
      "id": "0c9febf3239b3946fb94c8bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1304.3291950952923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.7342767869638,
        1313.9241134036208
      ],
      "voteCount": 3607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.965493746165496
      }
    },
    {
      "id": "67c34de791be87edcc490095",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1282.1880269992546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.9362035418953,
        1291.4398504566138
      ],
      "voteCount": 3574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.282221749985787
      }
    },
    {
      "id": "241659f34ca7735386f99338",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1293.1655402945328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.2214132345584,
        1302.109667354507
      ],
      "voteCount": 4438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.824747211662352
      }
    },
    {
      "id": "cdca71053b02df478cef2424",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1305.0851173265178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.6612410078333,
        1309.5089936452023
      ],
      "voteCount": 28073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.094596244944844
      }
    },
    {
      "id": "fe6ece26a1f416350b6e3bb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1294.1491990528389,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.0755910915789,
        1304.222807014099
      ],
      "voteCount": 3258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.416416807723564
      }
    },
    {
      "id": "553a40495892a7a81bce4bf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-2411",
      "organization": "mistral",
      "license": "MRL",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1303.542006768489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.2228825409156,
        1348.861130996062
      ],
      "voteCount": 153,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 534.6466320789837
      }
    },
    {
      "id": "b39a38161c909fb65d0514a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1426.3995169211207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.7408909848612,
        1440.0581428573803
      ],
      "voteCount": 2025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.564379100373564
      }
    },
    {
      "id": "22f90125b205ac933bf15db5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1467.8708496331212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.3569722488494,
        1474.3847270173928
      ],
      "voteCount": 9554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.045438870449752
      }
    },
    {
      "id": "a04bae9520b44bee53a5bcd4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1376.6883436656396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.7845954337101,
        1384.592091897569
      ],
      "voteCount": 6517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.261852340366833
      }
    },
    {
      "id": "002b8725f9216c1114b23070",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1428.5993333059102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.6357615860243,
        1433.5629050257962
      ],
      "voteCount": 19885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.4134604504235275
      }
    },
    {
      "id": "0a160e125b05f8a5600e2b13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1402.5754904448554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.3633871012253,
        1407.7875937884855
      ],
      "voteCount": 29812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.071798119593544
      }
    },
    {
      "id": "152d1f027bf6d48985de550d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1420.6536484179894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.4789103826524,
        1431.8283864533264
      ],
      "voteCount": 2964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.50712190007119
      }
    },
    {
      "id": "2c800ca0be0c016dad124436",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1449.9021871862526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.836965713017,
        1470.9674086594882
      ],
      "voteCount": 976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.51433359795425
      }
    },
    {
      "id": "d08211425380d4242a9e107a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1402.0408652964475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.501266538814,
        1425.580464054081
      ],
      "voteCount": 688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.24538581159493
      }
    },
    {
      "id": "5c93bb11ae15dfa42f1098fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1440.35886036551,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.216511608074,
        1446.5012091229464
      ],
      "voteCount": 11512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.821385577461536
      }
    },
    {
      "id": "2890e24ce749b1cd40d6beac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1432.1019975070674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.4250533908044,
        1436.7789416233304
      ],
      "voteCount": 23584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.694140504334622
      }
    },
    {
      "id": "a3ca0d783c01317019b661de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1412.8316759750955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.6051147523424,
        1420.0582371978485
      ],
      "voteCount": 7893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.594623694745746
      }
    },
    {
      "id": "0cd844237edfa6069fb44941",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1372.0981881442212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.9415794019337,
        1379.2547968865088
      ],
      "voteCount": 7935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.332707984341193
      }
    },
    {
      "id": "25d512d4ab7875f3085af5c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1424.177377431155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.2206392685853,
        1435.1341155937248
      ],
      "voteCount": 3048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.251177421555475
      }
    },
    {
      "id": "e768090ed47ffa37eb120478",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1428.942598644394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.4525423088983,
        1436.4326549798895
      ],
      "voteCount": 6847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.604072704536293
      }
    },
    {
      "id": "f1f322b4199e6bbb80bb014b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1414.0185218972847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.2855437281708,
        1427.7515000663989
      ],
      "voteCount": 1911,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.09454928356721
      }
    },
    {
      "id": "29a3360a7f3edac5762ec0dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1432.0903900606943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.52656301537,
        1443.654217106019
      ],
      "voteCount": 2840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.81023803087831
      }
    },
    {
      "id": "c928bf7be6fb08eee17a7585",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1454.5064935960354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.0195863632318,
        1459.9934008288392
      ],
      "voteCount": 14979,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.837166135742567
      }
    },
    {
      "id": "a6cb4db38c2973cd653588d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1394.1350390301932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.543151841793,
        1400.7269262185937
      ],
      "voteCount": 9712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.311582066301055
      }
    },
    {
      "id": "b570b3ae40edc20c45f3b286",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1404.7371565498765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.7241717677696,
        1410.7501413319835
      ],
      "voteCount": 11837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.412045703854961
      }
    },
    {
      "id": "1209757c720293db5c944c14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1364.1377076129068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.9871968832854,
        1398.2882183425281
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 303.5975231105677
      }
    },
    {
      "id": "c07e744edd22aa820e6ddd0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1347.6274606347126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.9164753745972,
        1372.338445894828
      ],
      "voteCount": 648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.95856783265054
      }
    },
    {
      "id": "68f507ac2eb579dbc2d79e77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1416.7474493473414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.6485172407936,
        1422.846381453889
      ],
      "voteCount": 11900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.683033081051853
      }
    },
    {
      "id": "77f8ef53549c25427dbfead2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1402.2263729214656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.848501030846,
        1413.6042448120854
      ],
      "voteCount": 2737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.699689311250516
      }
    },
    {
      "id": "2034c024a0dc49f99e571015",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1421.3672786791878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.9952972999838,
        1428.739260058392
      ],
      "voteCount": 7332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.14725811000883
      }
    },
    {
      "id": "0244c273d540c601c589a653",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1415.3796225810968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.7648255768688,
        1418.9944195853247
      ],
      "voteCount": 42553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.4015091640145885
      }
    },
    {
      "id": "ba0b85d5805e204283725c08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1404.630548117759,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.5770261613973,
        1413.6840700741207
      ],
      "voteCount": 4310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.337274103464985
      }
    },
    {
      "id": "69dffa3cd29e9a13d3d9981e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-large-3",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1415.3021625961696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.2060965921096,
        1434.3982286002297
      ],
      "voteCount": 1120,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.92741009404511
      }
    },
    {
      "id": "024787b15f412f038609f605",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1388.3446723662041,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.6995030245116,
        1402.9898417078966
      ],
      "voteCount": 1648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.833212083761126
      }
    },
    {
      "id": "d95de68c945f08f41be7658e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1433.1396818077365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.1660671816917,
        1441.113296433781
      ],
      "voteCount": 5900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.5506213062007
      }
    },
    {
      "id": "a4c699230a213653d077c778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1364.4174232112837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.8539944703257,
        1373.9808519522414
      ],
      "voteCount": 4080,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.80844714270631
      }
    },
    {
      "id": "53cada41dc00d925afe75130",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1402.6673349717564,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.9261983364638,
        1408.408471607049
      ],
      "voteCount": 16691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.580242924260585
      }
    },
    {
      "id": "83a4eceba9fb5e39372b3ccf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1365.3778523907513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.9398698168893,
        1371.8158349646135
      ],
      "voteCount": 23103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.789551979074146
      }
    },
    {
      "id": "d8c9db39ed77ceb1f9fdda06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1380.515633744052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.8472842319861,
        1394.1839832561177
      ],
      "voteCount": 1766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.63354967585733
      }
    },
    {
      "id": "999adac0e29bd515a580972a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1393.7245282050949,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.6459030870367,
        1421.8031533231533
      ],
      "voteCount": 454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.23692308590105
      }
    },
    {
      "id": "a21d6b53aecfbf5d4dbb90ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1392.740568097931,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.577598282811,
        1411.9035379130507
      ],
      "voteCount": 942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.59373906521282
      }
    },
    {
      "id": "38ec9b7cf7f8cea910963f0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1411.8545763454592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.4872229815787,
        1419.2219297093397
      ],
      "voteCount": 7334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.12950082814514
      }
    },
    {
      "id": "a58683167f079657a2fe0c57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1401.1178536309376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.161849673553,
        1407.073857588322
      ],
      "voteCount": 13734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.234508241837801
      }
    },
    {
      "id": "6c4a6a1e953fcc737b8955fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1386.7270655487848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.0394524533347,
        1395.4146786442352
      ],
      "voteCount": 5143,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.647385230228885
      }
    },
    {
      "id": "2e18253592ce42038a0e8b11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1354.9381641193238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.765983327114,
        1363.1103449115335
      ],
      "voteCount": 5629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.38520234573101
      }
    },
    {
      "id": "c959a6403032da6e9ae24f79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1409.23011623686,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.4147318369742,
        1422.0455006367463
      ],
      "voteCount": 2139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.75304903233738
      }
    },
    {
      "id": "f29b4817ad93c1b98dfa3307",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1407.5658850152888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.2119750420522,
        1415.9197949885254
      ],
      "voteCount": 5688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.167007665158458
      }
    },
    {
      "id": "3eb0f218b795afedeab6b8f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1355.5840539242467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.319092768409,
        1367.8490150800844
      ],
      "voteCount": 2192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.159412914655505
      }
    },
    {
      "id": "2df52e5eb77478badc213100",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1418.9958842628412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.2962054486177,
        1432.6955630770647
      ],
      "voteCount": 1990,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.856751659508994
      }
    },
    {
      "id": "c76dc0ae467b1e54d581d299",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1421.679332008919,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.1832136805099,
        1428.175450337328
      ],
      "voteCount": 10814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.985293688262376
      }
    },
    {
      "id": "c36ff6f5cc2c165f49f911a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1369.9353487446176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.4037565728195,
        1377.4669409164158
      ],
      "voteCount": 7210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.766494524609017
      }
    },
    {
      "id": "f227081500b83eab646d0fbd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1366.2539657050015,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.1133970636472,
        1373.394534346356
      ],
      "voteCount": 7938,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.273009786600047
      }
    },
    {
      "id": "d3e19f05086dd466880a7a60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1321.1056512476036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.9230562837934,
        1342.2882462114142
      ],
      "voteCount": 802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.80519051347446
      }
    },
    {
      "id": "8e4fca0b623e527d106ceeef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1314.7433436388085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.1194129583628,
        1339.3672743192542
      ],
      "voteCount": 606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.8405471611511
      }
    },
    {
      "id": "02b4d6d32de91c02b371a3af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1390.7001323202644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.6605322026344,
        1398.7397324378946
      ],
      "voteCount": 5905,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.825683436512833
      }
    },
    {
      "id": "5247172515ef9c2e9437fd99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1349.0435806004643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.97111632547,
        1361.116044875459
      ],
      "voteCount": 2229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.93985578756905
      }
    },
    {
      "id": "ca77ea523fea4d22c25f37ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1403.1804944868256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.0000396323562,
        1411.360949341295
      ],
      "voteCount": 5828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.420424049715578
      }
    },
    {
      "id": "6dcb3e871220b46b5be9a0a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1386.721575522945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.0306388150466,
        1391.4125122308435
      ],
      "voteCount": 33230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.728263200159519
      }
    },
    {
      "id": "bf822f368a85144341eb4797",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1382.9709661357595,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.2261557111506,
        1394.715776560368
      ],
      "voteCount": 2353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.90838229656493
      }
    },
    {
      "id": "cf6d1831af8e401f7b71f0e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2505",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1378.6313343447139,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.9921870997105,
        1406.2704815897175
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.86259259521321
      }
    },
    {
      "id": "3a80dba8e5d9c7d87517a21d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1430.670586310268,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.3104355657767,
        1440.030737054759
      ],
      "voteCount": 4684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.807070451366965
      }
    },
    {
      "id": "0ada76aab6a26921c44d0f7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1456.121761333887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.3584803514968,
        1460.8850423162771
      ],
      "voteCount": 20392,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.906309757890434
      }
    },
    {
      "id": "066aa3cc7246bf898c8a94a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1380.9487022700696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.2072912716128,
        1386.6901132685264
      ],
      "voteCount": 13462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.581063026270828
      }
    },
    {
      "id": "31e9a7256192b4f9ce06d7e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1425.4551766054128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.8888551775105,
        1429.021498033315
      ],
      "voteCount": 43439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.3108902426857583
      }
    },
    {
      "id": "1b8225c818b24e4b070ebd1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1395.1827368012373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.3739433933888,
        1398.9915302090856
      ],
      "voteCount": 65644,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.7764057616653126
      }
    },
    {
      "id": "158a615ab38b8fa84e973c99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1414.475426673956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.221321554451,
        1422.7295317934613
      ],
      "voteCount": 5824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.73551520501044
      }
    },
    {
      "id": "4af9c12766d605ab57253276",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1434.170920775819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.8262765065379,
        1450.5155650451002
      ],
      "voteCount": 1836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.5432148979989
      }
    },
    {
      "id": "6d7d1f1bdfba85514973e347",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1396.693043456109,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.8221550760136,
        1412.5639318362046
      ],
      "voteCount": 1647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.57016741049817
      }
    },
    {
      "id": "316d50ae429e9876aff85064",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1438.7739148335215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.347953639104,
        1443.199876027939
      ],
      "voteCount": 24955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.099399319071498
      }
    },
    {
      "id": "7a60092f35df4110a57f17b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1429.301462717703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.8299899972649,
        1432.7729354381415
      ],
      "voteCount": 49970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.1371214455890795
      }
    },
    {
      "id": "2ed7d69ddcb390ad9b49bd14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1406.8178310393978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.6372790392518,
        1411.9983830395438
      ],
      "voteCount": 17045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.9864393395649085
      }
    },
    {
      "id": "9970bf28d6ab9c64371b9d0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1375.0997585833707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.9513527739136,
        1380.2481643928274
      ],
      "voteCount": 17091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.900004299424035
      }
    },
    {
      "id": "29ceb698411de40b0eb161ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1416.2049103610555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.278647676819,
        1424.1311730452917
      ],
      "voteCount": 6370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.354630642159385
      }
    },
    {
      "id": "08eb8ad5d3214ea712c2a884",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1427.123674317963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.6578673801432,
        1432.5894812557826
      ],
      "voteCount": 14546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.777005267004235
      }
    },
    {
      "id": "b5ddc9f593646d3eadaa5e10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1407.449887520333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.4184961888066,
        1416.4812788518593
      ],
      "voteCount": 4657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.23308700948944
      }
    },
    {
      "id": "bea5a8281b099a6df26ef016",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1432.2737590535369,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.7393200757547,
        1440.808198031319
      ],
      "voteCount": 5690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.960674073379096
      }
    },
    {
      "id": "7bae5274e6dd9ea9105f6e4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1441.5624847660356,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.580202984523,
        1445.5447665475483
      ],
      "voteCount": 32666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.128267131730399
      }
    },
    {
      "id": "a9fb74ee59457ea3469ec25a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1388.1616951836288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.4285165498677,
        1392.8948738173897
      ],
      "voteCount": 20861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.831893825961565
      }
    },
    {
      "id": "752eb7409a60874d3a5ef79a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1398.4010648256294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.0993919695725,
        1402.7027376816864
      ],
      "voteCount": 25887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.817021403653295
      }
    },
    {
      "id": "5ac078edd81f3de9115cb7df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1353.9646159160868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.7876033544992,
        1374.1416284776747
      ],
      "voteCount": 974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.97844592719186
      }
    },
    {
      "id": "b60d7aec40d2b7e63e528f8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1344.1725647631072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.7440519181919,
        1359.6010776080225
      ],
      "voteCount": 1837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.96578428054165
      }
    },
    {
      "id": "54daa1a746e275f9d2055f5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1411.7995502939232,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3199238592329,
        1416.2791767286135
      ],
      "voteCount": 25190,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.223810518617274
      }
    },
    {
      "id": "f107496058d8d1a322edb8f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1398.9680597341026,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.9711574366966,
        1406.9649620315088
      ],
      "voteCount": 5729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.647437689493184
      }
    },
    {
      "id": "46fcc668f5f15faecd4da040",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1410.8262006368118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.4770958254378,
        1416.1753054481856
      ],
      "voteCount": 15758,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.4484521684638425
      }
    },
    {
      "id": "14a592be5aabe83c8826abd3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1410.0580304763873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3772478835629,
        1412.7388130692118
      ],
      "voteCount": 92031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 1.87079847668186
      }
    },
    {
      "id": "1e8ba365a2b06b68c872caff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1406.5096979966854,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.416070092397,
        1413.603325900974
      ],
      "voteCount": 7728,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.099074907018675
      }
    },
    {
      "id": "48f795ee6b1a7c4e34e13eb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium-2508",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1396.1636405882348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.0827378530182,
        1410.2445433234514
      ],
      "voteCount": 2402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.61367883745877
      }
    },
    {
      "id": "7d6f861eca83ff14896cc745",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1194.6628757244791,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.9907659497726,
        1208.3349854991857
      ],
      "voteCount": 3014,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.660312245087816
      }
    },
    {
      "id": "c2845e90e2860ee0605083f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1260.7515041186703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.2835207973308,
        1271.2194874400095
      ],
      "voteCount": 5149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.525276445899355
      }
    },
    {
      "id": "3171f498d95c418848d9489b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1193.0265185611547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.1098901129717,
        1203.9431470093375
      ],
      "voteCount": 5549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.02279166281519
      }
    },
    {
      "id": "d6c89eb067dd81126ea5ca4a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1246.5190855747348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.0495566243662,
        1252.9886145251035
      ],
      "voteCount": 23846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.895549527742647
      }
    },
    {
      "id": "61931bd88990fabd255fbf00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1111.8589767513217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.7187378023814,
        1119.999215700262
      ],
      "voteCount": 23596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.2495640949944
      }
    },
    {
      "id": "694f3aa48ef829eeedb08d22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1221.4589377131354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.3327060340944,
        1238.5851693921763
      ],
      "voteCount": 1357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.35323589676982
      }
    },
    {
      "id": "cc0771de2ec85d5c3f20b34d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1251.234311309352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.934100596062,
        1278.5345220226422
      ],
      "voteCount": 721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.01522696926003
      }
    },
    {
      "id": "1d67e69dbe35402862994076",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1214.7270895329343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.3470939702904,
        1237.1070850955784
      ],
      "voteCount": 852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.383852792014
      }
    },
    {
      "id": "6ee361a142a2c6acea1adb6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1241.7308836589018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.8979735179882,
        1251.5637937998156
      ],
      "voteCount": 6398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.16911578445942
      }
    },
    {
      "id": "d200644be29b91f9d83c4f02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1234.0986986630153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.388412513919,
        1242.8089848121112
      ],
      "voteCount": 8650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.750071090291225
      }
    },
    {
      "id": "337255e4d7f4b7af68641a79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1207.7060875169695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.059312071908,
        1220.352862962031
      ],
      "voteCount": 3224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.635466270314396
      }
    },
    {
      "id": "4fdc17faa68a077ac7e07ea3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1188.6491753493415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.9436858441236,
        1199.3546648545594
      ],
      "voteCount": 5402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.834370455549656
      }
    },
    {
      "id": "b63c63496cb3d65973df1d06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1253.909694946365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.5497089802225,
        1270.2696809125075
      ],
      "voteCount": 1811,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.67382791416063
      }
    },
    {
      "id": "6fea24290009acb5f4559fd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1251.2008453598655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.6910129695493,
        1261.7106777501817
      ],
      "voteCount": 6062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.753809953006762
      }
    },
    {
      "id": "733547ff4980068e87f00b69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1226.1969575236842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.9519748168373,
        1237.441940230531
      ],
      "voteCount": 3806,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.91708748668422
      }
    },
    {
      "id": "d3ab76d4e3d8c1859de605b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1241.0360549023585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.9239121505898,
        1257.1481976541272
      ],
      "voteCount": 1925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.5787913317952
      }
    },
    {
      "id": "3abf6d0e802ad326f371de69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1242.4380130867257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.4947687726221,
        1251.3812574008293
      ],
      "voteCount": 9016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.820636793210166
      }
    },
    {
      "id": "d8502ccad07e0e8905302c6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1206.8982521754428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.4417711341384,
        1216.3547332167475
      ],
      "voteCount": 8402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.278925496432052
      }
    },
    {
      "id": "c29c9aa93c686dc1d67ba878",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1208.5692599969861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.3472466564285,
        1216.791273337544
      ],
      "voteCount": 11466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.5978727165151
      }
    },
    {
      "id": "54bc43c7c4f98a061bc5eb36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1070.6193765012217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1036.780958872846,
        1104.4577941295975
      ],
      "voteCount": 337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 298.07387272355896
      }
    },
    {
      "id": "2d3dacb0024c001063ef65bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1102.9608889456592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.738382883375,
        1140.1833950079435
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 360.6741663070706
      }
    },
    {
      "id": "4839ecb33c8618833ef11006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1217.4842375470812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.5067915730667,
        1230.4616835210957
      ],
      "voteCount": 2718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.841184266042184
      }
    },
    {
      "id": "e4f020ecb2613eebd6f79a02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1220.3469029944802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.599290425565,
        1231.0945155633954
      ],
      "voteCount": 4406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.069611916503625
      }
    },
    {
      "id": "20c895001f494f843c5e899e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1194.175324662629,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.798905901769,
        1205.5517434234887
      ],
      "voteCount": 4621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.691081920554495
      }
    },
    {
      "id": "1000b03912c93f81f538816a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1221.9412560933058,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.4434232175706,
        1227.4390889690408
      ],
      "voteCount": 34550,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.868408263726357
      }
    },
    {
      "id": "3985477f6d61cab898b868f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1216.7791102976648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.6920401655352,
        1231.8661804297947
      ],
      "voteCount": 1757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.25344922236395
      }
    },
    {
      "id": "781f99e472ec56c0a966ef6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-medium",
      "organization": "mistral",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1197.512896416261,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.072808460895,
        1229.9529843716264
      ],
      "voteCount": 439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 273.94782963252226
      }
    },
    {
      "id": "8d617349e4ee9ae9009d74be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1265.3702448185488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.756639184604,
        1282.9838504524937
      ],
      "voteCount": 1054,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.76075207597084
      }
    },
    {
      "id": "b9eb307f97a25b926c01698c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1312.1367899305003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.6546874717524,
        1324.6188923892482
      ],
      "voteCount": 2083,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.55825900081516
      }
    },
    {
      "id": "906ddecb85f998ece3e0e285",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1226.9439837359732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.6048615907644,
        1239.283105881182
      ],
      "voteCount": 2415,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.634405162482025
      }
    },
    {
      "id": "ae33ddc962ef6e5cd826cc95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1293.9540577835746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.9233390945114,
        1300.9847764726378
      ],
      "voteCount": 8740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.867769145006948
      }
    },
    {
      "id": "e47617bfe64225cb1cd77a17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1187.5668931997159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.1960683833709,
        1196.937718016061
      ],
      "voteCount": 9628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.859117287833463
      }
    },
    {
      "id": "6431b6e9f08f9ce9d8acae10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1257.2275177693607,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.6049848588682,
        1277.850050679853
      ],
      "voteCount": 754,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.7102492816762
      }
    },
    {
      "id": "133d538d4fbe2f4b85d84850",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1256.2060578921275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.3700035937297,
        1306.0421121905254
      ],
      "voteCount": 142,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 646.5336279679509
      }
    },
    {
      "id": "3cebe7b1e27bbaf355834079",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1256.1487014855525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.0258544791393,
        1289.2715484919654
      ],
      "voteCount": 301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 285.6006129494319
      }
    },
    {
      "id": "b914b3141b0f52fad56b6424",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1294.8176891138921,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.039993834571,
        1306.5953843932132
      ],
      "voteCount": 2355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.109746991242226
      }
    },
    {
      "id": "2278662145ea284d78f968c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1284.5004296962366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.8595336778253,
        1294.1413257146478
      ],
      "voteCount": 3569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.195723649855985
      }
    },
    {
      "id": "6ccc0704608e5663a7906be3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1259.9863316742192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.3735136665177,
        1275.5991496819206
      ],
      "voteCount": 1443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.45508243599029
      }
    },
    {
      "id": "641d11727f0271c229ac1e8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1224.6939244108084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.1576577718295,
        1236.2301910497877
      ],
      "voteCount": 2680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.644507250392195
      }
    },
    {
      "id": "09934383542be16357abe6cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1275.7787118192514,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.1697629837697,
        1296.3876606547328
      ],
      "voteCount": 869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.5644474998574
      }
    },
    {
      "id": "c0cf7ec0c5dce65ed68af23e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1293.827642577092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.1295366451768,
        1305.5257485090074
      ],
      "voteCount": 2579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.623363097664964
      }
    },
    {
      "id": "d1434e595894890f72f7fabd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1269.9685285412143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.6443760142427,
        1284.292681068186
      ],
      "voteCount": 1447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.41235067017454
      }
    },
    {
      "id": "943b4949a27048703f40b88e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1286.112138377792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.3370190615183,
        1309.887257694066
      ],
      "voteCount": 654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.14626002444604
      }
    },
    {
      "id": "389b140ea05373e1cf7c703f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1305.733417790554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.7945969598316,
        1315.6722386212764
      ],
      "voteCount": 3478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.714231003354758
      }
    },
    {
      "id": "ae888e05e84f67b07967bd05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1247.3226936523215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.8191388270625,
        1256.8262484775805
      ],
      "voteCount": 3942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.51126447852477
      }
    },
    {
      "id": "cd9d310075174bc5a6677c29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1254.7948492469177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.595692527836,
        1262.9940059659993
      ],
      "voteCount": 5485,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.500167004761717
      }
    },
    {
      "id": "219b4fc5d1d5b869eab1d912",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1150.3372940139948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1113.2193071575591,
        1187.4552808704302
      ],
      "voteCount": 269,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 358.651494805188
      }
    },
    {
      "id": "c8db08fd1332f44082dd4238",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1238.906443793232,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.4738547582215,
        1278.3390328282424
      ],
      "voteCount": 231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 404.7756726240428
      }
    },
    {
      "id": "38ae1d58caa16654deee484c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1279.0258472963385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.4069153807718,
        1292.6447792119052
      ],
      "voteCount": 1767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.28251848534058
      }
    },
    {
      "id": "f6374ae3576097f1724566e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1261.3887176062995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.0781561263834,
        1274.6992790862155
      ],
      "voteCount": 1683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.12077212859694
      }
    },
    {
      "id": "f7409cd284c272efc14ef70d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1249.3655926466738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.4450190252446,
        1262.2861662681032
      ],
      "voteCount": 2151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.45776708771565
      }
    },
    {
      "id": "be7cdc13a3ba032b5303555a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1273.892775079908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.9950355466353,
        1279.7905146131811
      ],
      "voteCount": 14681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.054719372481932
      }
    },
    {
      "id": "a4d81051449a34424a4433ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-24b-instruct-2501",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1259.912324665815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.2011550219422,
        1274.623494309688
      ],
      "voteCount": 1418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.337584858375266
      }
    },
    {
      "id": "b7afe5e295af4b971b42aa28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1355.1844244976032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.0335370494017,
        1375.3353119458052
      ],
      "voteCount": 828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.70418268253657
      }
    },
    {
      "id": "cd25d96a83ea708dfe9e8d1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1412.5944037712381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.595644262692,
        1422.5931632797842
      ],
      "voteCount": 3360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.025319123863007
      }
    },
    {
      "id": "6abda2ad9919769bea2471b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1324.310112728286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.4899296548404,
        1337.1302958017316
      ],
      "voteCount": 2172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.78507247071355
      }
    },
    {
      "id": "5f9d1b14f44d28a9eae62bb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1381.4531436596367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.7330667660594,
        1388.1732205532137
      ],
      "voteCount": 8512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.7558030850968
      }
    },
    {
      "id": "8f17d3b2d718ff6f57c0377a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1319.7816428846008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.4656966293317,
        1327.0975891398698
      ],
      "voteCount": 12371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.93300621150851
      }
    },
    {
      "id": "7d74f034cd725e016a8b6871",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1335.854907284882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.134559341233,
        1355.5752552285312
      ],
      "voteCount": 840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.23553086749385
      }
    },
    {
      "id": "1b83afe89de4b463048f4ccb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1365.070414988043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.0594944806949,
        1405.0813354953914
      ],
      "voteCount": 222,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 416.7358898190862
      }
    },
    {
      "id": "72b092c551da2586dffd97f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1361.9054994018632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.1148625567325,
        1391.696136246994
      ],
      "voteCount": 403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.02734795894645
      }
    },
    {
      "id": "7532507b936f8405d27521d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1397.7238432922227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.6008351376267,
        1406.8468514468184
      ],
      "voteCount": 4071,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.666060128111
      }
    },
    {
      "id": "0e294a50f8562604c2f10df2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1374.5663773517708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.6673603867634,
        1381.4653943167784
      ],
      "voteCount": 7812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.390197918315861
      }
    },
    {
      "id": "1f6f91650b3c2342c204d151",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1364.2346712338176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.2787038262431,
        1375.1906386413918
      ],
      "voteCount": 2944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.246780829513167
      }
    },
    {
      "id": "abe2349e7aa6db91add10def",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1325.4785825567408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.2131904542198,
        1335.7439746592618
      ],
      "voteCount": 3160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.431837730714147
      }
    },
    {
      "id": "bdb3309e754b52aa434c18a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1367.2904684135988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.3510464626288,
        1384.2298903645685
      ],
      "voteCount": 1171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.69662683541407
      }
    },
    {
      "id": "615b5a32fbcaf5adc2e4088c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1368.846953907808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.8211496659578,
        1379.8727581496582
      ],
      "voteCount": 2909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.646404361984914
      }
    },
    {
      "id": "25202d9ed2302ad462fc41e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1356.940196630601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.7492867998658,
        1375.131106461336
      ],
      "voteCount": 993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.14154567720689
      }
    },
    {
      "id": "0c5d1b2b75066628bb2532cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1388.2361605895605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.479291733176,
        1405.9930294459448
      ],
      "voteCount": 1136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.07985723659496
      }
    },
    {
      "id": "2d28b37b490f8bc9cfed76c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1399.870430635039,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.2240303417998,
        1407.516830928278
      ],
      "voteCount": 6051,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.220113028279401
      }
    },
    {
      "id": "c8e027baa2752cda1b12981a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1330.1109967780017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.4734739277937,
        1339.7485196282091
      ],
      "voteCount": 3788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.178795354492998
      }
    },
    {
      "id": "1e81602117075012bb2f924f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1339.0653758705953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.1740960897632,
        1347.9566556514274
      ],
      "voteCount": 4385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.57938398692689
      }
    },
    {
      "id": "64c5625be78d30c4fd89dff8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1292.6929610313905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.6029909912509,
        1319.78293107153
      ],
      "voteCount": 463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.0384859060008
      }
    },
    {
      "id": "c35c5ce2bec4546eff799526",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1279.8170109284501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.1179263668073,
        1312.516095490093
      ],
      "voteCount": 337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.3396051024876
      }
    },
    {
      "id": "362e6813b3436ae9c7805a4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1360.5769340501124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.4902256845317,
        1370.6636424156927
      ],
      "voteCount": 3404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.485168890575313
      }
    },
    {
      "id": "41de763f18c45b0a2a3933fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1338.7371850763543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.2066510376994,
        1356.2677191150092
      ],
      "voteCount": 1042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.00075961374114
      }
    },
    {
      "id": "44242b89a15a3f43b0408098",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1367.2621226287788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.659483644596,
        1377.8647616129615
      ],
      "voteCount": 3082,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.263870491939205
      }
    },
    {
      "id": "ab1baff2fb8f6c63b8493743",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1357.3918850473397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.194384267455,
        1362.5893858272243
      ],
      "voteCount": 17712,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.03222802008844
      }
    },
    {
      "id": "e7ce7734c0c18038e0db8bf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1355.9908099263923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.2151854236467,
        1373.766434429138
      ],
      "voteCount": 985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.25334207943283
      }
    },
    {
      "id": "aa57e8f7c39d9bf7849f3f57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-2506",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1366.3784828304556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.8142994985167,
        1397.9426661623945
      ],
      "voteCount": 365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 259.35398917857646
      }
    },
    {
      "id": "4cc0a6207eaa1a002a014d05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1287.49587033392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.9775997190495,
        1303.0141409487906
      ],
      "voteCount": 1693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.688872669689594
      }
    },
    {
      "id": "7953cc518255c14952f032dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1361.6259839269235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.7458986505108,
        1369.5060692033362
      ],
      "voteCount": 6136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.164625696108878
      }
    },
    {
      "id": "8d302eb39bab3dc4a4949fdb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1271.5104230093875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.986760755165,
        1281.0340852636098
      ],
      "voteCount": 4178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.610859042375473
      }
    },
    {
      "id": "de8efda3a76b705f76a6c268",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1321.8473353315003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.226644970156,
        1327.4680256928445
      ],
      "voteCount": 15943,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.224000728035827
      }
    },
    {
      "id": "3673ded02a3329573e690cba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1240.8164901524594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.4145514436934,
        1247.2184288612252
      ],
      "voteCount": 23734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.669076812696403
      }
    },
    {
      "id": "3508589f47b6642edc986abd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1304.213314242866,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.9527757000055,
        1319.4738527857266
      ],
      "voteCount": 1642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.62385345993363
      }
    },
    {
      "id": "5457eb085a414cfc1da6afe6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1310.6363607004992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.6152746841756,
        1341.6574467168225
      ],
      "voteCount": 411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.50581629253375
      }
    },
    {
      "id": "f654ee718385faba58b5ab66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1293.5433914950695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.7498493001747,
        1315.336933689964
      ],
      "voteCount": 830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.64013349356588
      }
    },
    {
      "id": "8716a3b2a0d39952e69cab8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1335.3930174238558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.1243624933113,
        1342.6616723544003
      ],
      "voteCount": 7627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.753458507666972
      }
    },
    {
      "id": "74d4f479729ee41604d3cb0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1319.0558226602284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.2243382550655,
        1324.8873070653915
      ],
      "voteCount": 14699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.852420904387992
      }
    },
    {
      "id": "958776c871f8cdd7af25e765",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1297.763512689985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.1914658150154,
        1306.3355595649546
      ],
      "voteCount": 5578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.128146638155943
      }
    },
    {
      "id": "08505edb8acd71bc070052bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1277.1737029166209,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.0616060152238,
        1285.285799818018
      ],
      "voteCount": 5857,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.130501512382533
      }
    },
    {
      "id": "e2473909c7eabf344a9cd309",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1307.6329370128262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.5634001082626,
        1320.7024739173899
      ],
      "voteCount": 2155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.465606133683586
      }
    },
    {
      "id": "b70db7bcc976fac8cff7d327",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1306.0722728692976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.3016187573135,
        1314.8429269812818
      ],
      "voteCount": 5272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.02478150687685
      }
    },
    {
      "id": "9570443abebeaf1b2d121473",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1290.5295560117656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.1523229172578,
        1303.9067891062737
      ],
      "voteCount": 1941,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.58396031757119
      }
    },
    {
      "id": "1e8617323c39a7eca87607de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1315.7729972222407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.470793025814,
        1330.0752014186673
      ],
      "voteCount": 1955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.24879282171413
      }
    },
    {
      "id": "a418005e3dddfe8174e46b14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1343.8767681862664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.5113490962044,
        1350.2421872763284
      ],
      "voteCount": 11086,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.54770129874906
      }
    },
    {
      "id": "3378d9e7df80db71f9a45856",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1290.8932641894303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.403553424495,
        1298.382974954366
      ],
      "voteCount": 7133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.60272515227822
      }
    },
    {
      "id": "166889cc8780ed935a9ef3e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1295.027894388174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.9319990584988,
        1302.1237897178491
      ],
      "voteCount": 8042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.107450289056409
      }
    },
    {
      "id": "2147ac00a2593ac4f1a2c86d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1242.9952226751643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.0510761631967,
        1265.9393691871321
      ],
      "voteCount": 714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.04008912622382
      }
    },
    {
      "id": "06423c69fb36809e7b5a297a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1241.9883373458845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.2326932980777,
        1266.7439813936912
      ],
      "voteCount": 666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.53364094918985
      }
    },
    {
      "id": "fcb52ad028ae69cb5a888656",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1322.3106403608242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.4809027191718,
        1330.1403780024766
      ],
      "voteCount": 6301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.95872672299791
      }
    },
    {
      "id": "214104c06bfde3fb28f67363",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1277.4728931572326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.509261739106,
        1290.4365245753593
      ],
      "voteCount": 2131,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.74789562749327
      }
    },
    {
      "id": "f1e3581aafe9f991ed069136",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1291.4301586822335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.9095474344633,
        1299.9507699300038
      ],
      "voteCount": 5570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.899282648696932
      }
    },
    {
      "id": "5700138e573b121f17c87c3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1303.4171042591154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.913110420641,
        1307.9210980975897
      ],
      "voteCount": 33220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.280796031896353
      }
    },
    {
      "id": "4dd34a44b316e4daf05f7629",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1298.1049981473848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.1346408488316,
        1311.075355445938
      ],
      "voteCount": 2012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.79330257189471
      }
    },
    {
      "id": "b600549a105ee2647f19220e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mistral-small-3.1-24b-instruct-2503",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1304.8178263946966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.19228304147,
        1328.443369747923
      ],
      "voteCount": 703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.300607084037
      }
    },
    {
      "id": "b8dbcd9257da9b1ab4ad3a78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1209.4032077187094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.295095609093,
        1220.5113198283257
      ],
      "voteCount": 5655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.12065009654589
      }
    },
    {
      "id": "8736d96cb5a308fa9a66968d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1275.8127952197508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.1678346315643,
        1284.457755807937
      ],
      "voteCount": 8780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.454938100257927
      }
    },
    {
      "id": "1bc715a3a49ec459be6c9697",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1189.925260413876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.5712583308489,
        1199.2792624969031
      ],
      "voteCount": 7447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.77711646885921
      }
    },
    {
      "id": "713da535369beff9086c166e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1251.8395645942046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.1801817965193,
        1257.49894739189
      ],
      "voteCount": 29892,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.337617333862147
      }
    },
    {
      "id": "800f756e23a4728c87e06777",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1120.2137026143887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1113.1073838581087,
        1127.3200213706682
      ],
      "voteCount": 33717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.145986622011439
      }
    },
    {
      "id": "e7b3de5c401df00d467b2c89",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1213.2297166948515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.410253086021,
        1227.0491803036816
      ],
      "voteCount": 2582,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.71485660785479
      }
    },
    {
      "id": "2b44b5155552730804bd8532",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1257.2769647094644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.2974668324314,
        1283.2564625864975
      ],
      "voteCount": 767,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.6973955589126
      }
    },
    {
      "id": "38e417910c8aa589ee0f418e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1216.905617520812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.8110579449922,
        1234.000177096632
      ],
      "voteCount": 1653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.07109192919808
      }
    },
    {
      "id": "ba90bcb71fa34fba50a773dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1254.2943808010273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.993720521371,
        1262.5950410806836
      ],
      "voteCount": 9466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.936144650852953
      }
    },
    {
      "id": "9e65063ff250876667b0738c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1242.1542316839893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.1499665862425,
        1249.1584967817362
      ],
      "voteCount": 14707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.771119475556128
      }
    },
    {
      "id": "2aaf971b65918f11fbc67a1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1212.453907071332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.2603899541996,
        1222.6474241884644
      ],
      "voteCount": 5554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.04904466436392
      }
    },
    {
      "id": "ff1a59d96d62185215d423b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1201.006792110909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.0246186788208,
        1209.988965542997
      ],
      "voteCount": 7616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.002291923444467
      }
    },
    {
      "id": "528bf6053dd160d01252deb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1256.832211234003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.228171178243,
        1270.4362512897624
      ],
      "voteCount": 2798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.17698548315414
      }
    },
    {
      "id": "fd55a611355a670b9f011ce8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1249.936829241432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.8639575337615,
        1259.0097009491028
      ],
      "voteCount": 8677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.428578273546595
      }
    },
    {
      "id": "718b9f5b27e3b57c65378e45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1229.7497609757474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.3742235731427,
        1239.1252983783525
      ],
      "voteCount": 6001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.882114761745925
      }
    },
    {
      "id": "7cb31e6583c4a2bf2a03508c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1237.7609445388323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.9204587251727,
        1251.601430352492
      ],
      "voteCount": 2823,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.86622439531938
      }
    },
    {
      "id": "2c3759b6381ea442f6853b24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1253.866734094027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.500519084316,
        1261.232949103738
      ],
      "voteCount": 14389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.125134773535924
      }
    },
    {
      "id": "7400c87514d6fe3009634a86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1208.312723073665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.6932250099194,
        1215.9322211374108
      ],
      "voteCount": 12808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.113203981433111
      }
    },
    {
      "id": "b5050da3874e520a92aac9ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1212.9220245806284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.3834457431365,
        1219.4606034181202
      ],
      "voteCount": 18515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.129369130233542
      }
    },
    {
      "id": "dc89bca941da61623e1d1997",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1109.9716534420372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.9389461663454,
        1131.0043607177295
      ],
      "voteCount": 972,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.15801574179457
      }
    },
    {
      "id": "f01c27aa72497bc2bed0133e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1142.0338256329114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.1565310313883,
        1163.9111202344343
      ],
      "voteCount": 1187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.5922555523701
      }
    },
    {
      "id": "5019d6685ed120c8c02c9d33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1215.9152576741567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.999637045955,
        1225.8308783023583
      ],
      "voteCount": 5865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.594321592819384
      }
    },
    {
      "id": "3d562da58e25bdf8189d9bd7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1227.767773846213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.8378912206954,
        1236.6976564717304
      ],
      "voteCount": 6778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.75846896391023
      }
    },
    {
      "id": "ccd37aef7f3d3260883c7edb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1187.1312812749761,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.0740591803842,
        1196.188503369568
      ],
      "voteCount": 7764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.354718584733188
      }
    },
    {
      "id": "1e8fbcc5838074aebc9bb46c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1228.5125298174537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.957510331107,
        1233.0675493038002
      ],
      "voteCount": 51416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.401125845532054
      }
    },
    {
      "id": "7cec143e9c4ba5589a3d950c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1223.1104175528733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.8137776619906,
        1233.407057443756
      ],
      "voteCount": 4914,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.59909659095636
      }
    },
    {
      "id": "05e25d955400b78d41017e65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x22b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1223.2063820043772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.6101611056306,
        1248.8026029031244
      ],
      "voteCount": 826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.55148964972173
      }
    },
    {
      "id": "22c49a84a8a240b939c59563",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1152.8414266446102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.3574192739147,
        1163.3254340153057
      ],
      "voteCount": 8285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.612674423759124
      }
    },
    {
      "id": "9b36d7749b7252ddd8f0cce3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1237.9101846691412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.8058159049936,
        1246.014553433289
      ],
      "voteCount": 11784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.0978776894516
      }
    },
    {
      "id": "cae6ea76e9f241d4de3326a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1158.8270037266395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.1793269575703,
        1167.4746804957088
      ],
      "voteCount": 11172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.46716520803085
      }
    },
    {
      "id": "bb9389d597f42440617c5ade",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1228.935076352024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.6783742198845,
        1234.1917784841635
      ],
      "voteCount": 46298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.193339456661947
      }
    },
    {
      "id": "68f512717e04b7e8d9d2b66d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1070.006437040694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1063.4162906863482,
        1076.5965833950395
      ],
      "voteCount": 49034,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.305608363608018
      }
    },
    {
      "id": "0a657f93a3cb3fcc26b92d97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1191.9283559881696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.8821499756273,
        1204.9745620007122
      ],
      "voteCount": 3240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.30699358400196
      }
    },
    {
      "id": "9930cd8abfc6016c2212b6f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1243.6091216018826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.0033517187906,
        1266.214891484975
      ],
      "voteCount": 1252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.02780424312334
      }
    },
    {
      "id": "cc2d9f9d7dc6decab0c9d6e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1185.852528964037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.6576446814784,
        1202.0474132465956
      ],
      "voteCount": 1975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.27465532432068
      }
    },
    {
      "id": "4c35a663a9506a2b7e6a1e6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1227.5092480298406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.7454587553989,
        1235.2730373042823
      ],
      "voteCount": 13360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.691024350755468
      }
    },
    {
      "id": "0cd9e606d6fc985e3644272f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1209.492658535426,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.7578169091921,
        1216.22750016166
      ],
      "voteCount": 19541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.80751736452517
      }
    },
    {
      "id": "470ac231c7d32c63aa4c4d96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1178.989942186458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.0664435220149,
        1188.913440850901
      ],
      "voteCount": 7070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.63500751659995
      }
    },
    {
      "id": "e5d9f27a4076e009e592471f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1165.4658100304234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.0294113197683,
        1173.9022087410785
      ],
      "voteCount": 11001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.527550737165328
      }
    },
    {
      "id": "e5b829023a6e445d1e611088",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1226.014442142318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.321560499327,
        1238.7073237853092
      ],
      "voteCount": 3953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.939599491494306
      }
    },
    {
      "id": "4a2e33b6f7bb0ec8207e13f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1214.298113137042,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.8766452182717,
        1222.7195810558123
      ],
      "voteCount": 12824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.46202841608553
      }
    },
    {
      "id": "dd58258622558d631dd5bccb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1193.9456575561567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.1185219544745,
        1202.772793157839
      ],
      "voteCount": 8472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.283524194177946
      }
    },
    {
      "id": "440f53258cd4885682197ade",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1208.8102066459992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.0820342422676,
        1221.5383790497308
      ],
      "voteCount": 4050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.1731379408212
      }
    },
    {
      "id": "49c7c3c4c933030025473aee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1224.4134517191178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.4638731271612,
        1231.363030311075
      ],
      "voteCount": 20131,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.572474380203946
      }
    },
    {
      "id": "49fa6d1064cbba6bda8eab20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1169.5542370220282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.2450336235606,
        1176.8634404204959
      ],
      "voteCount": 17942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.907334899015444
      }
    },
    {
      "id": "a6ebb0fcd480bcff29c56c1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1178.2199120470748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.910228513966,
        1184.5295955801835
      ],
      "voteCount": 24974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.363798792665209
      }
    },
    {
      "id": "4abd8fd85b3fd84b4572ce84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1003.264824936628,
      "unit": "Arena rating",
      "confidenceInterval": [
        980.9592164175717,
        1025.5704334556845
      ],
      "voteCount": 960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.51854871517153
      }
    },
    {
      "id": "fd98ec7bcc6a0cd47ed7c4c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1062.2006309457438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1036.616164215181,
        1087.7850976763066
      ],
      "voteCount": 778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.39488601598453
      }
    },
    {
      "id": "d865c4f99b271c5114cfff8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1180.3770384683503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.754303115987,
        1189.9997738207137
      ],
      "voteCount": 6572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.104653982699947
      }
    },
    {
      "id": "7698bfd2d11d4d7d936b7a28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1190.5910350599474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.0520367118138,
        1199.1300334080809
      ],
      "voteCount": 9663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.980938282257014
      }
    },
    {
      "id": "70e562aa9a3f05b91f790123",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1165.9041179382787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.273192549474,
        1174.535043327083
      ],
      "voteCount": 10873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.39181871892331
      }
    },
    {
      "id": "15a8c2415d3cceb537cc8f5a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1196.1670741784965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.8974160143844,
        1200.4367323426086
      ],
      "voteCount": 73503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.745587988647345
      }
    },
    {
      "id": "cf4e3cb1e366d98b1ec6ba90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1158.5877796158138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.0084283997924,
        1169.1671308318353
      ],
      "voteCount": 5239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.135460609131417
      }
    },
    {
      "id": "4dc1088700b7daa575f0a381",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mixtral-8x7b-instruct-v0.1",
      "organization": "mistral",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1171.5325176420965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.4909194825198,
        1195.5741158016733
      ],
      "voteCount": 1065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.4632664426498
      }
    },
    {
      "id": "3c45d4fe0fe225ab30c0529e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1345.8662616526162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.7404389399308,
        1376.992084365302
      ],
      "voteCount": 376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 252.2002407841703
      }
    },
    {
      "id": "9ec8b43a33fa72f9b4b5dae3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1276.839685922395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.1860184933425,
        1309.4933533514472
      ],
      "voteCount": 583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.5669469169227
      }
    },
    {
      "id": "675ff0580453a3131f2fc900",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1347.0039961217512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.0908868822257,
        1387.9171053612768
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 435.7413643556594
      }
    },
    {
      "id": "cf9b7edf301ce1864e9c248a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1341.0908783073357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.0883879008547,
        1369.0933687138167
      ],
      "voteCount": 438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 204.1254392057684
      }
    },
    {
      "id": "5fc3a26349b37b8478b91521",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1351.8650413250784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.5854875650384,
        1387.1445950851185
      ],
      "voteCount": 288,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 324.00371098671786
      }
    },
    {
      "id": "9486b8749cf3b36459076fa7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1309.0455181424477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.5447418652816,
        1347.5462944196138
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 385.871577214136
      }
    },
    {
      "id": "2115e717ade2ede5c4730c14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "molmo-2-8b",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1327.9057337874324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.5961199921608,
        1349.2153475827042
      ],
      "voteCount": 805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.21020640840402
      }
    },
    {
      "id": "c2782f29acda599b4b08c377",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1166.2212613295599,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.5765482107076,
        1200.865974448412
      ],
      "voteCount": 258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 312.4480055914532
      }
    },
    {
      "id": "71ef9159bbd73d6aa7b8169c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1131.6898566213754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.6888766546454,
        1160.6908365881054
      ],
      "voteCount": 452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.94204214811893
      }
    },
    {
      "id": "9f3e11ccbe096c5a50379d55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1180.934234292431,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.1809543356158,
        1194.687514249246
      ],
      "voteCount": 2056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.239811852611474
      }
    },
    {
      "id": "a18fe017f14698c0c378651f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1010.8139465441445,
      "unit": "Arena rating",
      "confidenceInterval": [
        992.6794993842241,
        1028.948393704065
      ],
      "voteCount": 1777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.6076269838872
      }
    },
    {
      "id": "6b077875378f98b73f08a70d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1186.317933323154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.444522021086,
        1216.191344625222
      ],
      "voteCount": 359,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.31296871256612
      }
    },
    {
      "id": "5a37677890737f471b8d1b8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1155.9580584484797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.1910967688236,
        1182.7250201281358
      ],
      "voteCount": 434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.5099356787364
      }
    },
    {
      "id": "76bb57bfcbec5d3b0e501fcd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1123.0044376370258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.0986637909814,
        1160.9102114830705
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 374.0369890540303
      }
    },
    {
      "id": "19dc9b2bf6d472106ae604f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1129.8228139539726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.759881829079,
        1158.8857460788663
      ],
      "voteCount": 435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 219.87845324437285
      }
    },
    {
      "id": "c43c4375cbaea8bb88e0d629",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1153.0933563855428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.8229221785414,
        1179.3637905925445
      ],
      "voteCount": 509,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.65459103885283
      }
    },
    {
      "id": "f569e64c544321bfe44dded1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1113.0163240014867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.2226254187483,
        1149.8100225842254
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 352.412018086606
      }
    },
    {
      "id": "fe312be6467d067fb1002a6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1168.0330752161935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.446240923548,
        1192.6199095088389
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.36532623426066
      }
    },
    {
      "id": "715fdc903335e90d150cc9e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1137.8436119601483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.2016514434192,
        1160.4855724768777
      ],
      "voteCount": 647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.4540860569447
      }
    },
    {
      "id": "f81b2f5ac7cbb97a8ca1c1b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1132.0850183475168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.787770112341,
        1153.3822665826926
      ],
      "voteCount": 718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.07305598260783
      }
    },
    {
      "id": "44574a05f80c547a9c75d609",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1094.8428039981939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1060.9189311771363,
        1128.7666768192516
      ],
      "voteCount": 242,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 299.5812791171212
      }
    },
    {
      "id": "0c50f65d863659eb1b8408b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1123.2703142212333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.3950986718091,
        1155.1455297706575
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.4905005486073
      }
    },
    {
      "id": "64615d1d9ce217d7d5a27ceb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-30b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1149.2880808619886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.0227994091304,
        1161.553362314847
      ],
      "voteCount": 2572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.16145822191756
      }
    },
    {
      "id": "237c40ffedf86ae3d2902ace",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1086.866690477867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1043.7868672592235,
        1129.946513696511
      ],
      "voteCount": 178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 483.1162470236361
      }
    },
    {
      "id": "aa09d3a9f5ea4bf842211456",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1064.4802734629384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1033.0683767925411,
        1095.8921701333354
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.8574332012284
      }
    },
    {
      "id": "8cd25c37653f3859356fcfc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1050.9219039132588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1026.5202429351523,
        1075.3235648913655
      ],
      "voteCount": 683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.00388948145934
      }
    },
    {
      "id": "43a6365f96bf0a12a74f0534",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1086.0032144076317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.9350469862231,
        1099.0713818290403
      ],
      "voteCount": 3278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.45628802109839
      }
    },
    {
      "id": "304ae94ed6f8e1a222c2c3a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 876.6655964435976,
      "unit": "Arena rating",
      "confidenceInterval": [
        858.3381180391409,
        894.9930748480542
      ],
      "voteCount": 2652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.43981917919686
      }
    },
    {
      "id": "92e338138ae4f6124b586dc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1043.1493587399546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1019.11594503265,
        1067.182772447259
      ],
      "voteCount": 626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.36083982336785
      }
    },
    {
      "id": "bf5d8f5c7420b29b3e661920",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1030.8151001630404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1008.8503488322292,
        1052.7798514938515
      ],
      "voteCount": 714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.59038728344245
      }
    },
    {
      "id": "fb0c7aaff6adfbf67bcc49c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1008.6090327621048,
      "unit": "Arena rating",
      "confidenceInterval": [
        971.4740180914828,
        1045.7440474327268
      ],
      "voteCount": 306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 358.98063182625407
      }
    },
    {
      "id": "ab7e7a44b9f1475ca3281a39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1034.6405259651729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1010.2682543741212,
        1059.0127975562245
      ],
      "voteCount": 717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.63074062073417
      }
    },
    {
      "id": "a846249f7115100889fd6f4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1065.570999154727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.8350176528304,
        1090.3069806566236
      ],
      "voteCount": 677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 159.28031756217212
      }
    },
    {
      "id": "23427f3a4686315bf3a65777",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 984.7128964794479,
      "unit": "Arena rating",
      "confidenceInterval": [
        956.3125252864569,
        1013.113267672439
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.96739039725813
      }
    },
    {
      "id": "a030e5ad4b69c56bd13ebf4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1054.9080796032338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1033.117389657172,
        1076.6987695492955
      ],
      "voteCount": 882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.60777259083001
      }
    },
    {
      "id": "ee689b89590827d86878e8c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1054.7946561081376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1033.9154910781667,
        1075.6738211381085
      ],
      "voteCount": 892,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.48280762514752
      }
    },
    {
      "id": "e9e0671fd64dd3687b6f11ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1005.4153366186447,
      "unit": "Arena rating",
      "confidenceInterval": [
        986.8304414720232,
        1024.000231765266
      ],
      "voteCount": 1115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.91332296736763
      }
    },
    {
      "id": "d263e26ac51166499b676e30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 984.1886652075755,
      "unit": "Arena rating",
      "confidenceInterval": [
        959.0068874691495,
        1009.3704429460014
      ],
      "voteCount": 471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 165.07320777498282
      }
    },
    {
      "id": "626aff3680a168bbdfbbc248",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1001.5133267315153,
      "unit": "Arena rating",
      "confidenceInterval": [
        972.3961675310634,
        1030.6304859319673
      ],
      "voteCount": 466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.6997392077394
      }
    },
    {
      "id": "dff731d1b21e0788f325b6c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "mpt-7b-chat",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1061.2566535489507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1049.27175406353,
        1073.2415530343715
      ],
      "voteCount": 3924,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.39147609805258
      }
    },
    {
      "id": "8eccc404cda0696accf050af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1525.6522505958048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1502.7339428084906,
        1548.570558383119
      ],
      "voteCount": 723,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.73160545273356
      }
    },
    {
      "id": "9174d2e1f42c093c264e8715",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1526.29419984031,
      "unit": "Arena rating",
      "confidenceInterval": [
        1515.6334398335491,
        1536.9549598470712
      ],
      "voteCount": 3260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.585584338300738
      }
    },
    {
      "id": "3596f74e81566871bca26bb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1462.0156977831743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.56529518826,
        1476.4661003780884
      ],
      "voteCount": 1796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.3580303477966
      }
    },
    {
      "id": "81ba21ae21ee49ee5fa1c3c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1495.6610188867655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.647563374992,
        1503.674474398539
      ],
      "voteCount": 5799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.71642785632406
      }
    },
    {
      "id": "14426fac6f09f6cb97c7315b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1504.5077049612905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.3478042619156,
        1512.6676056606655
      ],
      "voteCount": 8916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.3329931496257
      }
    },
    {
      "id": "e2e0046aad60a0f273bc3815",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1486.0330525821082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.5434918686592,
        1503.5226132955572
      ],
      "voteCount": 1146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.6272323164322
      }
    },
    {
      "id": "5f0564e56ae04debf317a88f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1530.8151825986201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1499.061871128985,
        1562.5684940682554
      ],
      "voteCount": 391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 262.47132569951145
      }
    },
    {
      "id": "73f1a170f5d5281088af8167",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1502.8471783183832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.1565682711587,
        1543.5377883656076
      ],
      "voteCount": 226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 431.01483662816077
      }
    },
    {
      "id": "07334b4689a27c794b4c41bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1506.1463581935575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1496.2416679200912,
        1516.0510484670237
      ],
      "voteCount": 3760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.53792556224013
      }
    },
    {
      "id": "ac2370e95503b73b32ae2cb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1506.1427012824472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1498.8461159755318,
        1513.4392865893626
      ],
      "voteCount": 7580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.859359068041236
      }
    },
    {
      "id": "72622a5f16c263fad82f19a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1488.501404257722,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.0516635267836,
        1500.9511449886604
      ],
      "voteCount": 2401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.34822485473919
      }
    },
    {
      "id": "eeefbc5888fba9b7d50bb06e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1458.6769160419185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.8065322885332,
        1471.5472997953038
      ],
      "voteCount": 2214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.120800115585325
      }
    },
    {
      "id": "ca51722cc0b22620308fffcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1511.2221675638934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.6461189188267,
        1531.7982162089604
      ],
      "voteCount": 876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.21171841369765
      }
    },
    {
      "id": "d2b2f3178685860a0655f92e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1501.7130434998849,
      "unit": "Arena rating",
      "confidenceInterval": [
        1488.3302421524659,
        1515.0958448473039
      ],
      "voteCount": 2038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.622749393970444
      }
    },
    {
      "id": "64a79c197ce606c948129c3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1472.951287053498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.988046439012,
        1494.9145276679842
      ],
      "voteCount": 717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.57311188426354
      }
    },
    {
      "id": "f0d23b407a3e4bdc185c7732",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1515.391661374576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1494.7385217579858,
        1536.044800991166
      ],
      "voteCount": 864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.0391119447911
      }
    },
    {
      "id": "97b30ec9b67aab6dd3c99ca6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1519.6810802427528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1510.7521750169922,
        1528.6099854685137
      ],
      "voteCount": 4648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.753925071676644
      }
    },
    {
      "id": "0613c401713448e20e2ec1c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1459.3242581290176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.8391450380045,
        1470.8093712200307
      ],
      "voteCount": 2788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.33795046891182
      }
    },
    {
      "id": "fffd8cff5c09c47d84f6fc19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1461.3642007957299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.6524015850302,
        1471.0760000064292
      ],
      "voteCount": 3862,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.552923332365324
      }
    },
    {
      "id": "eab2c05dbc015d007249b573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1472.1707158147367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.374139570131,
        1511.9672920593423
      ],
      "voteCount": 239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 412.28282137527475
      }
    },
    {
      "id": "b5338dde71c10f62050827f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1471.7574788263728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.3050789538047,
        1481.209878698941
      ],
      "voteCount": 4355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.258836687147642
      }
    },
    {
      "id": "b0cc4d34c3251c365b131485",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1462.4979397397174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.0564855717369,
        1482.9393939076976
      ],
      "voteCount": 795,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.77457445349891
      }
    },
    {
      "id": "e0c5b0c1e966f681850817fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1495.1193647219948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1480.9209761747254,
        1509.3177532692641
      ],
      "voteCount": 1888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.47856263699405
      }
    },
    {
      "id": "cf4d99af10c7df7d0fb36d13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1488.9729876291767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1482.96744617115,
        1494.9785290872035
      ],
      "voteCount": 12228,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.388758252408188
      }
    },
    {
      "id": "e01c9a6de41f550138a06a9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1485.2176753405754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.6425452414228,
        1501.7928054397278
      ],
      "voteCount": 1316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.5183867971772
      }
    },
    {
      "id": "f946ff470a132ae1b2686a16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "muse-spark",
      "organization": "meta",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1474.929947515458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.7701643243354,
        1504.0897307065804
      ],
      "voteCount": 431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 221.34636747183166
      }
    },
    {
      "id": "bd7cb888d69d7ded0ae85270",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1286.938489702451,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.6559934459715,
        1300.2209859589304
      ],
      "voteCount": 2402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.926486535006134
      }
    },
    {
      "id": "909b4b8e03ec8a8e02628ff8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1307.07049776453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.7168855164448,
        1318.4241100126155
      ],
      "voteCount": 3254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.55613507698129
      }
    },
    {
      "id": "36626eaf6c7f94cce96a10bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1237.873293585005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1226.2238695109902,
        1249.5227176590201
      ],
      "voteCount": 3152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.32748562217227
      }
    },
    {
      "id": "c79c93b6b22cbaff90da68e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1287.5935524149027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.3567345582724,
        1294.8303702715327
      ],
      "voteCount": 10292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.633240686562456
      }
    },
    {
      "id": "71846144e2aef101d9913c4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1196.0923625059436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.6355639317208,
        1204.549161080166
      ],
      "voteCount": 12726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.61726116643655
      }
    },
    {
      "id": "ac49a68c10945fdcd0a166b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1255.9825503350055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.1390311200623,
        1274.8260695499484
      ],
      "voteCount": 1027,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.43317004756298
      }
    },
    {
      "id": "f7df09af770ca4ea222d3d66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1263.6737930819238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.2013495197475,
        1298.1462366441
      ],
      "voteCount": 357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 309.3484586495481
      }
    },
    {
      "id": "ce3ce3445c1c6e45bda55c58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1245.293369831457,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.1908134150267,
        1268.3959262478875
      ],
      "voteCount": 703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.9389130241689
      }
    },
    {
      "id": "c2d8a3b0d08cfa58606fbd9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1279.6661602423455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.5898763484756,
        1290.7424441362152
      ],
      "voteCount": 3257,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.936842388285466
      }
    },
    {
      "id": "a7ba44eaa1738a37704dc563",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1279.8108957755182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.843454324348,
        1288.7783372266888
      ],
      "voteCount": 5577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.93345521419386
      }
    },
    {
      "id": "8a1628b4be5b4335df01a15d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1259.232006466044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.959277155635,
        1272.5047357764533
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.858969618100375
      }
    },
    {
      "id": "138d934865ecfe9248d26c15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1252.9412732291098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.4547525854864,
        1264.4277938727334
      ],
      "voteCount": 3252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.34636752725886
      }
    },
    {
      "id": "b505e9df39196eceb3f93402",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1315.715716354834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.568841843581,
        1333.8625908660872
      ],
      "voteCount": 1177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.72499925110827
      }
    },
    {
      "id": "730066130533884fe415ea0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1301.807761787893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.1162315589565,
        1313.4992920168295
      ],
      "voteCount": 3316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.58332536529341
      }
    },
    {
      "id": "3320685611674f69b011fbb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1257.5956595135956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.985502553825,
        1270.2058164733662
      ],
      "voteCount": 2133,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.394706014659384
      }
    },
    {
      "id": "fa98797c452cb023c7a264c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1285.2556642887416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.5423106345256,
        1303.9690179429576
      ],
      "voteCount": 1069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.16057761735519
      }
    },
    {
      "id": "1eba3728ab0ce35fe5cd7fc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1299.428628445235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.1581433366082,
        1308.699113553862
      ],
      "voteCount": 5403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.372202374342436
      }
    },
    {
      "id": "1241223dd96cd67acce556c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1257.7191189663733,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.3214044238534,
        1267.1168335088933
      ],
      "voteCount": 5386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.990494690954936
      }
    },
    {
      "id": "c56e71443cb4ca1e30efb25d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1257.392155654139,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.1914928668439,
        1265.5928184414342
      ],
      "voteCount": 7354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.506596657667153
      }
    },
    {
      "id": "010522cc76b8ef9dc3f48978",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1180.2083827851393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.4342120512003,
        1208.9825535190782
      ],
      "voteCount": 434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 215.53085431129605
      }
    },
    {
      "id": "c3fe82b2d846972831deecc9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1221.726641442266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.1007912685686,
        1248.3524916159636
      ],
      "voteCount": 628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.5486130563517
      }
    },
    {
      "id": "f36aff300d0b95e0dd0a0ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1287.3075562106653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.8948391322278,
        1300.7202732891028
      ],
      "voteCount": 2130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.8314220777472
      }
    },
    {
      "id": "8eaa065b9510e4a16c8a7671",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1252.3043508927215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.2692888067345,
        1264.3394129787084
      ],
      "voteCount": 2352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.705133954133046
      }
    },
    {
      "id": "54a5171dff988b1c94d29f5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1255.9527234422294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.3922641516137,
        1267.5131827328455
      ],
      "voteCount": 3098,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.78996528351104
      }
    },
    {
      "id": "c8738a3740d592fd2617a3a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1276.4529206447494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1271.1272783582108,
        1281.778562931288
      ],
      "voteCount": 19659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.383253885575271
      }
    },
    {
      "id": "262fcb585e69b5c60b423ba7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1269.231853471424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.553030822197,
        1281.910676120651
      ],
      "voteCount": 2494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.846743977722696
      }
    },
    {
      "id": "40ffc997b0afee8431722bed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nemotron-4-340b-instruct",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1244.7825805479563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.8877971270167,
        1276.6773639688959
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.815336295814
      }
    },
    {
      "id": "7be6419639596556222a033b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1174.1446191809473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.5927060576166,
        1197.6965323042782
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.39634463364848
      }
    },
    {
      "id": "b3447695e268c7454cbcec02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1134.6943596647752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1111.3675695612646,
        1158.0211497682856
      ],
      "voteCount": 616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.64908747737428
      }
    },
    {
      "id": "6a039fc34c4043324b26836d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1190.8249328968018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.9548041706848,
        1203.6950616229187
      ],
      "voteCount": 3033,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.11909125109146
      }
    },
    {
      "id": "be745c5ed89cd94108af7e17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1024.3119206275394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1007.1217888536623,
        1041.5020524014164
      ],
      "voteCount": 2559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.92406562095148
      }
    },
    {
      "id": "416f7e56ea47ea495799ae80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1141.442998621178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.6599325766701,
        1160.226064665686
      ],
      "voteCount": 929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.84103917287325
      }
    },
    {
      "id": "0e6c540486f1cbb4ebf6a48f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1128.123977076189,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.4381566140262,
        1145.809797538352
      ],
      "voteCount": 1066,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.42433903881857
      }
    },
    {
      "id": "1d6b165bdad05672105549a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1152.2552566023664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.3425203518614,
        1187.1679928528713
      ],
      "voteCount": 282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 317.301111216148
      }
    },
    {
      "id": "801a2035401ad1ece767b510",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1112.6092322193708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.8948789215533,
        1136.3235855171883
      ],
      "voteCount": 593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.39504901215844
      }
    },
    {
      "id": "1e2a2b1f56af363e379ea149",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1187.4191148579157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.570664810638,
        1210.2675649051937
      ],
      "voteCount": 651,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.89932729478554
      }
    },
    {
      "id": "c140238dda057acb59691186",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1087.9322411098879,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.0414528321949,
        1113.8230293875808
      ],
      "voteCount": 464,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.49957136835823
      }
    },
    {
      "id": "b07969903ea25bace8159692",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1149.7744016092397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.567497686096,
        1181.9813055323834
      ],
      "voteCount": 266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 270.0236313159768
      }
    },
    {
      "id": "bb2a01bc93c9da7f26e7391c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1178.736368952402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.0898914322056,
        1197.3828464725984
      ],
      "voteCount": 993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.5101785910502
      }
    },
    {
      "id": "1cc29ec54e1672369fafc549",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1139.846435828123,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.8705154131353,
        1159.8223562431106
      ],
      "voteCount": 858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.87652583343639
      }
    },
    {
      "id": "271f087b8499c6eb13a4332b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1106.2010501671803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.8538476527583,
        1122.548252681602
      ],
      "voteCount": 1421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.56498625155886
      }
    },
    {
      "id": "bd1f11220cd61b9853da963f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1113.5455457668675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.0879491505175,
        1149.0031423832174
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 327.2822165982832
      }
    },
    {
      "id": "b82d064a793496516c68140a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1093.3215627700881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1071.879954335993,
        1114.7631712041832
      ],
      "voteCount": 628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.67916192785917
      }
    },
    {
      "id": "f7eb315a219403e8aed8e018",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1126.8392142599155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.8077363261664,
        1152.8706921936644
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.40117336798957
      }
    },
    {
      "id": "6149b62cd5f37f95f36e9a56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nous-hermes-2-mixtral-8x7b-dpo",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1163.7544469821828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.833264067093,
        1175.6756298972723
      ],
      "voteCount": 3777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.994956533035385
      }
    },
    {
      "id": "5405b9ca90c61add143f397d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1342.8838887625234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.9031653831594,
        1365.8646121418874
      ],
      "voteCount": 685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.477367762963
      }
    },
    {
      "id": "a9778b299cd94028f8a592a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1397.1071700226464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.268904262864,
        1408.9454357824288
      ],
      "voteCount": 2519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.48211336908608
      }
    },
    {
      "id": "fb45f86ae2b5e9835aa1930c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1274.561141387543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.6414505632283,
        1289.4808322118581
      ],
      "voteCount": 1720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.946000382460525
      }
    },
    {
      "id": "3208bd264a4bfdcdb566315f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1362.797155195185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.522862484021,
        1371.0714479063492
      ],
      "voteCount": 5761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.822375057414547
      }
    },
    {
      "id": "544195ea99b4873fe6c5526d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1292.6192636551662,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.7967761867135,
        1301.4417511236188
      ],
      "voteCount": 8775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.26216829702731
      }
    },
    {
      "id": "e4980a74ab0916924289a723",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1363.9662416513838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.1096359620565,
        1385.8228473407112
      ],
      "voteCount": 713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.3567182564305
      }
    },
    {
      "id": "d44116a36c72a0cdd2df15c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1346.402545295377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.9718021083709,
        1387.8332884823828
      ],
      "voteCount": 225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 446.8371421244279
      }
    },
    {
      "id": "3bebe78ef0c4c53fcab4d385",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1312.443162103166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.8659405770359,
        1350.0203836292962
      ],
      "voteCount": 263,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 367.5810788383552
      }
    },
    {
      "id": "a3b6f86d02bd24309f959934",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1378.8007757285097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.2253791901198,
        1389.3761722668996
      ],
      "voteCount": 3202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.11368237027701
      }
    },
    {
      "id": "b9594eec99022a772e72b676",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1359.2122744137541,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.2299890762895,
        1367.1945597512188
      ],
      "voteCount": 6482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.586636010636564
      }
    },
    {
      "id": "855680e29673e3db0bb51518",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1349.9312115197713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.3507875134032,
        1362.5116355261393
      ],
      "voteCount": 2285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.199730510557856
      }
    },
    {
      "id": "2e1ad4406e8d20e56b3ce2c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1283.44482390622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.5298125753277,
        1296.3598352371125
      ],
      "voteCount": 2212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.42035811461366
      }
    },
    {
      "id": "9f8b9a5646956a93ef93bdfa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1329.9995499495144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.860109014135,
        1350.1389908848932
      ],
      "voteCount": 891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.58412835370011
      }
    },
    {
      "id": "c889f6ac6df8819408704698",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1355.8836423394948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.4929131845574,
        1369.2743714944322
      ],
      "voteCount": 2060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.678003245779344
      }
    },
    {
      "id": "3ed1ed2f275c65fd8d97c789",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1350.7787895847719,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.3863510384576,
        1375.1712281310863
      ],
      "voteCount": 583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.88674641791755
      }
    },
    {
      "id": "cd56ceddea5b7c8568a107bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1358.4537329263449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.9524948748879,
        1380.9549709778018
      ],
      "voteCount": 711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.8003751910187
      }
    },
    {
      "id": "4f5dbf758fbbb0361af42e82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1386.4052377351445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.0853666776857,
        1395.7251087926038
      ],
      "voteCount": 4256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.61120073961069
      }
    },
    {
      "id": "9b84a8c10abadddae8e69fa9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1301.2502559821876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.6042242466297,
        1312.8962877177455
      ],
      "voteCount": 2750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.306913731569594
      }
    },
    {
      "id": "aab31ca794771e6f23cadca4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1330.3963121755953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.97774547467,
        1340.8148788765207
      ],
      "voteCount": 3328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.256591354535885
      }
    },
    {
      "id": "bb6f84e900c9719b822a7363",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1230.3359112382486,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.9697895783795,
        1282.7020328981175
      ],
      "voteCount": 149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 713.8461781560122
      }
    },
    {
      "id": "c96e0d774aba46ceccd1090a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1336.4431918525563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.353431708113,
        1347.5329519969994
      ],
      "voteCount": 2920,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.014603254046406
      }
    },
    {
      "id": "cbe16edde894da341325e679",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1335.1363550882443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.9383644689378,
        1355.3343457075507
      ],
      "voteCount": 825,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.19893225456256
      }
    },
    {
      "id": "89746c7f9cdfe3efab2332a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1324.0489751941702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.677103870396,
        1337.4208465179445
      ],
      "voteCount": 2072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.54662487499207
      }
    },
    {
      "id": "8ee4a11e5e15454da2489e8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1337.5040528694399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.371782580099,
        1343.6363231587811
      ],
      "voteCount": 12246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.789181833462829
      }
    },
    {
      "id": "95d72318e0369e00c22e0318",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1316.9005677913347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.0275515434735,
        1333.773584039196
      ],
      "voteCount": 1167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.11212526004599
      }
    },
    {
      "id": "6eb94b9efba960687bb86ce6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nova-2-lite",
      "organization": "amazon",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1330.438512445752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.2061127887396,
        1374.6709121027643
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 509.3130684827013
      }
    },
    {
      "id": "e6bb5ff7d6b59cdfcd7fe626",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1405.1123630866716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.2681412528177,
        1426.9565849205255
      ],
      "voteCount": 659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.21583825292615
      }
    },
    {
      "id": "2a0d45537acc23b1782fce28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1308.693024465285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.2155957107288,
        1338.170453219841
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.19500729749456
      }
    },
    {
      "id": "6e063ec5a82aa6fc61386f36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1365.7376734967888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.3664602565505,
        1380.1088867370272
      ],
      "voteCount": 1536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.7638901356445
      }
    },
    {
      "id": "de402655bd1dd42ea1f672ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1300.8671358159077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.226340581251,
        1315.5079310505644
      ],
      "voteCount": 2287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.79986539186997
      }
    },
    {
      "id": "e39d822fbd1c9997010c6187",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1361.1754339604772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.5821014467813,
        1402.768766474173
      ],
      "voteCount": 180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 450.3511270966234
      }
    },
    {
      "id": "3e625c2168be0f4fe240e87f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1367.729363950254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.570452296105,
        1388.8882756044036
      ],
      "voteCount": 710,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.54414723289936
      }
    },
    {
      "id": "e14f9421377bfc0bc26d1ae5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1360.7421443407475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.764299346352,
        1375.719989335143
      ],
      "voteCount": 1437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.39860614088426
      }
    },
    {
      "id": "ead11efcefba0e6914dcf89e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1326.7748894794568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.62650597631,
        1349.9232729826037
      ],
      "voteCount": 599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.49066847264595
      }
    },
    {
      "id": "a658e31b66b8355790732cb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1287.1781687726805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.973462103135,
        1310.3828754422257
      ],
      "voteCount": 570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.1702938266424
      }
    },
    {
      "id": "59ff20da68e035c285194b41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1348.8708162699252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.0735282162127,
        1385.6681043236376
      ],
      "voteCount": 233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 352.4807817315642
      }
    },
    {
      "id": "13822bad23371c1bc6f00547",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1374.1248088077941,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.30456485077,
        1396.9450527648182
      ],
      "voteCount": 594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.56400278267097
      }
    },
    {
      "id": "1704b2f78fb4310cd858c287",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1406.9732317577273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.6474218037006,
        1447.299041711754
      ],
      "voteCount": 183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 423.32119758463153
      }
    },
    {
      "id": "d9613d602da7fcc784e889ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1379.168451435752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.5555498753884,
        1418.7813529961159
      ],
      "voteCount": 197,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 408.48595371576323
      }
    },
    {
      "id": "4fd81bac56d6efb754f9c642",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1387.3514907134506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.8214238357746,
        1403.8815575911267
      ],
      "voteCount": 1198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.13003776285964
      }
    },
    {
      "id": "b7530bceb1a08ec76ea162d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1297.8864954235714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.8694464193654,
        1319.9035444277772
      ],
      "voteCount": 658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.18915612012567
      }
    },
    {
      "id": "65726b51d965c90d56a87456",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1321.8141842484633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.9215667396088,
        1341.7068017573174
      ],
      "voteCount": 807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.01196754260033
      }
    },
    {
      "id": "3c72f0df9d70bfb6171b6f13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1292.6960142370108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.530181148887,
        1323.8618473251345
      ],
      "voteCount": 383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 252.8490340295469
      }
    },
    {
      "id": "5bda960b03b77d79a69eb38a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1343.501444984377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.5970155928414,
        1365.4058743759124
      ],
      "voteCount": 642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.90151511817211
      }
    },
    {
      "id": "97c48260f8ca53d77a72f8b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1390.316242953497,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.3870036799344,
        1429.24548222706
      ],
      "voteCount": 194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 394.5078526559516
      }
    },
    {
      "id": "85b0ff53eb1b2d2717be4f35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1341.8744731150596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.969156158709,
        1365.7797900714102
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.76228158559897
      }
    },
    {
      "id": "5e82f9e3735b9bca9d659586",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-llama-3.3-nemotron-super-49b-v1.5",
      "organization": "nvidia",
      "license": "Nvidia Open",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1343.136383146728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.1696384690845,
        1353.1031278243713
      ],
      "voteCount": 3345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.858926024198105
      }
    },
    {
      "id": "376d602332c1a3fe7f31cb68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1359.9373768143919,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.2131671253649,
        1380.6615865034191
      ],
      "voteCount": 850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.80462612824789
      }
    },
    {
      "id": "9d0df53c287614e344755e81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1362.9263069228664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.4746559088662,
        1373.3779579368666
      ],
      "voteCount": 3277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.43633474085073
      }
    },
    {
      "id": "0ac66ce6a4a90d12a3d0a8d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1250.0562473511095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.1845844426216,
        1262.9279102595974
      ],
      "voteCount": 2349,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.12937187748043
      }
    },
    {
      "id": "32f1601186f4f32e831e1130",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1345.2047504069594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.6034521975723,
        1352.8060486163465
      ],
      "voteCount": 7187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.041091721917963
      }
    },
    {
      "id": "1f24f0ad9d489fc1fda2c0b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1257.8476190113051,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.660594745032,
        1266.0346432775782
      ],
      "voteCount": 10978,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.448414642756426
      }
    },
    {
      "id": "ed8be16122ebcf1dd01b843f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1345.7229382837797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.9506134482817,
        1365.4952631192778
      ],
      "voteCount": 944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.76988681862422
      }
    },
    {
      "id": "39b3b4f6d0486379cab9a7ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1362.2193304326295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.0911236015093,
        1395.34753726375
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 285.6930502374032
      }
    },
    {
      "id": "4db495364176f8d8b32456d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1305.8105427673588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.721255059724,
        1340.8998304749937
      ],
      "voteCount": 281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 320.51836796904524
      }
    },
    {
      "id": "bc7bbcee73e8bbeaa4407b68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1350.8182506915637,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.982554838588,
        1360.6539465445394
      ],
      "voteCount": 3885,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.183378874477775
      }
    },
    {
      "id": "f53bcecc23b56612bea89ade",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1327.8813480731828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.6301334977686,
        1335.1325626485968
      ],
      "voteCount": 8151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.687537800859996
      }
    },
    {
      "id": "5277fe6d5d12d6bff514dc2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1316.9776474113623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8361622869184,
        1328.1191325358059
      ],
      "voteCount": 2930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.31394544944534
      }
    },
    {
      "id": "65ec951001b0f17350b53cfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1263.7742109711494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.3909402313675,
        1275.1574817109313
      ],
      "voteCount": 2868,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.731678194004665
      }
    },
    {
      "id": "9f8a5fc6b1cd29f137fc2c10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1307.8968736769323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.5611291422342,
        1325.2326182116303
      ],
      "voteCount": 1202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.23278931257892
      }
    },
    {
      "id": "a8b682043916ba97a8a57496",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1319.0561372991397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.7316632471602,
        1331.3806113511191
      ],
      "voteCount": 2492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.54035894896473
      }
    },
    {
      "id": "f525aeff4996b9f314075730",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1361.918004536849,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.155589194977,
        1384.680419878721
      ],
      "voteCount": 661,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.87780980619056
      }
    },
    {
      "id": "9e621af6c5145ae195199af6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1302.2788510042092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.1421562805924,
        1322.4155457278262
      ],
      "voteCount": 981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.55533543865214
      }
    },
    {
      "id": "af0606a292104ae2130a62d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1356.575822292175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.015114231946,
        1365.1365303524042
      ],
      "voteCount": 5214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.077575971315497
      }
    },
    {
      "id": "f72e879a26e9f49d46f595c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1272.5544027277267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.0980626961132,
        1283.0107427593402
      ],
      "voteCount": 3485,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.461855758476094
      }
    },
    {
      "id": "2ba0892dc7b6683008765242",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1293.2337595349572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.8061165291033,
        1302.6614025408112
      ],
      "voteCount": 4206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.13716137396171
      }
    },
    {
      "id": "01213ada77a70003147cafdc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1224.2906091425052,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.445993003832,
        1280.1352252811782
      ],
      "voteCount": 127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 811.8325087530776
      }
    },
    {
      "id": "30ec932f7a80dc51901cb3b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1185.5032062590421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.8941354594122,
        1229.1122770586721
      ],
      "voteCount": 212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 495.05959708908244
      }
    },
    {
      "id": "689704704b202e21a5f21d5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1291.5149054356032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.5351708527453,
        1301.4946400184608
      ],
      "voteCount": 3851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.926375107228825
      }
    },
    {
      "id": "8cf7f347103cbc76c5e1e9ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1354.0196091692214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.3984845316218,
        1372.6407338068211
      ],
      "voteCount": 987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.26421965037801
      }
    },
    {
      "id": "6531c2304ffedad44cd75b92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1299.774422478571,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.7708526185424,
        1311.7779923385997
      ],
      "voteCount": 2610,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.508065583936975
      }
    },
    {
      "id": "32a7068bd1c62b5c02414268",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1316.6728400462036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.1198898869125,
        1322.2257902054948
      ],
      "voteCount": 15513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.026964991909068
      }
    },
    {
      "id": "1cdf5e944ca008856c685131",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1278.57946870561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.4528847612244,
        1292.7060526499954
      ],
      "voteCount": 1692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.94911184853251
      }
    },
    {
      "id": "83a966fbbfa2f6213f1de272",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-nano-30b-a3b-bf16",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1328.318708946249,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.7756424546224,
        1361.8617754378756
      ],
      "voteCount": 328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.8932372255365
      }
    },
    {
      "id": "58f234709b0a57bcc145f916",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1407.5174873417532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.3447749484776,
        1436.6901997350287
      ],
      "voteCount": 388,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 221.54269721600076
      }
    },
    {
      "id": "e7d140f1bf95db8f223c7d07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1408.5163109181774,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.6426507024382,
        1422.3899711339168
      ],
      "voteCount": 1747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.105560612779584
      }
    },
    {
      "id": "29c606119b5fe765b5950676",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1304.2147483121248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.7738416203667,
        1322.6556550038827
      ],
      "voteCount": 1056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.52549395614191
      }
    },
    {
      "id": "4d9ed4c77e36bf5f54ee9f56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1383.9377712354983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9509916653187,
        1393.9245508056779
      ],
      "voteCount": 3446,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.96299240436344
      }
    },
    {
      "id": "eaf627a160bd47def4aa9a8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1323.240655976038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.796941675169,
        1333.6843702769067
      ],
      "voteCount": 5106,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.39316350616674
      }
    },
    {
      "id": "ccaf6e9b86da2b6078cab56f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1397.800265214329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9493892998134,
        1421.6511411288448
      ],
      "voteCount": 594,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.08548221970253
      }
    },
    {
      "id": "bc4b72a1bb9732dbab7f22e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1392.7069761752496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.7309184068804,
        1430.6830339436183
      ],
      "voteCount": 244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 375.42533473413664
      }
    },
    {
      "id": "e2646d7931e47611bf9e239e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1314.2575993158125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.1183036148154,
        1355.3968950168096
      ],
      "voteCount": 196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 440.57263913823925
      }
    },
    {
      "id": "55936199e34834142a29fde3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1394.2549771687636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.1947391135454,
        1407.3152152239816
      ],
      "voteCount": 2001,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.40235494393403
      }
    },
    {
      "id": "39bf9f7ed88ae5c8cd89d1be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1380.3216666166081,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.9106250317816,
        1389.7327082014347
      ],
      "voteCount": 4077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.055747268255534
      }
    },
    {
      "id": "fc429b99dab734ea306f14d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1348.0617055940395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.4949495001367,
        1363.6284616879423
      ],
      "voteCount": 1376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.081216433103116
      }
    },
    {
      "id": "31ab622138914affd0cef405",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1316.7227151779352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.5468063690046,
        1333.898623986866
      ],
      "voteCount": 1176,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.7968256807701
      }
    },
    {
      "id": "b25de7d1606d12743be08b61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1364.7145407418004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.7462580125798,
        1390.682823471021
      ],
      "voteCount": 512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.5457338946258
      }
    },
    {
      "id": "fb0cbd219e8bb2f48df9556e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1367.3276110869929,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.0374477991159,
        1384.61777437487
      ],
      "voteCount": 1127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.82193184292117
      }
    },
    {
      "id": "9243e6bb8cad3ffe629ee6b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1397.9484850720348,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.4965600932233,
        1425.4004100508464
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.177603410083
      }
    },
    {
      "id": "3d963a45988de507ad3f7ee3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1351.6996961538648,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.5200375111651,
        1377.8793547965647
      ],
      "voteCount": 479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.4151695069963
      }
    },
    {
      "id": "a8b3b47d4fc45acde3d30133",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1403.5987458492323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.2203044218688,
        1414.977187276596
      ],
      "voteCount": 2651,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.70306317446072
      }
    },
    {
      "id": "de066521f2569ee7251bc780",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1326.0020904039102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.4069389783613,
        1340.5972418294593
      ],
      "voteCount": 1603,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.45248695291659
      }
    },
    {
      "id": "48cc462158d88c384d4aa91a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1346.8227066379673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.7192216217413,
        1359.9261916541932
      ],
      "voteCount": 1963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.69690489599775
      }
    },
    {
      "id": "3740d479e67a42d7c9741bf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1361.4042522660834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.527609262837,
        1374.28089526933
      ],
      "voteCount": 2013,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.16275216588146
      }
    },
    {
      "id": "fe0b7eeed46c43884c755975",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1374.7365804968115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.3151858292536,
        1400.1579751643694
      ],
      "voteCount": 511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.22965883751647
      }
    },
    {
      "id": "0b9fa21f5870c9909c577ed1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1348.7541552686234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.327797646525,
        1365.180512890722
      ],
      "voteCount": 1287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.24030123022858
      }
    },
    {
      "id": "57653a9b7f302218de3c807d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1361.241563849796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.990805202504,
        1368.492322497088
      ],
      "voteCount": 7458,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.685816616870696
      }
    },
    {
      "id": "84b08baeb653d2c39255bef7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1329.4515970843147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.8069543596057,
        1350.0962398090237
      ],
      "voteCount": 806,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.94776571205593
      }
    },
    {
      "id": "aad98ca93bda9cb5d30695e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "nvidia-nemotron-3-super-120b-a12b",
      "organization": "nvidia",
      "license": "NVIDIA Open Model",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1387.23428881417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.2463798569313,
        1421.2221977714084
      ],
      "voteCount": 314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.7133511525721
      }
    },
    {
      "id": "a1b893b7a93d04c2ef24fb35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1429.7443547190223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.6301267462097,
        1443.858582691835
      ],
      "voteCount": 1780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.85827587044909
      }
    },
    {
      "id": "4f6579c10fcfe21a922aefff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1432.8018050501105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.2536501352156,
        1442.3499599650052
      ],
      "voteCount": 3973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.732458561759774
      }
    },
    {
      "id": "1e8da97b23c59c009970c88c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1381.2813704874281,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.3948360076124,
        1390.167904967244
      ],
      "voteCount": 4642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.557423298549615
      }
    },
    {
      "id": "83d5fbc5d2e72b0992f8c81a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1411.413623409923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.8960656802028,
        1416.9311811396433
      ],
      "voteCount": 16316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.924969320716226
      }
    },
    {
      "id": "d80f5a3e6e4e0edc09a36dec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1386.2099764905468,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.74963459893,
        1392.6703183821633
      ],
      "voteCount": 19214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.864627034850221
      }
    },
    {
      "id": "ded5d5b626008d29db444169",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1400.6573333875676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.893773668653,
        1417.4208931064823
      ],
      "voteCount": 1330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.15370216537772
      }
    },
    {
      "id": "4a01383c14f707bd575850df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1388.306190001429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.6040264590183,
        1425.0083535438396
      ],
      "voteCount": 252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 350.66074415199887
      }
    },
    {
      "id": "4b130af772e327e3920ac666",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1374.8416139114136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.922146778229,
        1398.7610810445979
      ],
      "voteCount": 556,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.9384462104193
      }
    },
    {
      "id": "0b8e059c9f5dec57a2926de2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1422.7278026916665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.3608097962194,
        1432.0947955871138
      ],
      "voteCount": 4238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.84042599407705
      }
    },
    {
      "id": "b7ec580aab4e9c182d3a257d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1417.605535453923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.9280678137877,
        1425.2830030940586
      ],
      "voteCount": 6453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.344043009857355
      }
    },
    {
      "id": "d3e91572b53848d95dd3b6d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1370.3811392055159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.7693747029457,
        1381.9929037080856
      ],
      "voteCount": 2720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.09944558999028
      }
    },
    {
      "id": "41f2fa40db2921569c37c126",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1389.8093463431996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.3767299574458,
        1398.2419627289537
      ],
      "voteCount": 5210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.510941397111143
      }
    },
    {
      "id": "dd6918eaf80438fa2227e0fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1406.666852036115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.085342610987,
        1422.248361461243
      ],
      "voteCount": 1454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.20084303844746
      }
    },
    {
      "id": "713b86445c7c48d1cdf27eaa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1410.6422431438743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.7754092106802,
        1419.5090770770687
      ],
      "voteCount": 4820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.466376881436567
      }
    },
    {
      "id": "041ab6dc809f09ac9ace5dc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1414.014424656073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.6412845544035,
        1425.3875647577424
      ],
      "voteCount": 2644,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.67166532552621
      }
    },
    {
      "id": "9dc714d9e7ed1a983eb45374",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1398.4295359282155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.1086317493025,
        1415.7504401071287
      ],
      "voteCount": 1273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.09890345795259
      }
    },
    {
      "id": "c5c68826ef0ef9e71f356f2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1422.8286850074198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.172281009583,
        1430.4850890052567
      ],
      "voteCount": 6584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.25996370501217
      }
    },
    {
      "id": "c6060173524a5ecce3813710",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1397.1920688230177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.9868224795084,
        1404.3973151665268
      ],
      "voteCount": 7663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.514546763063178
      }
    },
    {
      "id": "bb4d3ceb57622e0c3fedfb1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1406.4041591668856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.9302191769393,
        1412.8780991568317
      ],
      "voteCount": 10246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.91041215062427
      }
    },
    {
      "id": "f09d38ec2a3bfbfa80119f94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1375.054320709308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.349118989193,
        1400.759522429423
      ],
      "voteCount": 581,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.00689277528465
      }
    },
    {
      "id": "6a320d9ef2c2aa7a07cdf079",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1409.8810460723184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.5241997668124,
        1441.2378923778244
      ],
      "voteCount": 396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 255.95792018654382
      }
    },
    {
      "id": "8f51dc16c2868aea52659c2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1411.6481070722143,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.8685372405912,
        1421.4276769038377
      ],
      "voteCount": 3571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.89678805780193
      }
    },
    {
      "id": "cb80628f6861d2ff96ed2927",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1408.7428864683884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.998494804563,
        1419.4872781322138
      ],
      "voteCount": 2986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.051591755660223
      }
    },
    {
      "id": "81e2faf83e3a271ebade46b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1385.8336790025303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.747046396089,
        1394.9203116089716
      ],
      "voteCount": 4399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.49362936800256
      }
    },
    {
      "id": "dac2d7b2119fb4de39ce6421",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1401.8777687713957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.4334505087256,
        1406.3220870340658
      ],
      "voteCount": 27807,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.14178746717213
      }
    },
    {
      "id": "d8995b1f395bbfac37c7796d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1386.3149976057362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.8466484770684,
        1396.783346734404
      ],
      "voteCount": 3078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.527270132204258
      }
    },
    {
      "id": "9e8de23562c8a627e1629486",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-2024-12-17",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1387.5787279730846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.790035830942,
        1436.367420115227
      ],
      "voteCount": 142,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 619.6438884409675
      }
    },
    {
      "id": "3dbd342a5db5595634066bac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1349.2148918758305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.1624205853054,
        1359.2673631663556
      ],
      "voteCount": 4309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.30567806752498
      }
    },
    {
      "id": "06adb33e4387dec435a009a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1387.64064772859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.2470324619958,
        1395.0342629951842
      ],
      "voteCount": 8478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.2304133044272
      }
    },
    {
      "id": "c3495c699926e3cb779ad28f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1280.8440889126675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.2024187123288,
        1288.4857591130062
      ],
      "voteCount": 7858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.201288410581775
      }
    },
    {
      "id": "6351f02d2412876122c3bfdc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1353.7734953489146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.0269293812405,
        1358.5200613165887
      ],
      "voteCount": 27352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.86493036554546
      }
    },
    {
      "id": "a8139acea2a04d00917d6fb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1291.2352310187098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.6718540263853,
        1296.798608011034
      ],
      "voteCount": 34410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.057137926869949
      }
    },
    {
      "id": "eb0f39cdc2feef9f7db5e873",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1350.7528223390925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.096998249462,
        1362.408646428723
      ],
      "voteCount": 3191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.36631304663051
      }
    },
    {
      "id": "2ee8ca115d239562d448951b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1325.5513805539763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.0538216960467,
        1355.0489394119056
      ],
      "voteCount": 424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.50404942250353
      }
    },
    {
      "id": "719d72a42c43f71b8f6e3dde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1299.7322686432353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.9937644658362,
        1317.4707728206345
      ],
      "voteCount": 1169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.91016619950449
      }
    },
    {
      "id": "c09db5326c9f93e6961e709f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1375.2973625238074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.932388989242,
        1382.6623360583724
      ],
      "voteCount": 8369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.120373976843391
      }
    },
    {
      "id": "fff3aa2386b66d085fb2e401",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1360.4997933168715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.4853042122681,
        1366.5142824214745
      ],
      "voteCount": 13899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.416755685240947
      }
    },
    {
      "id": "be67fa50c22783a58713b832",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1318.577176936602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.0541815216598,
        1327.1001723515442
      ],
      "voteCount": 6092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.909860611235
      }
    },
    {
      "id": "3f9bdfe17274a8562fe7e7e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1282.0147373793666,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.837924879806,
        1289.191549878927
      ],
      "voteCount": 8598,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.408093138049558
      }
    },
    {
      "id": "9b8c326027bdbd8f164a43de",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1343.077652562216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.4282802287314,
        1354.7270248957007
      ],
      "voteCount": 3138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.32717181115929
      }
    },
    {
      "id": "28a68503fef3836d44dd4102",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1340.126449645757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.8306841792091,
        1347.422215112305
      ],
      "voteCount": 8979,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.856244782874992
      }
    },
    {
      "id": "dcf2871cf7e5c97052c933bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1375.8892065117861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.6386120626596,
        1384.139800960913
      ],
      "voteCount": 6318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.72043172693916
      }
    },
    {
      "id": "a17b4fabe700ea2822b8c9d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1336.8096531708056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.2489779032244,
        1349.3703284383869
      ],
      "voteCount": 2639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.07048143473824
      }
    },
    {
      "id": "3c4fda1aa31aee3eaab56657",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1375.6175063315632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.3884623756157,
        1381.8465502875106
      ],
      "voteCount": 13214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.100586890610856
      }
    },
    {
      "id": "47c240f8cef2b9a1c15e21bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1310.0356750628473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.986891535198,
        1316.0844585904965
      ],
      "voteCount": 14272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.524449921801057
      }
    },
    {
      "id": "2ee9d1584286c946acab8ace",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1331.8712403165675,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.6264606042791,
        1337.116020028856
      ],
      "voteCount": 21478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.1607468710181275
      }
    },
    {
      "id": "9a9fef0de5ed9ba763792949",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1276.4993630342253,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.4797184338006,
        1294.51900763465
      ],
      "voteCount": 1093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.52715665632049
      }
    },
    {
      "id": "5c5a77f11236bb33e56858bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1251.5164420406513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.6326650413348,
        1275.4002190399683
      ],
      "voteCount": 716,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.49431697149367
      }
    },
    {
      "id": "2b83beaeab5cb5464d182bdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1344.5993842496875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.989022739202,
        1352.209745760173
      ],
      "voteCount": 7913,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.076981173994303
      }
    },
    {
      "id": "e886cb9ac49e1acf9e4ea1a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1361.717583293931,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.9298316288523,
        1369.5053349590098
      ],
      "voteCount": 7499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.78803231475953
      }
    },
    {
      "id": "d77dadf313759a16bfd3cf0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1323.9961462845881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.6915585548784,
        1331.3007340142976
      ],
      "voteCount": 9326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.889775835572719
      }
    },
    {
      "id": "f502af264ba2e1d0ecb0121e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1336.9528978039702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.3198646326123,
        1340.5859309753282
      ],
      "voteCount": 51981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.435916051757198
      }
    },
    {
      "id": "6c3fbe5c2c02df231cf0407e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1309.2217739131522,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.303569150392,
        1317.1399786759125
      ],
      "voteCount": 7413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.32139496777753
      }
    },
    {
      "id": "776130018b865bf72fc3731e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1332.6557623187045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.7810025069261,
        1360.530522130483
      ],
      "voteCount": 425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.26749025099244
      }
    },
    {
      "id": "d12b400e92b7632db2159dc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1385.3255117801282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.9753617628205,
        1397.6756617974356
      ],
      "voteCount": 2763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.705281917466806
      }
    },
    {
      "id": "c0bf36d21773d4026f18235c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1416.6188551915184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.3041308488503,
        1425.9335795341865
      ],
      "voteCount": 5123,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.58623445668414
      }
    },
    {
      "id": "334b878f67b39c74882dfc94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1364.9422725702932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.0734745169973,
        1374.811070623589
      ],
      "voteCount": 4508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.353174292036027
      }
    },
    {
      "id": "5b32825e9277a188049751d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1409.25556365321,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.9880932249125,
        1415.5230340815074
      ],
      "voteCount": 15891,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.225590694340566
      }
    },
    {
      "id": "f6562bbef5d608c4e820f2b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1365.899432092783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.525936321229,
        1373.272927864337
      ],
      "voteCount": 21521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.153071119814586
      }
    },
    {
      "id": "9608037de1a2780ac33b5262",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1379.949591556865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.4255893873133,
        1394.473593726417
      ],
      "voteCount": 1982,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.91315900219146
      }
    },
    {
      "id": "36598044605228dc889bca2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1391.2143446254368,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.4279666412785,
        1426.0007226095952
      ],
      "voteCount": 290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 315.0084771800537
      }
    },
    {
      "id": "784889261d675cd2210b8a1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1353.32328474095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.04045095295,
        1374.6061185289502
      ],
      "voteCount": 774,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.91328117524637
      }
    },
    {
      "id": "ff09d06fa6d712e0b1c05618",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1413.0275551696254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.5786781925108,
        1422.47643214674
      ],
      "voteCount": 4917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.241502849825125
      }
    },
    {
      "id": "43b2ab879ea067d225333d49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1396.40628759113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.708595102808,
        1404.1039800794517
      ],
      "voteCount": 8496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.424991496865312
      }
    },
    {
      "id": "2633c3d0ab43070375bcf739",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1353.6659735174978,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.172264552283,
        1364.1596824827127
      ],
      "voteCount": 3778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.665653593218604
      }
    },
    {
      "id": "35388865241435cc44e67501",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1371.6355813150503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.0898899736496,
        1381.1812726564513
      ],
      "voteCount": 4823,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.720213449751284
      }
    },
    {
      "id": "4adfeddccea4062b0d57281c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1391.4336200544194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.1167407338176,
        1405.7504993750213
      ],
      "voteCount": 1945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.358123319317414
      }
    },
    {
      "id": "00e7ce3641e1dca9292d92fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1389.157029247277,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.0709254328726,
        1398.2431330616814
      ],
      "voteCount": 5419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.491127818784168
      }
    },
    {
      "id": "850d47215cd945f351f00130",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1397.4392142083668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.1270521859212,
        1407.7513762308126
      ],
      "voteCount": 3876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.68237030273759
      }
    },
    {
      "id": "2cd6becc747d15c3ec506d72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1365.8259506662616,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.5142333430351,
        1381.1376679894884
      ],
      "voteCount": 1699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.031159861303564
      }
    },
    {
      "id": "ee4e66a92901bc624638c786",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1407.2421598657788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.3778793596794,
        1415.106440371878
      ],
      "voteCount": 8206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.099849240981655
      }
    },
    {
      "id": "e6d9c32d551ac034bd95657f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1380.712477910322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.769296795364,
        1388.6556590252799
      ],
      "voteCount": 8360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.424522341651578
      }
    },
    {
      "id": "c48b682fc879ed3430f39a2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1380.1958555915587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.3413073095955,
        1387.0504038735219
      ],
      "voteCount": 12782,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.23098680549559
      }
    },
    {
      "id": "04de67f740196019b5a86c47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1347.3530578594273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.7461472556315,
        1370.959968463223
      ],
      "voteCount": 674,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.0715090979176
      }
    },
    {
      "id": "bb5f74f0395615b3efc70407",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1345.0032316548939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.1641045215288,
        1374.8423587882592
      ],
      "voteCount": 493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.78004753940093
      }
    },
    {
      "id": "a9522e1d320640f8bd54ba1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1381.2693235103002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.6279296447078,
        1390.9107173758923
      ],
      "voteCount": 4578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.198222605099936
      }
    },
    {
      "id": "f3b1c1eb090e3c641363d3b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1385.6860639420008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.047399364613,
        1395.3247285193886
      ],
      "voteCount": 4569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.18452446630699
      }
    },
    {
      "id": "58ea641f8771ba17a5633461",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1390.3221602397682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.0688266761879,
        1399.5754938033485
      ],
      "voteCount": 5871,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.28949626574677
      }
    },
    {
      "id": "ba17130d118916e68535801e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1388.1127400222329,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.1206047195824,
        1393.1048753248833
      ],
      "voteCount": 31122,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.487487187345711
      }
    },
    {
      "id": "fade2196dac7409b502bb6cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1357.6249461789423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.916148279769,
        1367.3337440781156
      ],
      "voteCount": 4488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.53775012222011
      }
    },
    {
      "id": "034400f39789aeec1b643dbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o1-preview",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1349.1392896992725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.916467311735,
        1380.3621120868102
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 253.77459016144297
      }
    },
    {
      "id": "a0f87c1df476ba9623b3cd08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1464.8812208084696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.4795353902746,
        1476.2829062266646
      ],
      "voteCount": 2975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.84090171035417
      }
    },
    {
      "id": "1c9c19f18ac735ac4bb84fa8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1458.5439604089806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.347432718879,
        1464.740488099082
      ],
      "voteCount": 11756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.995409870684824
      }
    },
    {
      "id": "cdee03bc8b57faedea92753f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1383.4060623265252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.1555038998254,
        1390.656620753225
      ],
      "voteCount": 7709,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.685060794037076
      }
    },
    {
      "id": "daed5042c95afaeebdfe0090",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1437.8763035344557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.3273929978907,
        1442.425214071021
      ],
      "voteCount": 30172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.386648155175212
      }
    },
    {
      "id": "0f74b3f8d271f6b17550a595",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1424.255230687363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.25094680015,
        1429.2595145745763
      ],
      "voteCount": 43546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.519100787678697
      }
    },
    {
      "id": "52d6849fb98fa6ad60d1e6c6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1444.4629547789516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.9966038554105,
        1455.929305702493
      ],
      "voteCount": 2954,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.22585263533679
      }
    },
    {
      "id": "0219247b3e936665c7d4448e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1479.1082850757991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.8219315735782,
        1502.3946385780198
      ],
      "voteCount": 764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 141.1584204701709
      }
    },
    {
      "id": "1c85dff4c9f3ebf7f517a7e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1439.2252605412511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.639436487821,
        1455.811084594681
      ],
      "voteCount": 1413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.61070113505247
      }
    },
    {
      "id": "1adba1ee513cd7bad3b418bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1445.4517130436598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.607308502896,
        1451.2961175844234
      ],
      "voteCount": 13973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.891690899325209
      }
    },
    {
      "id": "53c3673516bfac9e7dcf8e23",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1439.9855937640177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.194732853495,
        1444.7764546745404
      ],
      "voteCount": 25759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.9749041536849345
      }
    },
    {
      "id": "e26bb9f15fb73076f9f2db53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1426.187877051097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.3173566864557,
        1433.0583974157385
      ],
      "voteCount": 9571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.288053128842623
      }
    },
    {
      "id": "34fe5e568290773d390e83eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1394.7676973622104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.3338467613296,
        1401.2015479630913
      ],
      "voteCount": 10597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.775706700657706
      }
    },
    {
      "id": "b9dd131a1b5f2576707b0d33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1451.9934930935228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.8737853182,
        1462.113200868846
      ],
      "voteCount": 3813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.658748730106016
      }
    },
    {
      "id": "45a2514a9d38e3b013f57673",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1454.324747171132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.5709721419419,
        1461.078522200322
      ],
      "voteCount": 10011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.873998726522336
      }
    },
    {
      "id": "231abe797f3c6e622aeb3ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1449.3773118486808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.1236470971785,
        1459.6309766001834
      ],
      "voteCount": 3457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.36919637660109
      }
    },
    {
      "id": "ddcafe98c0f330209efefa4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1475.4138675456195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.2536669654792,
        1486.5740681257596
      ],
      "voteCount": 3337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.42259849773852
      }
    },
    {
      "id": "b09bce519e30d1e3eefc489d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1453.2056564411623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.970172315204,
        1458.4411405671206
      ],
      "voteCount": 19604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.135386662353429
      }
    },
    {
      "id": "46f56b9ba4e9603124a2167e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1396.4048114546151,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.487401587903,
        1402.3222213213273
      ],
      "voteCount": 13307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.1152192864938
      }
    },
    {
      "id": "5e04f374d5063bb2802270e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1401.7166546451358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.1724907633802,
        1407.2608185268914
      ],
      "voteCount": 15513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.001583404246807
      }
    },
    {
      "id": "317fd8cdb53762a3e0a56b06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1427.6060051289376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.290428065263,
        1445.9215821926118
      ],
      "voteCount": 1281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.32629421100535
      }
    },
    {
      "id": "12929407616faff3e5b90bc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1394.9767598896115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.2493047752582,
        1413.704215003965
      ],
      "voteCount": 1144,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.2980176100768
      }
    },
    {
      "id": "937e8209be93b2c758bce7ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1408.1492186379921,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.9491550373195,
        1414.3492822386647
      ],
      "voteCount": 11463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.006820441573902
      }
    },
    {
      "id": "d78b5afbcee6150a715e4034",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1447.7273924108874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.816087619043,
        1457.6386972027321
      ],
      "voteCount": 3732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.572046262125834
      }
    },
    {
      "id": "0b369f07c17beb8c46d98e27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1418.3470845444526,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.5908227068085,
        1425.1033463820968
      ],
      "voteCount": 9948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.882744589868913
      }
    },
    {
      "id": "9bab2d5935712e07c4ef0e11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1431.1939722919421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.5861519192058,
        1434.8017926646787
      ],
      "voteCount": 59775,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.3883918712891816
      }
    },
    {
      "id": "1ac9556fedd191f27d5344dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1431.152702719313,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.485762258918,
        1440.8196431797082
      ],
      "voteCount": 3805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.32662752009904
      }
    },
    {
      "id": "7c492db629e998a6ba00b9c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1404.2306569676173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.6621567922962,
        1423.7991571429384
      ],
      "voteCount": 1070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.68249485031606
      }
    },
    {
      "id": "c13b62977346d3542c9d628a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1412.581755464388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.3979602165477,
        1429.7655507122283
      ],
      "voteCount": 1181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.86736547298044
      }
    },
    {
      "id": "57bec85742e0f1c025173260",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1434.6758934156949,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.1510018918025,
        1446.2007849395873
      ],
      "voteCount": 2596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.57621982616662
      }
    },
    {
      "id": "42cc17b287c5bd388c94ac7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1311.9058688448101,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.1487038784926,
        1322.6630338111277
      ],
      "voteCount": 3065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.123086960922162
      }
    },
    {
      "id": "29e144a3498e8d6228f1cb14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1378.8627680476907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.3848872408112,
        1385.3406488545704
      ],
      "voteCount": 11130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.923698966153593
      }
    },
    {
      "id": "f98b2c3587aa2ff618a067ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1329.6821314982822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.9336459357726,
        1337.4306170607915
      ],
      "voteCount": 12679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.62922611300292
      }
    },
    {
      "id": "6a15556f711dab69c7f74977",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1397.2308819556322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.8968863260566,
        1417.5648775852078
      ],
      "voteCount": 847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.63394782112834
      }
    },
    {
      "id": "535f37c1a85c557844344453",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1374.0569258571882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.9042974483286,
        1418.209554266048
      ],
      "voteCount": 203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 507.4776761653735
      }
    },
    {
      "id": "232841c434cb31d2af0faf58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1325.691105021809,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.1913591281357,
        1355.1908509154828
      ],
      "voteCount": 377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 226.5376380200439
      }
    },
    {
      "id": "df5ce515230b518bab092ea5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1413.69011610769,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.8200613972244,
        1424.560170818156
      ],
      "voteCount": 2944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.758650534529657
      }
    },
    {
      "id": "5d288a9947267bca4c617c3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1401.2663633616237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.189277788484,
        1410.343448934763
      ],
      "voteCount": 4386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.448487761533972
      }
    },
    {
      "id": "addc976acee6168fd214c681",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1349.5574554848263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.907813646445,
        1363.2070973232073
      ],
      "voteCount": 1815,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.50051269908427
      }
    },
    {
      "id": "0f91f09ed974a633b4033aa5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1310.1714984387036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.8961492968065,
        1320.4468475806007
      ],
      "voteCount": 3214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.485079214985973
      }
    },
    {
      "id": "50734afa95b244cc5764ef7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1359.1965080347995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.0398757622247,
        1377.3531403073744
      ],
      "voteCount": 1023,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.8172144669596
      }
    },
    {
      "id": "8c2f48b04963c175f78f5ece",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1372.5442182720487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.10975553971,
        1382.9786810043875
      ],
      "voteCount": 3382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.34288159644788
      }
    },
    {
      "id": "c5d3fdf50891ed4133a55c27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1412.4957756710398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.777308387835,
        1426.2142429542446
      ],
      "voteCount": 1711,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.99085305471393
      }
    },
    {
      "id": "fbbe288ec1f53064a17f0a0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1368.0324671942435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.1397483006394,
        1388.9251860878478
      ],
      "voteCount": 824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.63019184682948
      }
    },
    {
      "id": "24403995bc1c0261b4dd7d29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1410.8181817338036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.5972024671178,
        1420.03916100049
      ],
      "voteCount": 4338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.133898241629893
      }
    },
    {
      "id": "caab6f211eb1b290ce93afb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1340.6860932190862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.922131555547,
        1349.4500548826254
      ],
      "voteCount": 4762,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.99423334339089
      }
    },
    {
      "id": "20f870afc07e2a3b295ccff0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1366.1486212370191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.537835783016,
        1373.7594066910226
      ],
      "voteCount": 6681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.078660980258407
      }
    },
    {
      "id": "f4108150ea5a09b55e1eec0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1316.1195170731958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.8370255761397,
        1346.4020085702518
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.71902161991073
      }
    },
    {
      "id": "d4607639b26c08ec5c6a883d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1331.5516239060767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.318660779269,
        1371.7845870328842
      ],
      "voteCount": 241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 421.3741178853973
      }
    },
    {
      "id": "fb53b4724ab58929e32ca881",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1372.4096998132757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.2095733647402,
        1384.6098262618111
      ],
      "voteCount": 2160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.74650030307025
      }
    },
    {
      "id": "2bdb4e08999a87b2db682cf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1405.6076821859554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.5478353054216,
        1418.6675290664894
      ],
      "voteCount": 1909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.399695142943536
      }
    },
    {
      "id": "ef76cd69e5f17d3f35cbc6ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1344.8917852203886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.2167922700014,
        1356.5667781707755
      ],
      "voteCount": 2535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.48273370973092
      }
    },
    {
      "id": "bf7ef7904cbbd38f03c2a4a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1363.4335535162381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.1909838287802,
        1368.676123203696
      ],
      "voteCount": 18589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.154713407258827
      }
    },
    {
      "id": "a082806360e95fab0eb64058",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1328.436297459877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.026628693528,
        1341.8459662262262
      ],
      "voteCount": 1740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.81013771500119
      }
    },
    {
      "id": "37096ece0bb418c140c4ce72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini-high",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1342.918640305103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.8003240046187,
        1393.0369566055876
      ],
      "voteCount": 126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 653.8780567590552
      }
    },
    {
      "id": "90dfc30259e76e16df9df8e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1360.8917097187577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.4739452660792,
        1371.3094741714362
      ],
      "voteCount": 3367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.25223990605756
      }
    },
    {
      "id": "46076ed24ea93fe060df3480",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1415.6917522506787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.3040440260934,
        1422.0794604752646
      ],
      "voteCount": 9460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.621698231575941
      }
    },
    {
      "id": "25aa89e1b2baa433fc19a1ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1301.0654470946984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.1491520910984,
        1307.9817420982981
      ],
      "voteCount": 8186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.452336159151637
      }
    },
    {
      "id": "e733e6a16479bcbf02000a48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1362.8467750498871,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.5618016608814,
        1367.1317484388933
      ],
      "voteCount": 30411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.779693809439401
      }
    },
    {
      "id": "d4db1b431c588564483b58c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1306.772993813563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.8840974193745,
        1311.6618902077516
      ],
      "voteCount": 40077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.221935225324587
      }
    },
    {
      "id": "01a1a8fb5038607d00de3975",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1365.7106749454138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.381980699237,
        1377.0393691915906
      ],
      "voteCount": 2861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.409004056476995
      }
    },
    {
      "id": "17d8e093d35a343d541ab0a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1359.1084012356785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.989317475463,
        1382.227484995894
      ],
      "voteCount": 656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.13777522032115
      }
    },
    {
      "id": "789a5aeaadf3fa27269fa139",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1326.670608542216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.0475977609976,
        1343.2936193234348
      ],
      "voteCount": 1282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.93217481440531
      }
    },
    {
      "id": "578486f2e46b26bf8e874d06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1383.0329621910994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.0574357608677,
        1389.008488621331
      ],
      "voteCount": 11290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.295144835613405
      }
    },
    {
      "id": "71a91931407dce23cdfd7520",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1370.0320619299223,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.1567638138495,
        1374.9073600459951
      ],
      "voteCount": 20111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.18737121234767
      }
    },
    {
      "id": "915f9b2efdec03843b19754e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1326.9265132427847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.8111140444107,
        1334.0419124411587
      ],
      "voteCount": 7713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.179603925332337
      }
    },
    {
      "id": "bfb69c2c8654340386e06a2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1301.2145857302007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.9980032383453,
        1307.431168222056
      ],
      "voteCount": 10298,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.060214018136824
      }
    },
    {
      "id": "06923c5ed21072415df3e064",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1340.48277196547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.4107050814168,
        1350.5548388495233
      ],
      "voteCount": 3633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.40833497168988
      }
    },
    {
      "id": "f47160087a47b44c7eecae08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1349.7695491348572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.277998260602,
        1356.2611000091122
      ],
      "voteCount": 9656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.969851486115045
      }
    },
    {
      "id": "1d3aec528d8a40ba3a3e71e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1392.0210963338038,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.228910034591,
        1400.8132826330168
      ],
      "voteCount": 4380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.12322493309916
      }
    },
    {
      "id": "206d25ab7e78b1e33a35488b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1342.2198697599279,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.077591636054,
        1353.362147883802
      ],
      "voteCount": 3045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.31854552779704
      }
    },
    {
      "id": "a6a46e7b0d729994732bf237",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1389.3963014957521,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.173811304387,
        1394.618791687117
      ],
      "voteCount": 16876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.100012019385642
      }
    },
    {
      "id": "f3cf091b4d29393cf9010129",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1323.8156648966701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.2163070436145,
        1329.4150227497257
      ],
      "voteCount": 13437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.161693208235176
      }
    },
    {
      "id": "0f007ea9ad82386573f4cf9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1343.0268116227448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.9383912515527,
        1348.1152319939372
      ],
      "voteCount": 16953,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.740153437148092
      }
    },
    {
      "id": "080bfbf996b0b540f8160729",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1298.8003600230288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.0343906909793,
        1315.5663293550783
      ],
      "voteCount": 1323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.17473406950016
      }
    },
    {
      "id": "61cfe35284ac81230261f8e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1292.3301157975523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.3354455427225,
        1311.3247860523818
      ],
      "voteCount": 1072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.92200071131157
      }
    },
    {
      "id": "df8994e870d0249e0f015bb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1358.1013563818428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.641052033854,
        1364.5616607298314
      ],
      "voteCount": 9223,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.864500757839526
      }
    },
    {
      "id": "117f0bd82fc48ac85d2b1a8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1381.9375618019974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.4821335089157,
        1390.3929900950789
      ],
      "voteCount": 4722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.61122843079851
      }
    },
    {
      "id": "69446b47891f0375bd2b0889",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1339.653753077983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.1124049815512,
        1346.195101174415
      ],
      "voteCount": 9490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.138798283658495
      }
    },
    {
      "id": "deb42391c460eaafc3c5f3cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1347.5838214946589,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.0685126270457,
        1351.0991303622718
      ],
      "voteCount": 57344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.216849902997574
      }
    },
    {
      "id": "eaeb9c3e38fcb99441e2f184",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1326.729084208324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.0115139143493,
        1335.4466545022985
      ],
      "voteCount": 4444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.783117658581737
      }
    },
    {
      "id": "c7ce41b504cd2321b6f12994",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o3-mini",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1326.9031031740674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.4330313001483,
        1348.373175047987
      ],
      "voteCount": 837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.9971177064355
      }
    },
    {
      "id": "eef56adbb26abc6c45e3b267",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1401.06866765257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.4913901882774,
        1413.6459451168625
      ],
      "voteCount": 2299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.17912381661814
      }
    },
    {
      "id": "09e11ec21c9c571a71ddc3a9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1432.056213099608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.1924763496345,
        1438.9199498495814
      ],
      "voteCount": 8721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.263799866641376
      }
    },
    {
      "id": "93f2e88ec8e6a3cc049e187c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1337.877833177095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.7384942961492,
        1346.0171720580406
      ],
      "voteCount": 5836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.245749729761513
      }
    },
    {
      "id": "81a883cf214805170fffc9d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1403.0764149842018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.155283319478,
        1407.997546648926
      ],
      "voteCount": 22996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.304255230093419
      }
    },
    {
      "id": "c42bb4ea24aecbfb83a04a84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1367.4477489407577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.9924277188386,
        1372.9030701626768
      ],
      "voteCount": 32158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.747194756845735
      }
    },
    {
      "id": "a6e7cf1fdfab34c0050be4dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1406.1282946640545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.5692439599575,
        1418.6873453681515
      ],
      "voteCount": 2252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.05985823364333
      }
    },
    {
      "id": "8d2e7fe3ff21eb0e87d36d67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1410.1080827639269,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.4062416276386,
        1435.8099239002152
      ],
      "voteCount": 564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.96192088182787
      }
    },
    {
      "id": "ab8d62f92abd6cd720debc93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1378.865588209361,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.7178934996746,
        1397.0132829190472
      ],
      "voteCount": 1132,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.7327485854624
      }
    },
    {
      "id": "0d0b271ef2bc1ffbf1223412",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1417.054197323518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.6971987994643,
        1423.411195847572
      ],
      "voteCount": 10493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.51981346698917
      }
    },
    {
      "id": "24bb568f0524ee9663048a20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1405.4381506235943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.2712474007906,
        1410.6050538463978
      ],
      "voteCount": 19535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.949674631419114
      }
    },
    {
      "id": "5a1015cb31ebaf3a1e6bfbdb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1379.3370069923396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.8296948113539,
        1386.8443191733254
      ],
      "voteCount": 7117,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.671440932586092
      }
    },
    {
      "id": "8986b8074a03d08f5d0700e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1349.7799315180505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.7356740988178,
        1356.8241889372832
      ],
      "voteCount": 7991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.917374597666447
      }
    },
    {
      "id": "83558424ef86c3e0e9e896e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1399.0686035345543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.5411770682913,
        1410.5960300008173
      ],
      "voteCount": 2778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.59143183294398
      }
    },
    {
      "id": "c85a4c13eb6ef9a3a1c3d5d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1403.2290849562646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.8653461658143,
        1410.5928237467147
      ],
      "voteCount": 7579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.115639788163046
      }
    },
    {
      "id": "d9d3fc0625184d82009cc475",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1409.638181880925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.7324502844672,
        1420.5439134773826
      ],
      "voteCount": 2788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.960889392661695
      }
    },
    {
      "id": "81aaa567f39a5fe91edd46e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1418.0292074154793,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.6037071089581,
        1430.4547077220002
      ],
      "voteCount": 2505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.191256778708784
      }
    },
    {
      "id": "64cb02e4751da21c210ddc7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1421.3028456483225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.6287578860938,
        1426.9769334105513
      ],
      "voteCount": 14991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.381001446647447
      }
    },
    {
      "id": "27f796d81c196c843fe612ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1353.8214256416368,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.3323719120199,
        1360.310479371254
      ],
      "voteCount": 10056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.961413429455723
      }
    },
    {
      "id": "1e2e05e45149d8878ba76392",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1367.6860237338738,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.644397657199,
        1373.7276498105484
      ],
      "voteCount": 11897,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.50192292931034
      }
    },
    {
      "id": "34150795e5771a94ed43ea70",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1341.6820685139407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.678608888543,
        1361.6855281393384
      ],
      "voteCount": 983,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.16313584551543
      }
    },
    {
      "id": "04aaad101430a635e01cd250",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1362.222710406806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.8688134617255,
        1382.5766073518869
      ],
      "voteCount": 938,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.84473820706094
      }
    },
    {
      "id": "f171c0902281a2c5f8b74eeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1367.5568915585836,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.6185405172623,
        1374.4952425999054
      ],
      "voteCount": 8549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.53188369826343
      }
    },
    {
      "id": "65456c6c914ce39e1844e4ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1415.522928311613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.881661300466,
        1426.1641953227597
      ],
      "voteCount": 2939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.47748990370816
      }
    },
    {
      "id": "35ad624fcf852cc91d7a265c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1380.7583126983498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.5489524674397,
        1387.9676729292598
      ],
      "voteCount": 7923,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.52998362471995
      }
    },
    {
      "id": "3cc5c8ae5fd4722cd5411ef1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1389.91934342499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.9518741079755,
        1393.8868127420046
      ],
      "voteCount": 45452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.097613306865352
      }
    },
    {
      "id": "c0f6d42a8e0833e9960b778a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1374.8492596921246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.1399061687798,
        1385.5586132154694
      ],
      "voteCount": 2901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.855911059135682
      }
    },
    {
      "id": "08f196a06a90f206fd654d32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "o4-mini-2025-04-16",
      "organization": "openai",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1382.7031718774551,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.9742792234638,
        1403.4320645314465
      ],
      "voteCount": 876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.85515990590653
      }
    },
    {
      "id": "ff41e1619af41d61bc735e05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 938.4248795292245,
      "unit": "Arena rating",
      "confidenceInterval": [
        903.2080842123889,
        973.6416748460601
      ],
      "voteCount": 321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 322.8520023973053
      }
    },
    {
      "id": "951ff51f195d9d8e97cc4a47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1048.5538685553195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1023.6104845958023,
        1073.4972525148369
      ],
      "voteCount": 714,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.9625336083854
      }
    },
    {
      "id": "15270ca8040d042b29026c96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1010.9316634137587,
      "unit": "Arena rating",
      "confidenceInterval": [
        990.3635533416523,
        1031.499773485865
      ],
      "voteCount": 1094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.12669188572559
      }
    },
    {
      "id": "785e65535f079fa09eb21621",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1049.3154509949304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1037.4888198415335,
        1061.1420821483273
      ],
      "voteCount": 5212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.41043961867184
      }
    },
    {
      "id": "3189d535e1660686f3cd45ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 820.9463864715982,
      "unit": "Arena rating",
      "confidenceInterval": [
        804.4086911947563,
        837.4840817484401
      ],
      "voteCount": 4325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.19570398525285
      }
    },
    {
      "id": "32d8e3c48cf7e3e946227b87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1032.3442857432533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1011.8075857609797,
        1052.8809857255267
      ],
      "voteCount": 1002,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.79059410708552
      }
    },
    {
      "id": "368fd6ec71d21d3069ba04cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1020.7571469617881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1001.8367403872121,
        1039.677553536364
      ],
      "voteCount": 1153,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.18902054052835
      }
    },
    {
      "id": "c6121d4fed3c3a507a97cabe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 963.4340478792437,
      "unit": "Arena rating",
      "confidenceInterval": [
        932.4684326469578,
        994.3996631115297
      ],
      "voteCount": 454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 249.6107264116702
      }
    },
    {
      "id": "214adec8f440cb4cc1cabca1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 986.1833350144816,
      "unit": "Arena rating",
      "confidenceInterval": [
        964.8430344855402,
        1007.5236355434231
      ],
      "voteCount": 1067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.55090680973396
      }
    },
    {
      "id": "22e91fc322cc6eae4018eb57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1066.6709581784032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1025.5025500519548,
        1107.8393663048514
      ],
      "voteCount": 266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 441.19640656712096
      }
    },
    {
      "id": "3ebdc2da33ed3e9e5381b50c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1046.3760492186873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1025.1221776179545,
        1067.6299208194198
      ],
      "voteCount": 1134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.59258112750122
      }
    },
    {
      "id": "b0f8ff186149c8c68b9e99d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 971.067513084924,
      "unit": "Arena rating",
      "confidenceInterval": [
        946.0509960080823,
        996.0840301617659
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.9136627170284
      }
    },
    {
      "id": "bb4d013ce37a508bad4d90b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 984.1716949896509,
      "unit": "Arena rating",
      "confidenceInterval": [
        935.2319422522986,
        1033.1114477270032
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 623.4869381107685
      }
    },
    {
      "id": "e9616d51fa83264a46d4e1be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1018.4490990088539,
      "unit": "Arena rating",
      "confidenceInterval": [
        999.5023419626713,
        1037.3958560550363
      ],
      "voteCount": 1409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.44877019980737
      }
    },
    {
      "id": "044592e6676fb1a7b83247ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1010.2665947739226,
      "unit": "Arena rating",
      "confidenceInterval": [
        992.4419915075987,
        1028.0911980402466
      ],
      "voteCount": 1408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.70724649976454
      }
    },
    {
      "id": "4145351adb0ae64834f6b17f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 984.0719569552202,
      "unit": "Arena rating",
      "confidenceInterval": [
        967.9155631137859,
        1000.2283507966547
      ],
      "voteCount": 1744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.95050373919486
      }
    },
    {
      "id": "58885d58763bf5472e2ddfc8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 958.9919168754244,
      "unit": "Arena rating",
      "confidenceInterval": [
        937.0205411758395,
        980.9632925750093
      ],
      "voteCount": 687,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.66615253865446
      }
    },
    {
      "id": "bb5bcf866f502c15eeafbb78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 958.5413539620289,
      "unit": "Arena rating",
      "confidenceInterval": [
        933.0439898993501,
        984.0387180247078
      ],
      "voteCount": 683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.23663756138168
      }
    },
    {
      "id": "3be648aa007875a8976a7f17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "oasst-pythia-12b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1021.4194631408964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1010.5379953571601,
        1032.3009309246327
      ],
      "voteCount": 6310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.82327486907548
      }
    },
    {
      "id": "daf5a291da4e6b94d6ec055b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1240.5806543596136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.9151481365839,
        1277.2461605826434
      ],
      "voteCount": 229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 349.9606293705174
      }
    },
    {
      "id": "6a12fdd97cd5beee999b3c7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1279.384252716034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.434693887765,
        1306.3338115443034
      ],
      "voteCount": 427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.06325824081378
      }
    },
    {
      "id": "3f50413e75d8aea08694d4ff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1223.8586548844164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.1625439085274,
        1248.5547658603055
      ],
      "voteCount": 567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.76726155383307
      }
    },
    {
      "id": "7238e63fc09401ed903b973b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1286.8192548775462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.8797465564464,
        1299.758763198646
      ],
      "voteCount": 2025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.585232435618536
      }
    },
    {
      "id": "bf0fcacabddf588df420fe1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1154.1630919117072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.9376173446092,
        1171.3885664788052
      ],
      "voteCount": 2276,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.24070149166033
      }
    },
    {
      "id": "d0f4d476817e0102c2542e97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1295.7639855749742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.134137974143,
        1319.3938331758054
      ],
      "voteCount": 538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.35355543330047
      }
    },
    {
      "id": "157a68327d6c399fc010c623",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1260.7329540971402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.9976242344703,
        1280.4682839598102
      ],
      "voteCount": 789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.38941036936949
      }
    },
    {
      "id": "8f194c67c2bb228e8d7edb6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1236.2300239537615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.405701691946,
        1268.054346215577
      ],
      "voteCount": 336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.6465818579011
      }
    },
    {
      "id": "00fc0e4b8686371805ae19b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1252.5328047461926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.4978286141072,
        1275.5677808782777
      ],
      "voteCount": 606,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.12724544834765
      }
    },
    {
      "id": "fe63e5f9b8eb9937ed29a16a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1273.6476323049405,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.1595701394604,
        1314.1356944704207
      ],
      "voteCount": 202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 426.7345439406769
      }
    },
    {
      "id": "d84d06de410c1a373e49ed48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1286.6291915049544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.6639799630307,
        1310.5944030468781
      ],
      "voteCount": 580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.50866091683906
      }
    },
    {
      "id": "d7d7169ae963be96ac9a7650",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1219.8164889946897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.948052526213,
        1249.6849254631666
      ],
      "voteCount": 336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.23560077372758
      }
    },
    {
      "id": "446b351d9dd0a93136aa4bf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1244.8285084360432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.534818307302,
        1290.1221985647846
      ],
      "voteCount": 204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 534.0466893532248
      }
    },
    {
      "id": "16fb50724aa9f498835cbd3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1268.8857601130007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.5981920681133,
        1290.173328157888
      ],
      "voteCount": 740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.96574541538932
      }
    },
    {
      "id": "d1074808a7668398aca20582",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1232.8849288512106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.5811062677028,
        1252.1887514347184
      ],
      "voteCount": 872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.00418089297969
      }
    },
    {
      "id": "450108f3d506fda587d327e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1227.8367232651374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.547441982242,
        1245.126004548033
      ],
      "voteCount": 1063,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.8139923481122
      }
    },
    {
      "id": "b4db0d18a18b2b551a940e04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1242.6674435594819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.5631307793606,
        1276.7717563396034
      ],
      "voteCount": 261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 302.77668055131846
      }
    },
    {
      "id": "ff654951c9527b9c988fe9cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1227.0203597523905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.8307579996022,
        1255.2099615051789
      ],
      "voteCount": 375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.8624665973166
      }
    },
    {
      "id": "1e10cdc6e1cf3d6f8f9a2cff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1242.901760958167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.5829392439193,
        1272.2205826724144
      ],
      "voteCount": 363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.76741410871222
      }
    },
    {
      "id": "f10ce1ed8505bf44b6b2baba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1251.3724693258714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.5884305270793,
        1262.1565081246636
      ],
      "voteCount": 3334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.27378353956736
      }
    },
    {
      "id": "3957f3f90834876f571382aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-2-0325-32b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1224.9311743981402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.619561655539,
        1258.2427871407415
      ],
      "voteCount": 304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 288.86514090303984
      }
    },
    {
      "id": "0fc3c957ca4473d24b63018f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1315.2813246716344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.4725216768513,
        1354.0901276664176
      ],
      "voteCount": 261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 392.0706325873729
      }
    },
    {
      "id": "7562c7527fb8a31231e1f13c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1364.3196709513704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.9891491322173,
        1382.6501927705235
      ],
      "voteCount": 1055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.46886166066734
      }
    },
    {
      "id": "5e373012f63514b44b69af9c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1262.5621329861751,
      "unit": "Arena rating",
      "confidenceInterval": [
        1241.8297416452017,
        1283.2945243271483
      ],
      "voteCount": 867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.89292161606421
      }
    },
    {
      "id": "b77df7acefcbb4fbf91c70e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1347.8766410957196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.6549804121241,
        1359.0983017793146
      ],
      "voteCount": 2815,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.78068941397485
      }
    },
    {
      "id": "d15b2619d703b1f14f25ace0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1247.0600765087875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1234.9472400185628,
        1259.1729129990122
      ],
      "voteCount": 4327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.194033747942015
      }
    },
    {
      "id": "49e989937218c73a8d947b00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1315.6215743726384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.8024812561755,
        1353.440667489101
      ],
      "voteCount": 275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 372.3282926909636
      }
    },
    {
      "id": "5d87cb4424737512b4a210fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1275.438382545513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.4107277721,
        1330.4660373189256
      ],
      "voteCount": 128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 788.2533514480723
      }
    },
    {
      "id": "d5fd459cf4ec8c5e3064c8a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1356.9101074408154,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.5994076262082,
        1372.2208072554229
      ],
      "voteCount": 1506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.02304873091421
      }
    },
    {
      "id": "4f7ba1f61d76594e08bc41ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1327.6666525775777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.543362073348,
        1338.7899430818072
      ],
      "voteCount": 3024,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.20849094488768
      }
    },
    {
      "id": "ea50850c25fd25e60c3ecde3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1308.17528311563,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.0913842429368,
        1326.259181988323
      ],
      "voteCount": 1114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.13104362230368
      }
    },
    {
      "id": "cb28f19dabb54d87c7304986",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1263.4029590130065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.03719401692,
        1281.768724009093
      ],
      "voteCount": 1053,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.80552900226783
      }
    },
    {
      "id": "cd6fa3a8d6d3f46410b57d02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1298.9837293395317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.6460331389476,
        1328.3214255401158
      ],
      "voteCount": 430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 224.05561494532648
      }
    },
    {
      "id": "253ec12e164b2ae153cf6512",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1323.2750043197252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.5299741087076,
        1343.020034530743
      ],
      "voteCount": 1006,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.48910511125912
      }
    },
    {
      "id": "815f5b1e437bb7fd512a9b15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1334.3210991652923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.4128672737565,
        1374.2293310568282
      ],
      "voteCount": 202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 414.59951727943354
      }
    },
    {
      "id": "b84f3899631dc26c101f43ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1331.468416678891,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.7637479645377,
        1367.173085393244
      ],
      "voteCount": 315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.85917837624146
      }
    },
    {
      "id": "099bc5c67319ffc38407ce5f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1359.0393401544125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.437765694846,
        1372.640914613979
      ],
      "voteCount": 1944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.15952387215852
      }
    },
    {
      "id": "e42c1666d003d80a96edef49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1278.9729540397493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.464985236309,
        1295.4809228431898
      ],
      "voteCount": 1337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.93998575419307
      }
    },
    {
      "id": "3d7e09d4c8374a28bdd03583",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1298.992183185485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.1660300009162,
        1314.8183363700537
      ],
      "voteCount": 1494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.20104374727548
      }
    },
    {
      "id": "212cabd7c2ced10c979f879b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1319.6868053999196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.1319031894675,
        1336.241707610372
      ],
      "voteCount": 1344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.34393468471907
      }
    },
    {
      "id": "f5552d0f4c93b1baa7244260",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1311.3353388021956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.2994799890334,
        1343.3711976153575
      ],
      "voteCount": 314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 267.16315280230106
      }
    },
    {
      "id": "9166f960f96a4b16c8e7de77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1300.5674331373448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.1462371178472,
        1321.9886291568423
      ],
      "voteCount": 816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.4514012316873
      }
    },
    {
      "id": "744ebac28387f9f053e1f3f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1305.3886957481084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.2055293231545,
        1313.571862173062
      ],
      "voteCount": 5947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.43197463884122
      }
    },
    {
      "id": "d344bb2c02c23738c00dd663",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1270.8208681391454,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.4699981726853,
        1298.1717381056055
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.73593830872738
      }
    },
    {
      "id": "b6fbbcf62625441f02ac349e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1326.9949270144084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.3717243175793,
        1353.6181297112375
      ],
      "voteCount": 529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 184.51191459300406
      }
    },
    {
      "id": "31876da0337d814e1531a1a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1383.7008204200056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.7979037681007,
        1395.6037370719105
      ],
      "voteCount": 2513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.88167215510899
      }
    },
    {
      "id": "d61e62f07220a1c1d2e426fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1292.2954985262459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.4241791346185,
        1307.1668179178737
      ],
      "voteCount": 1724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.57087366300005
      }
    },
    {
      "id": "d922b72c10db182f04d00feb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1366.3220431569562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.979263095152,
        1374.6648232187606
      ],
      "voteCount": 5503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.118632115666614
      }
    },
    {
      "id": "b8014731f513b61471067765",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1277.576730845487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.4386317265776,
        1286.7148299643966
      ],
      "voteCount": 8735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.737797905621424
      }
    },
    {
      "id": "c5ad394e71f8d3e2b97a41bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1330.9243425339773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.6165677430643,
        1353.2321173248902
      ],
      "voteCount": 752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.54370705246143
      }
    },
    {
      "id": "49b5b9b7c7fabb048cb9bec4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1356.734753330818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.1905689005034,
        1392.278937761133
      ],
      "voteCount": 327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 328.882621365167
      }
    },
    {
      "id": "e039b7a500b9a7ca66976da4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1291.1548724908193,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.880997757537,
        1331.4287472241012
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 422.2315171763353
      }
    },
    {
      "id": "faf89c994eab9cb25bb28806",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1373.258205793876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.3682383298103,
        1384.1481732579416
      ],
      "voteCount": 3039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.87144673517007
      }
    },
    {
      "id": "5caf270faa1c53759bdc69da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1349.9054825230505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.987620557452,
        1357.8233444886491
      ],
      "voteCount": 6447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.319981817466186
      }
    },
    {
      "id": "308f9d705c70d9471cec5bd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1349.1526101180027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.5032837208855,
        1361.80193651512
      ],
      "voteCount": 2220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.65226435302362
      }
    },
    {
      "id": "7778da6de78c10d65fe82811",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1295.8949945868299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.6785551853131,
        1309.1114339883466
      ],
      "voteCount": 2115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.470816845149734
      }
    },
    {
      "id": "f0bd63fa110450ee60768e1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1355.843939813888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.8729440657369,
        1375.8149355620394
      ],
      "voteCount": 908,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.82531475389031
      }
    },
    {
      "id": "2bfd26631e61ea980dabef35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1342.5651034477241,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.201324519493,
        1356.9288823759553
      ],
      "voteCount": 1882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.70827977841399
      }
    },
    {
      "id": "807a6f152086505dbb062b75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1353.1648962940158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.8776645531811,
        1381.4521280348501
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.297815207373
      }
    },
    {
      "id": "f3f95434c6b5bdb6b6c93ddf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1322.5119960349855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.5881452250696,
        1345.435846844901
      ],
      "voteCount": 805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.79775327132555
      }
    },
    {
      "id": "57e994dc7d3b36aa745c0072",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1378.1294442405126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.7720385991731,
        1387.486849881852
      ],
      "voteCount": 4173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.79369490175863
      }
    },
    {
      "id": "16ee72343546e9346d0ab48c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1301.565330908958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.6719031964612,
        1313.4587586214552
      ],
      "voteCount": 2651,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.82289186346958
      }
    },
    {
      "id": "109416bfd14582cae988f44b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1321.8532498726213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.2210627256718,
        1332.4854370195708
      ],
      "voteCount": 3230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.427206903478417
      }
    },
    {
      "id": "1fdb041ccb55d7318221f5ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1217.8537677938307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.0187422249624,
        1267.688793362699
      ],
      "voteCount": 187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 646.5069363937653
      }
    },
    {
      "id": "1cf53dbf1c2b7e246078c595",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1336.5748065119005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.502898450428,
        1347.6467145733732
      ],
      "voteCount": 2874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.911613229151353
      }
    },
    {
      "id": "d4f993e9b7ca3f6784e36578",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1306.60665000646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.8302759885082,
        1329.383024024412
      ],
      "voteCount": 696,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 135.04328371581863
      }
    },
    {
      "id": "a3bff97c2fe468d48de55d9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1328.7028091143902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.6098566855462,
        1341.7957615432347
      ],
      "voteCount": 2219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.62507898835225
      }
    },
    {
      "id": "4634e58c88f4731bc248604a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1330.3577806712292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.2693330826366,
        1336.4462282598217
      ],
      "voteCount": 12225,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.649769988251526
      }
    },
    {
      "id": "67e1da6c93a204e0b27506e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1298.1548107100657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.0012344594156,
        1314.3083869607158
      ],
      "voteCount": 1394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.92680537921734
      }
    },
    {
      "id": "3b1004f811266fdc2f87c1a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-instruct",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1353.6260785718614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.7016744647644,
        1386.5504826789586
      ],
      "voteCount": 338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 282.188729960552
      }
    },
    {
      "id": "923608060627bc088028d86f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1282.6229899602704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.4737204333014,
        1310.7722594872394
      ],
      "voteCount": 491,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 206.2709537932174
      }
    },
    {
      "id": "b60c87827ca6177afc79d843",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1338.4185588799287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.0045240591112,
        1353.8325937007462
      ],
      "voteCount": 1569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.84954220450198
      }
    },
    {
      "id": "14f670507ad799573073e07a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1246.2381000988894,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.2514499903605,
        1263.2247502074183
      ],
      "voteCount": 1370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.11372511796131
      }
    },
    {
      "id": "a7f799a6e50b1ce18f0f204e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1342.7742018522436,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.091948050917,
        1352.4564556535697
      ],
      "voteCount": 3809,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.403759886292324
      }
    },
    {
      "id": "cf773fb5db4d8de4ed928f62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1208.3720179810948,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.0591955656316,
        1219.6848403965578
      ],
      "voteCount": 6107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.31545565824334
      }
    },
    {
      "id": "9ed8b9620bd2cba8186423f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1323.165828097757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.3201798542075,
        1350.0114763413062
      ],
      "voteCount": 503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 187.60811016221254
      }
    },
    {
      "id": "4d9f3b5a55b076e08b964c24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1283.0400081928533,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.4116087966918,
        1327.6684075890146
      ],
      "voteCount": 210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 518.4733523457155
      }
    },
    {
      "id": "b1d4b218d701d0b684f31dc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1252.2919284396198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.2568360627645,
        1302.3270208164754
      ],
      "voteCount": 159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 651.7082665767306
      }
    },
    {
      "id": "78415d9ffdc1caf943d6411e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1345.6063294730825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.4936193625208,
        1358.7190395836444
      ],
      "voteCount": 2058,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.759861935097206
      }
    },
    {
      "id": "527ccaa26abf9cd9ea30bfe1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1305.046451741473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.5462984424444,
        1314.5466050405014
      ],
      "voteCount": 4382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.494437118223534
      }
    },
    {
      "id": "a273fbc04f60ddf21d25e67a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1279.2051087510852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.4922651640566,
        1294.9179523381138
      ],
      "voteCount": 1534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.27075366795525
      }
    },
    {
      "id": "e8c7adf7cc546eb035d38cf6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1255.012159535305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.2587436066835,
        1269.7655754639268
      ],
      "voteCount": 1659,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.66162042147688
      }
    },
    {
      "id": "181496a26685747262863190",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1297.0099194360519,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.8260137615835,
        1321.1938251105203
      ],
      "voteCount": 636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.2497886794743
      }
    },
    {
      "id": "1bd50af7d8c664f99c76f286",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1304.2751765357523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.8192136023058,
        1320.7311394691988
      ],
      "voteCount": 1412,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.49371832600583
      }
    },
    {
      "id": "6a7e00ab6881cb62a9dfbc7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1310.0300185785488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.0202112634474,
        1341.0398258936502
      ],
      "voteCount": 340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.3236907134029
      }
    },
    {
      "id": "991c20bb558ef05e147633f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1285.5971081838413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.2656175550305,
        1311.9285988126521
      ],
      "voteCount": 595,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.49064980211648
      }
    },
    {
      "id": "cecea538be3f953d0081b5ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1330.7473570508146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.1461937896775,
        1342.3485203119517
      ],
      "voteCount": 2778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.035385069476376
      }
    },
    {
      "id": "45894923274fd0b317610a58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1268.9202186804246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.1093902138766,
        1282.7310471469723
      ],
      "voteCount": 1942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.652746999366386
      }
    },
    {
      "id": "a21502c754d7a64dd3bfe4cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1278.2204861254581,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.9662785965515,
        1291.4746936543647
      ],
      "voteCount": 2159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.73106869529813
      }
    },
    {
      "id": "2fc85e360d5b4a32c6976fd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1301.371614880798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.611071134861,
        1315.132158626735
      ],
      "voteCount": 1970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.291837560198026
      }
    },
    {
      "id": "e0b6006a53f5d752ed3f87c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1296.7904131301395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.4713343107703,
        1323.109491949509
      ],
      "voteCount": 473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.32053504481036
      }
    },
    {
      "id": "0abebf7413837cac3f1f0fe5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1265.9903320244732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.2644483107752,
        1283.7162157381713
      ],
      "voteCount": 1217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.79365394700955
      }
    },
    {
      "id": "a07f813a5e2f1b063f5b8596",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1284.8830334740937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.6668255598033,
        1292.0992413883846
      ],
      "voteCount": 8505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.555698262792335
      }
    },
    {
      "id": "37a59a2b4422e3214a2bf511",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1221.9772863806086,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.2232673887254,
        1242.7313053724915
      ],
      "voteCount": 904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.12649267384714
      }
    },
    {
      "id": "fb3971c1c47485389fcf0019",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-3.1-32b-think",
      "organization": "allenai",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1303.2676028581207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.5148154146807,
        1349.0203903015608
      ],
      "voteCount": 177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 544.9277622261103
      }
    },
    {
      "id": "1a06c92e523ac7b36041d449",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1077.8228172407134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1054.1604072729533,
        1101.4852272084736
      ],
      "voteCount": 722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.75443122443286
      }
    },
    {
      "id": "9a870aa01b67dd64e6b94563",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1105.5728389735214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1083.5967034447808,
        1127.548974502262
      ],
      "voteCount": 772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.72060649873286
      }
    },
    {
      "id": "91950abae3e8ec0798be2ad3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1002.7911509840509,
      "unit": "Arena rating",
      "confidenceInterval": [
        982.383258557084,
        1023.1990434110179
      ],
      "voteCount": 1019,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.4176852468251
      }
    },
    {
      "id": "382fe3360a5d8e6d367fb1fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1109.511344596822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.4673858526087,
        1122.5553033410351
      ],
      "voteCount": 4043,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.291730736291875
      }
    },
    {
      "id": "9507bb9bd8ab83b84fc1d961",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 885.6712550942062,
      "unit": "Arena rating",
      "confidenceInterval": [
        868.0667847393879,
        903.2757254490244
      ],
      "voteCount": 4315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.67700083211463
      }
    },
    {
      "id": "9631097b5109a7bd5efffa57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1084.651022756169,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.735710747556,
        1103.5663347647817
      ],
      "voteCount": 1076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.13884258130027
      }
    },
    {
      "id": "496603bd0eee0e9c18ab3368",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1067.0930761929571,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.1552636453382,
        1084.030888740576
      ],
      "voteCount": 1462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.68243375479906
      }
    },
    {
      "id": "64bdcf2927eade47d350463d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1086.9397050213138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1060.5653652275525,
        1113.3140448150748
      ],
      "voteCount": 548,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.07855167143944
      }
    },
    {
      "id": "ec73f4f64abebbe5916158a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1024.4579834219558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1003.4335938615704,
        1045.4823729823413
      ],
      "voteCount": 876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.06695165014814
      }
    },
    {
      "id": "b1a00ec171a4472c221a2b4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1105.4523599090066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.016902174768,
        1140.8878176432454
      ],
      "voteCount": 301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 326.87364968502345
      }
    },
    {
      "id": "5fa37cdc4219e83ad3c7086d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1075.0751269538155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1055.0491041393752,
        1095.1011497682562
      ],
      "voteCount": 1169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.39825297724384
      }
    },
    {
      "id": "efe92562372410b3d47694f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1058.5598609003375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1037.9495399466655,
        1079.1701818540096
      ],
      "voteCount": 726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.57917047685962
      }
    },
    {
      "id": "e31d832adc7fd19fd94066db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1121.4393000977286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.136845808908,
        1153.7417543865492
      ],
      "voteCount": 339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.6282021455589
      }
    },
    {
      "id": "6b78013e905a8a431d1bbd55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1115.057668215449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1097.557332723661,
        1132.558003707237
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.72537429668398
      }
    },
    {
      "id": "0ca01b6c4078c70cd103fcce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1022.773168931006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1004.5410432480938,
        1041.005294613918
      ],
      "voteCount": 1511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.53233639439088
      }
    },
    {
      "id": "d2ec7a45ab1afb4f9c2bfc53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1027.902196030682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1011.889060221338,
        1043.915331840026
      ],
      "voteCount": 1908,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.75081796195367
      }
    },
    {
      "id": "0265ae8ccfe824e95e93ec37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1053.928501946922,
      "unit": "Arena rating",
      "confidenceInterval": [
        1034.8210266872934,
        1073.0359772065508
      ],
      "voteCount": 848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.04087583355957
      }
    },
    {
      "id": "dc093db7010b6c75d8b4bc5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1039.9927200948541,
      "unit": "Arena rating",
      "confidenceInterval": [
        1012.1717147000422,
        1067.813725489666
      ],
      "voteCount": 537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.48812659621174
      }
    },
    {
      "id": "f397a494a2ce3c00b7d494ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1073.3577038456283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.189602966185,
        1084.5258047250718
      ],
      "voteCount": 6328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.4685186214974
      }
    },
    {
      "id": "b989a12e800a2e0023f61332",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "olmo-7b-instruct",
      "organization": "allenai",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 979.534468399874,
      "unit": "Arena rating",
      "confidenceInterval": [
        951.2539592412527,
        1007.8149775584955
      ],
      "voteCount": 497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.19882122967877
      }
    },
    {
      "id": "6ab7b0c85341843353a165f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1178.0892878705822,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.4456601012002,
        1195.7329156399644
      ],
      "voteCount": 1525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.03629776988195
      }
    },
    {
      "id": "48e050f240c2b27d5140077c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1228.108465814818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.0241292148871,
        1242.1928024147485
      ],
      "voteCount": 2005,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.63885563253368
      }
    },
    {
      "id": "c12b6750eb761c1b2ccbcc38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1146.4447244235719,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.4855041719063,
        1161.4039446752377
      ],
      "voteCount": 1858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.25346072495646
      }
    },
    {
      "id": "80d0956f7e954277ab661bc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1206.5396021046768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.7044687832972,
        1215.3747354260563
      ],
      "voteCount": 8216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.32029612969977
      }
    },
    {
      "id": "f2b93cd6c038c8355c4ef515",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1050.8169156371473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1039.0742242318368,
        1062.5596070424576
      ],
      "voteCount": 8130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.895426158814104
      }
    },
    {
      "id": "d6502a6b3ba70b6fbe3d3af4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1158.54605511815,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.3814876686324,
        1181.7106225676675
      ],
      "voteCount": 611,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.68578349260795
      }
    },
    {
      "id": "8188a6d21befbf8f13d9ffa2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1185.8438554115478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.8292534790812,
        1229.8584573440144
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 504.30976191577224
      }
    },
    {
      "id": "438a5104e26eea85d8af7f4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1132.7089904776408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.2301490807881,
        1167.1878318744934
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 309.46329495067056
      }
    },
    {
      "id": "0e3a7e96e2c52218c79eb8a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1195.8111137642668,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.277021343729,
        1208.3452061848047
      ],
      "voteCount": 2468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.896825955873574
      }
    },
    {
      "id": "2f8b947ae8728e776c23d87a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1185.6405705578684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.3892883735853,
        1196.8918527421515
      ],
      "voteCount": 3435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.95397834500169
      }
    },
    {
      "id": "0b09cade845169b86932d4db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1172.8132445789893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.656584542077,
        1190.9699046159017
      ],
      "voteCount": 1174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.81747692311396
      }
    },
    {
      "id": "d751ef827579253557eb0e0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1139.8897441016709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.2725855084482,
        1154.5069026948936
      ],
      "voteCount": 1868,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.6198400952326
      }
    },
    {
      "id": "de3f62709b3d88f17f1ac776",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1206.792392012115,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.3125627921659,
        1231.272221232064
      ],
      "voteCount": 637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.9985585188684
      }
    },
    {
      "id": "ac787612c18eadca0547b806",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1182.2829669042308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.008147119785,
        1196.5577866886767
      ],
      "voteCount": 2209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.045077245312356
      }
    },
    {
      "id": "50b7de796af506b80212a1e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1154.0142717293925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.9732017206077,
        1169.0553417381773
      ],
      "voteCount": 1467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.89267530096411
      }
    },
    {
      "id": "d86a127e6ace076b3ea70249",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1194.4677206981119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.9363498495036,
        1215.9990915467197
      ],
      "voteCount": 743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.68330086550783
      }
    },
    {
      "id": "2350e8f9bbb83d058edd6849",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1210.1527420937146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.372717974195,
        1221.9327662132341
      ],
      "voteCount": 3463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.12402858750033
      }
    },
    {
      "id": "3e5b6ce7b7da651030d09a2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1161.8546410919923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.458838529731,
        1174.2504436542538
      ],
      "voteCount": 3121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.999366994334196
      }
    },
    {
      "id": "4957b43c09c3830dfa54bdcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1152.7054022659397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.129833248985,
        1163.2809712828944
      ],
      "voteCount": 4414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.11463203246396
      }
    },
    {
      "id": "c7b87cd4c0e940c0a5d56e63",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1167.7260777466322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.1437592712546,
        1186.3083962220098
      ],
      "voteCount": 1097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.88839293556832
      }
    },
    {
      "id": "ff723d3c7c3011ef3566ba68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1157.5896932552425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.992118886245,
        1171.1872676242401
      ],
      "voteCount": 1726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.13120154363896
      }
    },
    {
      "id": "0b906abd85a4b2de378d12f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1151.208533365581,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.090375303693,
        1166.3266914274686
      ],
      "voteCount": 1801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.497892298875556
      }
    },
    {
      "id": "0ddf685e5ebb409fd2b044ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1181.4300215633853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1173.4334103961423,
        1189.4266327306282
      ],
      "voteCount": 12637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.64622559939858
      }
    },
    {
      "id": "ce2f5ac401007a527cd40078",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5-0106",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1148.5038565027783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.7213963907113,
        1169.286316614845
      ],
      "voteCount": 790,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.434017509943
      }
    },
    {
      "id": "0ce56e758844376299372a17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1175.122911460434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.9192617299573,
        1207.3265611909108
      ],
      "voteCount": 322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 269.96906757830214
      }
    },
    {
      "id": "7f59fd89fbf76c239c7f2f32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1200.8623587951588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.2475202940323,
        1220.477197296285
      ],
      "voteCount": 971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.1551513067509
      }
    },
    {
      "id": "e44301e9fde0c72aa6521fb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1184.0026946444177,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.3322569853908,
        1201.6731323034448
      ],
      "voteCount": 1454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.28275783655043
      }
    },
    {
      "id": "53fa15d73c56675196b9c586",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1200.4115021013126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.7601764493545,
        1211.0628277532708
      ],
      "voteCount": 6196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.53324334310081
      }
    },
    {
      "id": "8027f046c4a1ef09624c7e27",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1048.4237686443912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1034.3432902273016,
        1062.5042470614808
      ],
      "voteCount": 5304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.610568200313025
      }
    },
    {
      "id": "60cf4c185c49e20221f77851",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1158.2386884534944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.668882777143,
        1199.808494129846
      ],
      "voteCount": 194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 449.8417982930193
      }
    },
    {
      "id": "1e27815a329eb7a490443503",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1178.0645330751831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.122589506599,
        1195.006476643767
      ],
      "voteCount": 1389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.7188673050049
      }
    },
    {
      "id": "d403101478c4f29baff942b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1174.167601781197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.4268942240205,
        1189.9083093383729
      ],
      "voteCount": 1663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.49890158025214
      }
    },
    {
      "id": "54e2160653c157cd223e17cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1147.6505133190367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1123.7414189901763,
        1171.5596076478973
      ],
      "voteCount": 615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.8092983183563
      }
    },
    {
      "id": "e27c1e1677bd809570dc3ef9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1170.830960747583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.5365962644341,
        1188.125325230732
      ],
      "voteCount": 1340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.85975506616428
      }
    },
    {
      "id": "26dc023b79639331c93aca52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1231.3082477054909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.8711720561423,
        1259.74532335484
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.51046210113213
      }
    },
    {
      "id": "c592eb76cea9917c43c0f33d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1187.8105705051403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.1652094385909,
        1205.4559315716897
      ],
      "voteCount": 1439,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.05222044593997
      }
    },
    {
      "id": "c3f6eca4ea49f553fb4d630c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1131.2424312922776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1111.2456939068998,
        1151.2391686776552
      ],
      "voteCount": 826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.09313875906855
      }
    },
    {
      "id": "c3837607eba1575c370703d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1204.7117246519128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.5197637971378,
        1234.903685506688
      ],
      "voteCount": 426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.29383622328066
      }
    },
    {
      "id": "08364ab4107eca0f8df1cefa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1199.3177174634588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.78106972712,
        1214.8543651997975
      ],
      "voteCount": 1879,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.83743602370964
      }
    },
    {
      "id": "0e9865ed2a820647d7ff5316",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1174.855437331335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.4195347316966,
        1190.2913399309737
      ],
      "voteCount": 1995,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.0251576775924
      }
    },
    {
      "id": "c7cf04c188b61c85b492cf30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1151.3747012260742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.1907994780167,
        1165.5586029741314
      ],
      "voteCount": 2391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.37152815871975
      }
    },
    {
      "id": "cb63ca2e277acc82c6646929",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1180.590746186006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.3021020211918,
        1208.8793903508204
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.3186169724159
      }
    },
    {
      "id": "95150750f32c2d2a95bec1e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1124.2013722839642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.9048821651443,
        1142.4978624027844
      ],
      "voteCount": 945,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.14438089631558
      }
    },
    {
      "id": "03bff8d70a492ffbb51037e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1155.043940980558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.249570049701,
        1173.8383119114148
      ],
      "voteCount": 1167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.95162441512478
      }
    },
    {
      "id": "230f0799853a88a6644740d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1181.4489943268743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.7822123974715,
        1191.115776256277
      ],
      "voteCount": 7968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.32582964763926
      }
    },
    {
      "id": "c54c3cea61e6e97d6eca4dc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openchat-3.5",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1184.5253047820343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.1602579930814,
        1225.8903515709874
      ],
      "voteCount": 187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 445.4211734965567
      }
    },
    {
      "id": "ec57443761f7b9ba84665253",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1117.3195843217163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.8637774027811,
        1159.7753912406515
      ],
      "voteCount": 205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 469.22162263663375
      }
    },
    {
      "id": "c0dc80dc04ace412f10488b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1184.979767094323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.8237046458873,
        1208.1358295427585
      ],
      "voteCount": 589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.5832294823253
      }
    },
    {
      "id": "7f826468cef0d4cf7c55331c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1156.9677940489214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.0698589766032,
        1178.8657291212398
      ],
      "voteCount": 811,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.82746342308124
      }
    },
    {
      "id": "0ef3a31df8516274aad4bec2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1206.3212216138838,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.7879106075566,
        1217.854532620211
      ],
      "voteCount": 3857,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.62675743186469
      }
    },
    {
      "id": "c448b6ca524140902c188586",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1039.0216494911665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1023.6886259113276,
        1054.3546730710054
      ],
      "voteCount": 3283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.20112776776195
      }
    },
    {
      "id": "b101e50529422f1c70ebbf0d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1194.5808927197445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.9106004586224,
        1213.2511849808668
      ],
      "voteCount": 917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.74152018444282
      }
    },
    {
      "id": "7a84399dcddc7169961bdfef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1179.0323980452076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.124239409513,
        1195.940556680902
      ],
      "voteCount": 1139,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.42116180179531
      }
    },
    {
      "id": "d98c9b9a705987960f94e747",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1132.4441638340843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.7507254487207,
        1162.1376022194481
      ],
      "voteCount": 381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 229.52225295130765
      }
    },
    {
      "id": "2e1be7c7969cec3c16c89daa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1149.627750427308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.5353158495277,
        1170.7201850050883
      ],
      "voteCount": 799,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.81298074088289
      }
    },
    {
      "id": "23dfc45dc31968846b72131c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1212.8283304832698,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.6138425113004,
        1249.0428184552388
      ],
      "voteCount": 275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 341.40393019621877
      }
    },
    {
      "id": "89706596a86ba134d1200922",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1182.9257535266124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.5353576866185,
        1203.3161493666066
      ],
      "voteCount": 884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.231862403908
      }
    },
    {
      "id": "0dc687853c2a696e60353f87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1158.381957171215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.3299751801744,
        1180.4339391622555
      ],
      "voteCount": 568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.58990566643826
      }
    },
    {
      "id": "db5d9fe172272283414b4af3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1191.312318814183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.2757066208767,
        1226.3489310074892
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 319.5567755070525
      }
    },
    {
      "id": "69a4dd8b11006ad57c2da73f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1186.9689553460212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.5176713934407,
        1204.420239298602
      ],
      "voteCount": 1192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.27907750904116
      }
    },
    {
      "id": "2c01b7b023017dc0db416c83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1157.0671652378428,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.674310435612,
        1175.4600200400737
      ],
      "voteCount": 1136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.06474924409632
      }
    },
    {
      "id": "9df8a8add5da6473fc7934cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1150.5206190645208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.128975537574,
        1165.9122625914674
      ],
      "voteCount": 1577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.669980473145806
      }
    },
    {
      "id": "90c4863c78add6654cb43ee1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1136.957177939511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.7245606384022,
        1170.1897952406198
      ],
      "voteCount": 270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 287.49673085976076
      }
    },
    {
      "id": "dde45acc9b65db2ad87c02e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1151.0503823730876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.0270987744807,
        1171.0736659716945
      ],
      "voteCount": 697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.36969515601696
      }
    },
    {
      "id": "172c993fbea4a0df0adb5b65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1134.2365428312828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1111.7915705416835,
        1156.681515120882
      ],
      "voteCount": 722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.14204904839892
      }
    },
    {
      "id": "e6791e911706c8e4014023e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "openhermes-2.5-mistral-7b",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1174.4240805225568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.0117889496628,
        1184.8363720954503
      ],
      "voteCount": 5006,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.22256357790767
      }
    },
    {
      "id": "189caed2ad97cc85a2fcc48b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1071.1850441730858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1036.310710256107,
        1106.0593780900645
      ],
      "voteCount": 355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 316.603463142986
      }
    },
    {
      "id": "3098af03a5cb92f75a28cef5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1151.5422132445678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1130.6649967544597,
        1172.4194297346762
      ],
      "voteCount": 917,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.46162713676813
      }
    },
    {
      "id": "bb90d68e4f4f1fe3763207d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1086.4985130476286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.8743257834922,
        1104.1227003117651
      ],
      "voteCount": 1576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.85781762076246
      }
    },
    {
      "id": "ae2b7f41d5286bdaa15b2f88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1164.894814894181,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.7561107827069,
        1175.0335190056553
      ],
      "voteCount": 6912,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.758928276484745
      }
    },
    {
      "id": "d4f7d9191696d7b10f10713a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 985.1297838686278,
      "unit": "Arena rating",
      "confidenceInterval": [
        971.9542019956996,
        998.3053657415558
      ],
      "voteCount": 6230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.190112869376904
      }
    },
    {
      "id": "3301eb1fce64c4a8f789ba80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1167.3866964345198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.711941316805,
        1184.0614515522343
      ],
      "voteCount": 1366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.38069473448421
      }
    },
    {
      "id": "a5d6a2c22af5d37423bfa500",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1144.9428031905427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.4657973438566,
        1160.4198090372288
      ],
      "voteCount": 1605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.3559228822011
      }
    },
    {
      "id": "43b564427064a0df41cbebd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1094.4590637914027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1069.9536966961211,
        1118.9644308866846
      ],
      "voteCount": 755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.324210281657
      }
    },
    {
      "id": "73c20774f6651733df10934e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1095.990238293835,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.1808475576277,
        1113.7996290300428
      ],
      "voteCount": 1480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.56613260730089
      }
    },
    {
      "id": "03091cdc0a0ce598099981e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1158.2452258442338,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.7950913755526,
        1190.695360312915
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 274.11753612009784
      }
    },
    {
      "id": "de43e77bd6e306cff958dd25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1161.2046460510087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.7725625447133,
        1179.6367295573043
      ],
      "voteCount": 1368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.44080289312197
      }
    },
    {
      "id": "0f92b2814c37ee5bc64c11f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1122.3387205104186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.411782792713,
        1143.2656582281243
      ],
      "voteCount": 801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.00271164734134
      }
    },
    {
      "id": "fb5815a2d34709bef1a4a283",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1149.2862524947575,
      "unit": "Arena rating",
      "confidenceInterval": [
        1111.579146710542,
        1186.993358278973
      ],
      "voteCount": 303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 370.1265308279659
      }
    },
    {
      "id": "687115b49b1d511dc3547778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1141.8444696074225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.6745714352,
        1157.0143677796452
      ],
      "voteCount": 2077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.90583819769248
      }
    },
    {
      "id": "ec2bc69ec53ce1d54257cb58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1094.3621310126896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1079.2479561744115,
        1109.4763058509675
      ],
      "voteCount": 2155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.46654427516677
      }
    },
    {
      "id": "656ba4a921c56a5bdf354497",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1113.137988018104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.6316212192903,
        1126.6443548169175
      ],
      "voteCount": 2536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.48767398504399
      }
    },
    {
      "id": "cd401d0f271639da610f3e09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1137.4465985080003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.0655853392582,
        1174.8276116767427
      ],
      "voteCount": 251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 363.75247288715974
      }
    },
    {
      "id": "3c2cec64781f05ed4f6463a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1114.1580035567497,
      "unit": "Arena rating",
      "confidenceInterval": [
        1094.7040130283326,
        1133.611994085167
      ],
      "voteCount": 901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.51927747890382
      }
    },
    {
      "id": "b25afd46c7164d7f29ab48f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1089.7679186505031,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.0133975611598,
        1109.5224397398465
      ],
      "voteCount": 1163,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.58669445239427
      }
    },
    {
      "id": "94b9a501bfae723f0c97183b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "palm-2",
      "organization": "google",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1136.8145568372274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.438653067577,
        1146.1904606068779
      ],
      "voteCount": 8554,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.88390312143468
      }
    },
    {
      "id": "a412a276de60bc724aa4ed36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1200.0565972497275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.1783832622743,
        1212.9348112371806
      ],
      "voteCount": 2819,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.17328474620123
      }
    },
    {
      "id": "f21797b9cd8e579b42857a1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1229.6797165776134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.4150694702669,
        1239.94436368496
      ],
      "voteCount": 3973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.427856227629547
      }
    },
    {
      "id": "52ce290549559a2becbb37ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1149.4966438976421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.554506195735,
        1160.438781599549
      ],
      "voteCount": 3735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.167945063604208
      }
    },
    {
      "id": "59c80a1465cb93709a5a7203",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1229.3012836652665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.6916519486435,
        1235.9109153818895
      ],
      "voteCount": 13283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.372562734251732
      }
    },
    {
      "id": "2997fc268aa49bf20eb05424",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1063.940765588974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1055.2874764139144,
        1072.5940547640337
      ],
      "voteCount": 15851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.49244207534504
      }
    },
    {
      "id": "23199bf6a45e7bf484c722c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1200.9047145794773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.9782194561974,
        1218.8312097027572
      ],
      "voteCount": 1091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.65551796984012
      }
    },
    {
      "id": "34667f1f59557021c3467a39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1188.065305334147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.9761623567817,
        1222.1544483115122
      ],
      "voteCount": 350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 302.5073866915156
      }
    },
    {
      "id": "155d3defd7b034139b160a7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1168.4925360715079,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.370522478203,
        1189.614549664813
      ],
      "voteCount": 851,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.1380296028135
      }
    },
    {
      "id": "0baa38119cde1b4eb2259c09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1227.9224482285917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.048832208466,
        1237.7960642487178
      ],
      "voteCount": 4087,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.377935274930394
      }
    },
    {
      "id": "5f25e92e7673a6e76f1f3f01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1211.3279722307466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1203.1662629255866,
        1219.4896815359068
      ],
      "voteCount": 6823,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.34067756319187
      }
    },
    {
      "id": "6eaa2f5a187ca9ac0c90398b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1179.867622565106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.5700001253836,
        1192.1652450048286
      ],
      "voteCount": 2847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.36825167961646
      }
    },
    {
      "id": "56fe1baad0112c662517c236",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1135.1768577191676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.6026096442934,
        1145.751105794042
      ],
      "voteCount": 3888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.107359356979014
      }
    },
    {
      "id": "59d6ee49ab650d3cef5e33cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1213.1264290627423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.5758294946343,
        1229.6770286308504
      ],
      "voteCount": 1474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.30685472618545
      }
    },
    {
      "id": "27e4bf474364487ae2c64d5d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1223.6732998655634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.9962057294742,
        1234.3503940016526
      ],
      "voteCount": 4186,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.676314262900416
      }
    },
    {
      "id": "ccb8d1886282e80494a273be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1224.1641936507717,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.045742983534,
        1235.2826443180095
      ],
      "voteCount": 2729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.18046867347742
      }
    },
    {
      "id": "92cb8ff837e103930880ec78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1217.993673885178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.6525638564312,
        1235.3347839139249
      ],
      "voteCount": 1320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.28122363544348
      }
    },
    {
      "id": "3774e4868fbbd9653b29da86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1220.6109108099567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.0812388643958,
        1229.1405827555177
      ],
      "voteCount": 6654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.939498480877884
      }
    },
    {
      "id": "e78ed6715e28c34f1505c874",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1172.0272055731937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.3267274618254,
        1180.727683684562
      ],
      "voteCount": 6655,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.705617813370363
      }
    },
    {
      "id": "3330529fbfe7b1317eb04978",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1175.39781281055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.9835141820317,
        1182.8121114390683
      ],
      "voteCount": 9385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.310142765741567
      }
    },
    {
      "id": "0c0f90960683f9e8d2e4eb68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1116.3097603125752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.3280686216376,
        1140.2914520035126
      ],
      "voteCount": 683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.71435675972162
      }
    },
    {
      "id": "01a1837013270e46a1703a53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1028.5935658521396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1003.1600693035375,
        1054.0270624007417
      ],
      "voteCount": 732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.38986876628115
      }
    },
    {
      "id": "c222924f14ba6c8793728242",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1188.5826097783063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.4710698723525,
        1201.69414968426
      ],
      "voteCount": 2150,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.75187337146973
      }
    },
    {
      "id": "93aac49a25877a77c43b7384",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1215.300289085275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.7380725949756,
        1225.8625055755742
      ],
      "voteCount": 3238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.041159204146567
      }
    },
    {
      "id": "211added462b2f1b1ddabafd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1138.343894822996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.3208560954695,
        1149.3669335505226
      ],
      "voteCount": 3824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.630531123745467
      }
    },
    {
      "id": "3eace6f2844c707afce6938b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1197.0442047089798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.8867320947277,
        1202.201677323232
      ],
      "voteCount": 25055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.924328753302724
      }
    },
    {
      "id": "b06df08fcfc2a3d243f69618",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1193.0298956893562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.496118134338,
        1204.563673244374
      ],
      "voteCount": 2964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.629558950888566
      }
    },
    {
      "id": "0910049d10d6f751854928b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1161.1314316143096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1130.2658736463304,
        1191.9969895822887
      ],
      "voteCount": 419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.00022937706123
      }
    },
    {
      "id": "2137f2bda4e1d3545babff12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1123.8891537151499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.7648749410664,
        1140.0134324892329
      ],
      "voteCount": 2016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.68063335307909
      }
    },
    {
      "id": "333414abbbc7e6adfe59a6c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1152.9910270927132,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.9641875167588,
        1166.0178666686675
      ],
      "voteCount": 3886,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.17554821191282
      }
    },
    {
      "id": "7d77ac0d6dd59890e2699e2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1084.8888505122745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.3964872254055,
        1099.3812137991436
      ],
      "voteCount": 2949,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.674175473951784
      }
    },
    {
      "id": "477bb1d00e76f122761fa580",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1162.168433268447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.0243714717442,
        1171.3124950651495
      ],
      "voteCount": 12596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.766175311182984
      }
    },
    {
      "id": "ec27c5a4c6605eaade5db8eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 954.8067590442083,
      "unit": "Arena rating",
      "confidenceInterval": [
        941.7883234156889,
        967.8251946727275
      ],
      "voteCount": 13845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.118569044891835
      }
    },
    {
      "id": "cbf4e9425da963553972b973",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1093.006314182735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.5973033110727,
        1113.4153250543973
      ],
      "voteCount": 1095,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.42956913029383
      }
    },
    {
      "id": "1e753385cbd2c3e58012339e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1133.9468102765877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.0774499141812,
        1169.8161706389938
      ],
      "voteCount": 372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 334.9277118049851
      }
    },
    {
      "id": "e1ed00da31311e35d893a60f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1091.4420473391012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1066.896286259405,
        1115.9878084187976
      ],
      "voteCount": 727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.8399962368105
      }
    },
    {
      "id": "f649bb251553ba5d45701f2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1151.8261018153275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.3023564284738,
        1164.3498472021813
      ],
      "voteCount": 4149,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.829332249981036
      }
    },
    {
      "id": "2c1d79c9faa7f2aa170791f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1128.773806297429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.8527214099336,
        1139.6948911849245
      ],
      "voteCount": 6167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.04812538334797
      }
    },
    {
      "id": "a6cd58a8c8c5e35456cbf873",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1099.5962660818327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1083.4097101969369,
        1115.7828219667288
      ],
      "voteCount": 2085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.2044513931599
      }
    },
    {
      "id": "eb1dcdb2be56769cef8f1f91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1085.121689345963,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.8376191144012,
        1099.4057595775248
      ],
      "voteCount": 2922,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.11384864548039
      }
    },
    {
      "id": "2d9016dd611d3ae85f898bc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1118.136591049541,
      "unit": "Arena rating",
      "confidenceInterval": [
        1095.546938230351,
        1140.7262438687312
      ],
      "voteCount": 1033,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.83818421860184
      }
    },
    {
      "id": "df17d9e63fc58e306322f8cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1138.1997643026239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.3474503401346,
        1152.0520782651129
      ],
      "voteCount": 3426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.95149266775047
      }
    },
    {
      "id": "4282e3cd64f55c2cc7e2fc81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1141.5680847277229,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.8610663644336,
        1155.275103091012
      ],
      "voteCount": 2569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.90911530781373
      }
    },
    {
      "id": "5cf211b666a49dc5bcd346ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1129.62362561207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.5411688240395,
        1151.7060824001005
      ],
      "voteCount": 1114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.94002996161859
      }
    },
    {
      "id": "7b07f9e16b002379ca3a9a99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1140.474175127928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.0532805766381,
        1151.895069679218
      ],
      "voteCount": 6056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.95502553587581
      }
    },
    {
      "id": "52916411b04b176683d6e07d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1097.4771346350499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.4591185164506,
        1109.4951507536493
      ],
      "voteCount": 4627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.59840158870079
      }
    },
    {
      "id": "04b45702bf749b5004a61084",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1097.5521910380714,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.2309149938344,
        1107.8734670823085
      ],
      "voteCount": 7368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.731323997921194
      }
    },
    {
      "id": "7e704293fe327a249f08012e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 981.4021557596627,
      "unit": "Arena rating",
      "confidenceInterval": [
        949.3778760094663,
        1013.4264355098594
      ],
      "voteCount": 385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 266.97006043488966
      }
    },
    {
      "id": "e8051d322004cd4c8ef80ba9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 939.234732382039,
      "unit": "Arena rating",
      "confidenceInterval": [
        898.0514050897153,
        980.4180596743627
      ],
      "voteCount": 260,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 441.5162379796603
      }
    },
    {
      "id": "f1e66f8fa1fc1556997bc630",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1070.2131163570916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.998616510347,
        1086.427616203836
      ],
      "voteCount": 2074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.4401467129541
      }
    },
    {
      "id": "5902394cc8733e784f7f2835",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1138.6759387502061,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.4980317931752,
        1151.8538457072368
      ],
      "voteCount": 2813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.20606360080231
      }
    },
    {
      "id": "b929460e30b5cfd1aac48893",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1056.81394348538,
      "unit": "Arena rating",
      "confidenceInterval": [
        1041.0859548527778,
        1072.541932117982
      ],
      "voteCount": 2507,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.39470991974838
      }
    },
    {
      "id": "48ee838d45749343bcc68d24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1128.440422049156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.0173559913565,
        1135.8634881069556
      ],
      "voteCount": 20685,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.34400634509429
      }
    },
    {
      "id": "457d91ac3fd314a433579ad8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1062.5758609674062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1046.4346679205983,
        1078.7170540142145
      ],
      "voteCount": 1800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.82270099338173
      }
    },
    {
      "id": "177cf933f9501e7ec15fc626",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-128k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1141.6258686797505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1106.632894551307,
        1176.6188428081937
      ],
      "voteCount": 366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 318.7612559472
      }
    },
    {
      "id": "d4dc0d72f04bbdfc98b75855",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1123.421767371979,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.488919200395,
        1141.3546155435629
      ],
      "voteCount": 1172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.71482255977227
      }
    },
    {
      "id": "e31cf078164795929b0d815a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1195.4973184463495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.600839978105,
        1209.393796914594
      ],
      "voteCount": 1841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.27051514338388
      }
    },
    {
      "id": "362a8d14935f44ed8ee9e6ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1095.6026700478653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.869155388917,
        1110.3361847068136
      ],
      "voteCount": 1955,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.50885883145277
      }
    },
    {
      "id": "409c0b40d789678033163289",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1191.4879823172037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.2158342226585,
        1199.7601304117484
      ],
      "voteCount": 6694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.81313748033863
      }
    },
    {
      "id": "078be802308815964a3c8b20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 962.4595829331815,
      "unit": "Arena rating",
      "confidenceInterval": [
        950.0740236948402,
        974.845142171523
      ],
      "voteCount": 8201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.93328701588061
      }
    },
    {
      "id": "2f61c6f49dc0d0c6969d37c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1144.7895373666383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.7262416542198,
        1170.852833079057
      ],
      "voteCount": 486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.83266048137259
      }
    },
    {
      "id": "9f08d6142da12f98f2aa3cff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1105.2521540088962,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.9672511653798,
        1137.5370568524127
      ],
      "voteCount": 397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.3331055380034
      }
    },
    {
      "id": "17f9e33191d3bd4003183887",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1200.6410492573286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.6226572559694,
        1213.6594412586876
      ],
      "voteCount": 2028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.11827334658958
      }
    },
    {
      "id": "10b22af1548e13670e5a4712",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1174.0380424302357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.1442005792223,
        1184.9318842812493
      ],
      "voteCount": 3155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.893417270433613
      }
    },
    {
      "id": "5af356b6d99d570434cb264e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1105.0764153325208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.0801077742358,
        1122.072722890806
      ],
      "voteCount": 1424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.19915847064185
      }
    },
    {
      "id": "9da0585848d32ddae6883042",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1090.86170374404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.9156183248915,
        1104.8077891631883
      ],
      "voteCount": 1973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.63006206663962
      }
    },
    {
      "id": "824f6bbe75b0f0b97f99ee80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1154.4744390595702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.578075242251,
        1179.3708028768895
      ],
      "voteCount": 706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.35248619229515
      }
    },
    {
      "id": "7729b31897612232a95522d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1159.7469089582353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.1008390769728,
        1174.3929788394978
      ],
      "voteCount": 1956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.84007872510961
      }
    },
    {
      "id": "793c771cdd85e0466a128390",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1196.592160903402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.1522034661898,
        1211.032118340614
      ],
      "voteCount": 1357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.27947572032496
      }
    },
    {
      "id": "db1b29962bbf62fb4358b441",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1147.368124363512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.6217665313238,
        1173.1144821957
      ],
      "voteCount": 653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.55812767069906
      }
    },
    {
      "id": "6d55318a327be0a0a8a9ab18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1179.2858754837744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.855556415691,
        1190.7161945518574
      ],
      "voteCount": 3104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.01108799978744
      }
    },
    {
      "id": "c70bc4d525be1b2a25cc2819",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1102.4425041343343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.0954182889172,
        1113.7895899797518
      ],
      "voteCount": 3382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.51756798475944
      }
    },
    {
      "id": "d8a541fb5e6051532bb5d199",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1122.2531830933797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.537015174918,
        1131.9693510118414
      ],
      "voteCount": 4431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.575017832076444
      }
    },
    {
      "id": "191fc898872090360d865c72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1023.664400439041,
      "unit": "Arena rating",
      "confidenceInterval": [
        990.6877246206302,
        1056.6410762574515
      ],
      "voteCount": 354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 283.0854627867787
      }
    },
    {
      "id": "9ea746391a095a5143d36efa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 956.9323312231702,
      "unit": "Arena rating",
      "confidenceInterval": [
        916.0456240288507,
        997.8190384174898
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 435.1791606325098
      }
    },
    {
      "id": "b2f4631fe5ad92e7ef01481a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1104.5902127587344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.548506022084,
        1123.6319194953849
      ],
      "voteCount": 1035,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.38773454796056
      }
    },
    {
      "id": "08326a856b42cce0325ba37a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1193.2234417450131,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.6616212502756,
        1206.7852622397504
      ],
      "voteCount": 1568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.87841903723605
      }
    },
    {
      "id": "036e1817a7a1b3647fa5a98d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1097.3699148726816,
      "unit": "Arena rating",
      "confidenceInterval": [
        1082.5689146164268,
        1112.1709151289365
      ],
      "voteCount": 1839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.02771233821833
      }
    },
    {
      "id": "4d3392567b9d5df20193922e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1142.198547115453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.7617531503868,
        1148.635341080519
      ],
      "voteCount": 12297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.785568317305584
      }
    },
    {
      "id": "da8595660f85935784cc7c75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct-june-2024",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1073.4662699519504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1056.7116744580355,
        1090.2208654458652
      ],
      "voteCount": 1415,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.07548597227677
      }
    },
    {
      "id": "2c554e7c399b69871059479e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1110.9295624102879,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.3212768699173,
        1125.5378479506587
      ],
      "voteCount": 2296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.55233477433098
      }
    },
    {
      "id": "d36a283b469d428afcfe5160",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1186.0613211197642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.3234791078255,
        1197.7991631317027
      ],
      "voteCount": 3449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.86578472610949
      }
    },
    {
      "id": "591a302ae186a2fedc736d15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1073.3001412560684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1060.3812844936044,
        1086.2189980185321
      ],
      "voteCount": 2812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.4462186995146
      }
    },
    {
      "id": "eb4adbeda1546692a6d9f9b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1171.4811279561827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.3094199200646,
        1179.6528359923004
      ],
      "voteCount": 10322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.38319095543209
      }
    },
    {
      "id": "5811741b781ea8259a3ce628",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 949.353760214312,
      "unit": "Arena rating",
      "confidenceInterval": [
        937.8402686158347,
        960.8672518127894
      ],
      "voteCount": 12861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.507851047133
      }
    },
    {
      "id": "bc79d32179d9c789ffc8e45c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1136.0550015894046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.4723849958832,
        1155.6376181829257
      ],
      "voteCount": 936,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.82636559398581
      }
    },
    {
      "id": "6bc6913e79b67aa9d30e8740",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1150.094963796053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1113.2931110387374,
        1186.8968165533684
      ],
      "voteCount": 307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 352.5682376380125
      }
    },
    {
      "id": "ab9629bf067121e23f0730b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1108.660420242603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.7207848894982,
        1132.600055595708
      ],
      "voteCount": 699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.18971348912567
      }
    },
    {
      "id": "dd811b8e19cdff27c987d5ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1176.8106245261501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.181942722477,
        1188.4393063298232
      ],
      "voteCount": 3447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.20179359013464
      }
    },
    {
      "id": "ac520c6a3464aedf675179b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1151.8001990665985,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.1841170861537,
        1161.416281047043
      ],
      "voteCount": 5872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.071332525158954
      }
    },
    {
      "id": "932be8f3d9d72f8145f31220",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1112.7406607164635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.0178706692648,
        1126.4634507636622
      ],
      "voteCount": 2483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.02173249002023
      }
    },
    {
      "id": "53cf6ab947486179aefb0778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1068.2557523326652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1055.8746509233329,
        1080.6368537419976
      ],
      "voteCount": 2995,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.90454649217711
      }
    },
    {
      "id": "33ae737b1d0f597c55e6fd66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1155.1838339471785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.7996412071482,
        1174.568026687209
      ],
      "voteCount": 1126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.81360304019968
      }
    },
    {
      "id": "c6f85f61a1fdaf75d2c1f20e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1145.896393342956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.1949562886646,
        1158.5978303972472
      ],
      "voteCount": 3517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.996155828887424
      }
    },
    {
      "id": "cb7ecd269c93cf5657fe8d64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1154.134012643212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.1998200307103,
        1167.0682052557133
      ],
      "voteCount": 2198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.54942909606893
      }
    },
    {
      "id": "fbd3cbc34f4ff0dcc5aa8fdd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1130.4226460186214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1109.7838029953934,
        1151.0614890418494
      ],
      "voteCount": 1078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.8854373350999
      }
    },
    {
      "id": "a7cac387b2cfaee704f5f8bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1162.2960498935934,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.352528006806,
        1172.2395717803806
      ],
      "voteCount": 5715,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.738562386866846
      }
    },
    {
      "id": "2fd2b968f3a6cb118ee5fcfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1092.1412872792928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1081.6248306652817,
        1102.6577438933039
      ],
      "voteCount": 5207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.79006775201974
      }
    },
    {
      "id": "703ac7e94a50e5068a13aea8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1111.5279986370806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.658909637127,
        1120.3970876370345
      ],
      "voteCount": 7636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.476788470398514
      }
    },
    {
      "id": "71b9c8360d5bb2a82f3398d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1000.6042759205134,
      "unit": "Arena rating",
      "confidenceInterval": [
        966.3774268465033,
        1034.8311249945234
      ],
      "voteCount": 384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.95633357417597
      }
    },
    {
      "id": "72bcde1868b2ad1e7a454287",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 969.6597357611164,
      "unit": "Arena rating",
      "confidenceInterval": [
        944.8288455605823,
        994.4906259616505
      ],
      "voteCount": 860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 160.5049375590001
      }
    },
    {
      "id": "f83372accc372fae25116157",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1106.1375552309914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1090.7566523056694,
        1121.5184581563133
      ],
      "voteCount": 1706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.58394137241559
      }
    },
    {
      "id": "a71a7b40343a93a95f8a7c10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1149.7957286735796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.587370730426,
        1162.0040866167328
      ],
      "voteCount": 2564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.79880290926204
      }
    },
    {
      "id": "f5c5ee1242f11e50f8f3040a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1063.434170550834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1049.9040232552427,
        1076.9643178464257
      ],
      "voteCount": 2939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.65504314512546
      }
    },
    {
      "id": "e225ca4bec708ad6e183bb83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1127.4274299434446,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.0307711054372,
        1133.8240887814522
      ],
      "voteCount": 20118,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.651485854653926
      }
    },
    {
      "id": "dce18a68ed7b699869dcfd16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1067.089474668988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.9054005797052,
        1080.273548758271
      ],
      "voteCount": 2751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.248385497542706
      }
    },
    {
      "id": "9a5761edcc203e4494e88872",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1140.0666909568608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.153808952448,
        1172.979572961274
      ],
      "voteCount": 410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 281.99125707162517
      }
    },
    {
      "id": "fe1eb0eeff4cc27604354e41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1149.2350571535744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.0595419210538,
        1163.4105723860948
      ],
      "voteCount": 2376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.30961504127579
      }
    },
    {
      "id": "d91e33675b56168022cb7d10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1203.444519300495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.7854623167,
        1215.1035762842898
      ],
      "voteCount": 3219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.38593437969363
      }
    },
    {
      "id": "301f65bf12cfd39f064ba982",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1132.924933693107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.7836265391547,
        1146.0662408470594
      ],
      "voteCount": 2400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.95530520442098
      }
    },
    {
      "id": "fc0c4bda379f7fde0eabbcf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1210.0700171627782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.1672663245001,
        1217.9727680010565
      ],
      "voteCount": 9107,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.25774835212775
      }
    },
    {
      "id": "35e21ac36ccb61aecbac411c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1021.0378833922368,
      "unit": "Arena rating",
      "confidenceInterval": [
        1010.5385071726523,
        1031.5372596118214
      ],
      "voteCount": 11205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.696624419485236
      }
    },
    {
      "id": "d0a305fa999ce4c58bac4460",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1161.969969180387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.8299153766916,
        1181.1100229840822
      ],
      "voteCount": 895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.36524448338392
      }
    },
    {
      "id": "bb57d1c3c14ddfdbd476c574",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1213.7922318269743,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.6836061806907,
        1249.900857473258
      ],
      "voteCount": 271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 339.4108610613326
      }
    },
    {
      "id": "4233a4d5ccd33695b5b6654f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1145.7858652524042,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.5722857920857,
        1169.9994447127228
      ],
      "voteCount": 620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.6236405614308
      }
    },
    {
      "id": "571db96130050f7fd429d559",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1212.0453948154136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.4046271767552,
        1223.6861624540722
      ],
      "voteCount": 3070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.275002946082935
      }
    },
    {
      "id": "c5b75f828b69a950d9e86fb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1187.4309007964566,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.8532749068145,
        1197.0085266860988
      ],
      "voteCount": 5229,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.8791880802641
      }
    },
    {
      "id": "5d46dbc6d5a47153353e4877",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1159.900087531884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.032468854685,
        1173.7677062090834
      ],
      "voteCount": 2178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.06193135280121
      }
    },
    {
      "id": "1e4b1357e2373f58d1da0610",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1113.2108951624057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.6088477572098,
        1125.8129425676018
      ],
      "voteCount": 2625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.341481508869215
      }
    },
    {
      "id": "a3adc4d578534e7d20770cb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1195.2177020991667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.8367983629714,
        1213.598605835362
      ],
      "voteCount": 1187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.95034332770206
      }
    },
    {
      "id": "db5fad8e7c8e807d76e2933c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1192.7767972968018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.5234697095325,
        1205.030124884071
      ],
      "voteCount": 3117,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.08516112475229
      }
    },
    {
      "id": "ab518dd1cd0fa3be6b329418",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1202.516584253275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.0715704515198,
        1215.9615980550298
      ],
      "voteCount": 1849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.057226060988874
      }
    },
    {
      "id": "7d22ed952b6cb2ec74bfa997",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1200.2525968992582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.6821064750984,
        1219.823087323418
      ],
      "voteCount": 977,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.70277264951277
      }
    },
    {
      "id": "62a7f46b0d8b4d6f741e191c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1197.9480771579974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.01979412438,
        1207.876360191615
      ],
      "voteCount": 5136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.65973204362125
      }
    },
    {
      "id": "2bdcf7566042be3abe585f5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1139.8002547847,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.6197844119422,
        1149.9807251574575
      ],
      "voteCount": 4639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.979848502416132
      }
    },
    {
      "id": "77537e1ad2dd123fa40e2460",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1152.0049026614056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.2506827790835,
        1160.7591225437277
      ],
      "voteCount": 6632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.94980795712264
      }
    },
    {
      "id": "2e69a0a80a2747d8636e0d50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1033.743223829183,
      "unit": "Arena rating",
      "confidenceInterval": [
        1002.296597501627,
        1065.189850156739
      ],
      "voteCount": 390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 257.4257212019925
      }
    },
    {
      "id": "78f48f53cc5c4d459586019b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 978.0078860383073,
      "unit": "Arena rating",
      "confidenceInterval": [
        952.4496247554849,
        1003.5661473211298
      ],
      "voteCount": 726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 170.04600343027636
      }
    },
    {
      "id": "047ddec1fd35399801ee302a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1159.8594857521305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.5099157011541,
        1173.2090558031068
      ],
      "voteCount": 2238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.39149574789047
      }
    },
    {
      "id": "6a2f99c69ac487d0362ca5cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1192.8800323238002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.2342911997061,
        1205.5257734478937
      ],
      "voteCount": 2092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.628656206368554
      }
    },
    {
      "id": "73e2dc6c8ba33503e97218ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1118.1809013078541,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.8895655899448,
        1130.4722370257632
      ],
      "voteCount": 3115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.32801073292524
      }
    },
    {
      "id": "1b31aeb27688ff4fb7fb9073",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1170.1928731020225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1164.277094797796,
        1176.1086514062488
      ],
      "voteCount": 17766,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.110193439072564
      }
    },
    {
      "id": "297fa1b1c84eed98a102aac1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1167.1863674788149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.875166469844,
        1180.4975684877854
      ],
      "voteCount": 2195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.125204140339115
      }
    },
    {
      "id": "e9e620cef1b21229f143c975",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-3-small-8k-instruct",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1176.1169564941592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.6324160988463,
        1213.6014968894724
      ],
      "voteCount": 272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 365.77009782808557
      }
    },
    {
      "id": "d3a01608ecbb909235237544",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1267.0202023239472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.4851627635996,
        1282.555241884295
      ],
      "voteCount": 1503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.82442827226733
      }
    },
    {
      "id": "99e4439186ce602819a990b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1306.258728497247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.3688909167295,
        1316.1485660777644
      ],
      "voteCount": 3305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.46139160521862
      }
    },
    {
      "id": "c62b2d5e76967619a3454a53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1210.350335731218,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.6774494968572,
        1220.0232219655782
      ],
      "voteCount": 4062,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.356561522628844
      }
    },
    {
      "id": "5eb9a15c8a37ffc99a2daa97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1271.4857602393104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.7541106615772,
        1277.217409817044
      ],
      "voteCount": 14101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.55190916142492
      }
    },
    {
      "id": "0c0c399b4d68e3b72d2758bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1156.7908557145547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.009066417294,
        1164.5726450118154
      ],
      "voteCount": 15789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.763866669803132
      }
    },
    {
      "id": "16054748e63b921613785b42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1265.9325776420544,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.7284812278222,
        1283.1366740562864
      ],
      "voteCount": 1124,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.04909703462889
      }
    },
    {
      "id": "7b163b3cfd7b7d92bde4f6ba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1268.5222377792534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.2420415307665,
        1308.8024340277404
      ],
      "voteCount": 205,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 422.36407717718356
      }
    },
    {
      "id": "e826f5610cea30bbfab32395",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1256.0600527629176,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.3787842000565,
        1281.7413213257787
      ],
      "voteCount": 523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.6867434436324
      }
    },
    {
      "id": "716b47bd71c1f47d8e7c697d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1289.9438157084094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.6153157372323,
        1299.2723156795864
      ],
      "voteCount": 3804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.653089821882887
      }
    },
    {
      "id": "7d9ef6c7c4e136fe2d2947c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1277.4357868172735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.667410006614,
        1285.204163627933
      ],
      "voteCount": 5747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.709573130732348
      }
    },
    {
      "id": "848286c4138be529a12f5493",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1256.9091968471757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.8434409952201,
        1268.9749526991313
      ],
      "voteCount": 2438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.89770268907771
      }
    },
    {
      "id": "85f6d8e28e46e18e4bc6013f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1202.1192162605098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.0917934613979,
        1211.1466390596215
      ],
      "voteCount": 4486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.214430818550383
      }
    },
    {
      "id": "30050ce87620bd26f982912e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1299.194655711564,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.5914470033838,
        1315.7978644197444
      ],
      "voteCount": 1341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.76089925066134
      }
    },
    {
      "id": "a484938c1dce960ea0a5a682",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1264.6173712376735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.946709070629,
        1274.2880334047177
      ],
      "voteCount": 4245,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.345362299680836
      }
    },
    {
      "id": "00f81195066a9667a37ecc30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1278.381126987128,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.8886476335838,
        1289.873606340672
      ],
      "voteCount": 2350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.38201158896516
      }
    },
    {
      "id": "6cf79ddf395422937aaee54d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1272.8141226630353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.441777933039,
        1292.1864673930315
      ],
      "voteCount": 1037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.69406828367417
      }
    },
    {
      "id": "13a21fe3d919e63917c81789",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1290.0003099861565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.9056936459747,
        1298.0949263263383
      ],
      "voteCount": 5580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.056752851745227
      }
    },
    {
      "id": "11dec6ed27cb9d430d637a87",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1228.7812164044333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.0458509800465,
        1236.51658182882
      ],
      "voteCount": 6470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.576342489072152
      }
    },
    {
      "id": "44569c25373c8959619079c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1244.692461740908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.0905673790749,
        1251.294356102741
      ],
      "voteCount": 9162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.345952462124423
      }
    },
    {
      "id": "df225cf1fed8fa7b1930b740",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1194.7502087723735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.1964150717727,
        1221.3040024729744
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.55109160500058
      }
    },
    {
      "id": "d9b8b92a4b76e7eb126e20da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1196.0667724004943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.4033931325575,
        1229.7301516684313
      ],
      "voteCount": 319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 294.99811312104487
      }
    },
    {
      "id": "f708fc5c378125f512e400f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1266.0046502889709,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.1708740094164,
        1276.8384265685256
      ],
      "voteCount": 2896,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.553681284609986
      }
    },
    {
      "id": "43cc88133825c012b111cfe8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1264.8402871721928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.425672031817,
        1275.2549023125684
      ],
      "voteCount": 2764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.235161063771667
      }
    },
    {
      "id": "68331d5f0b73a2b9a9d1409c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1241.4365280625898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.2290865492303,
        1251.6439695759495
      ],
      "voteCount": 3517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.122993402238624
      }
    },
    {
      "id": "91abf06658fba2108304301a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1255.8511759243656,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.268740230888,
        1260.4336116178429
      ],
      "voteCount": 24126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.466339186492078
      }
    },
    {
      "id": "f55c4cac2dae67bce682a0c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1245.2372256668173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.9768626123368,
        1256.4975887212977
      ],
      "voteCount": 2576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.007193890939135
      }
    },
    {
      "id": "fdc104417e6ecea340e81fef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "phi-4",
      "organization": "microsoft",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1265.3609608259067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.4723317765465,
        1317.249589875267
      ],
      "voteCount": 127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 700.8873322077188
      }
    },
    {
      "id": "2d055cecd1d3eb74cd30725c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1204.8811537396282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.5831399803747,
        1248.179167498882
      ],
      "voteCount": 195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 488.02241101670245
      }
    },
    {
      "id": "386af496bb9cf38af2ccd599",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1195.8573840695283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.2208691454146,
        1219.493898993642
      ],
      "voteCount": 599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.43559200691976
      }
    },
    {
      "id": "36c06b95f4b1490b9a970e5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1101.1113435332734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.2006375632204,
        1122.0220495033263
      ],
      "voteCount": 898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.82593034981339
      }
    },
    {
      "id": "62124bc29f80d965233e0697",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1152.0928633121594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.2117228004718,
        1163.9740038238465
      ],
      "voteCount": 3849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.7468470826797
      }
    },
    {
      "id": "87c7ce084b654611315b9a93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 988.532067554439,
      "unit": "Arena rating",
      "confidenceInterval": [
        972.676354011861,
        1004.3877810970168
      ],
      "voteCount": 3347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.44483845302871
      }
    },
    {
      "id": "e50941a2b43cf20742679154",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1151.9443855247855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.4953880794592,
        1172.3933829701116
      ],
      "voteCount": 830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.85486895402876
      }
    },
    {
      "id": "eda99e3ad21146a90a3f0038",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1140.2155251334925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.2667125715598,
        1159.1643376954253
      ],
      "voteCount": 1006,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.4690476370591
      }
    },
    {
      "id": "974e6517dfab7775b3f78df3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1120.1430019642808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.7029720554815,
        1148.5830318730798
      ],
      "voteCount": 426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.55420322512754
      }
    },
    {
      "id": "501c4595fd2eb2e950f15727",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1084.2133328849065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.89111129294,
        1105.5355544768731
      ],
      "voteCount": 847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.35012552204799
      }
    },
    {
      "id": "8c06157b76c2054f8239d8f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1173.3908011943756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1135.8038809979544,
        1210.977721390797
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 367.7708484707524
      }
    },
    {
      "id": "e4a6bfa3ac2329d1c454da74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1133.6203668300523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.2393488934365,
        1155.0013847666683
      ],
      "voteCount": 894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.0037299223963
      }
    },
    {
      "id": "11d8f33a87d1d1d60285538c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1139.596251265108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1113.8447509381535,
        1165.3477515920624
      ],
      "voteCount": 467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.62706696653143
      }
    },
    {
      "id": "7dcb4c842191f000efeeca18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1156.8956466797672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.4596643306063,
        1194.331629028928
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 364.8230632844473
      }
    },
    {
      "id": "7978f804c45b931df614c7f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1170.7274919709293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.4416542127146,
        1189.013329729144
      ],
      "voteCount": 1173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.04293814591304
      }
    },
    {
      "id": "215dc9f6f77aa3c394617b28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1119.23807439425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.0586978641159,
        1137.417450924384
      ],
      "voteCount": 1230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.03235032587745
      }
    },
    {
      "id": "8e7562900bab3859344744f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1115.6627047716104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.2165468486196,
        1132.1088626946012
      ],
      "voteCount": 1470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.40973834494369
      }
    },
    {
      "id": "7f6157d45620cbcbbae520a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1124.8410415713888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.7158403526178,
        1162.9662427901599
      ],
      "voteCount": 214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 378.3799425732598
      }
    },
    {
      "id": "b3a7565cf7bf2f5cc629f2be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1124.6659674305956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1101.0511149615882,
        1148.2808198996033
      ],
      "voteCount": 534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.1691357795747
      }
    },
    {
      "id": "d72a09d1e8f80c4f727d08d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1094.5136128151535,
      "unit": "Arena rating",
      "confidenceInterval": [
        1071.008093605074,
        1118.019132025233
      ],
      "voteCount": 753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.82802448877473
      }
    },
    {
      "id": "8314badfc8852fc1d80375d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1137.7368129532151,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.7862927410533,
        1148.6873331653767
      ],
      "voteCount": 4964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.215717391262515
      }
    },
    {
      "id": "125543bfa48a9feb453e0cab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1310.0387530905475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.545753065152,
        1325.531753115943
      ],
      "voteCount": 1421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.48486863736111
      }
    },
    {
      "id": "603a17a6a5d48bb4a22c523a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1352.6153575563576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.4870217307844,
        1363.7436933819313
      ],
      "voteCount": 2756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.23771593739564
      }
    },
    {
      "id": "91c809d65da0c9d8f4a112a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1284.7189028496045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.6944117403687,
        1296.74339395884
      ],
      "voteCount": 2358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.6389265601868
      }
    },
    {
      "id": "f7cec5d2d334a998b6946f60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1327.3555761391885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.0426041011538,
        1334.668548177223
      ],
      "voteCount": 8347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.921679894361779
      }
    },
    {
      "id": "153819a368e278bda0ab31c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1257.9744581674113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.3166047457762,
        1266.6323115890464
      ],
      "voteCount": 10342,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.513010387281728
      }
    },
    {
      "id": "ba9ddc56ee532cf7a7242359",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1298.6874283102716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.6826786149077,
        1316.6921780056355
      ],
      "voteCount": 1011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.38747536388631
      }
    },
    {
      "id": "a941812551a28312ee575b9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1378.3184417642524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.3056276738162,
        1420.3312558546884
      ],
      "voteCount": 183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 459.4807936737461
      }
    },
    {
      "id": "1048e603122f5acdcf59285e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1283.1809501137727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.475962543652,
        1308.8859376838932
      ],
      "voteCount": 438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.00402680892512
      }
    },
    {
      "id": "99eebdc9ec4727d5efa75481",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1329.6375642706803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.3232900063667,
        1340.9518385349936
      ],
      "voteCount": 2531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.324007389717224
      }
    },
    {
      "id": "ea7597c8fd354c8737090949",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1318.401366278035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.1366928016873,
        1327.6660397543828
      ],
      "voteCount": 4447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.344161067391656
      }
    },
    {
      "id": "33e510c016f5effaf111bcd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1306.4498534768125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.5651980270543,
        1319.3345089265704
      ],
      "voteCount": 2195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.21648462418858
      }
    },
    {
      "id": "c5b96b563fe21b92d8a2dc58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1279.4002230435663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.571741656634,
        1291.228704430498
      ],
      "voteCount": 2396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.4218330721861
      }
    },
    {
      "id": "4d5b9c69c99764e2a0f65c68",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1326.7555058947491,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.7958590292128,
        1344.7151527602853
      ],
      "voteCount": 1085,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.96521493271744
      }
    },
    {
      "id": "c044c8ff7e2b845a69ff39b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1324.689429669078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.5823444057135,
        1335.7965149324425
      ],
      "voteCount": 2975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.1147118337084
      }
    },
    {
      "id": "b776655beb12118415d0291f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1301.3725915961845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.462027990753,
        1314.2831552016162
      ],
      "voteCount": 1804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.390456696285995
      }
    },
    {
      "id": "1c53bcb2ac30566dfd0abe22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1316.4713327622158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.717828720496,
        1335.2248368039354
      ],
      "voteCount": 933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.55217594633652
      }
    },
    {
      "id": "6dfb0e6b3783343fae84f3ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1343.9275132446883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.5195695422908,
        1353.3354569470857
      ],
      "voteCount": 4410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.040571001483567
      }
    },
    {
      "id": "f5634d5124a789595ff2b343",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1306.574661453638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.1231617651179,
        1316.0261611421583
      ],
      "voteCount": 4631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.254406862535877
      }
    },
    {
      "id": "d0f15d39609eb3a964b4858a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1301.0674512360565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.113156083357,
        1309.0217463887561
      ],
      "voteCount": 6919,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.47051662650089
      }
    },
    {
      "id": "de35559a6aa0e5322d308908",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1242.1797612892437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.1131333749302,
        1274.246389203557
      ],
      "voteCount": 312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 267.67659730092606
      }
    },
    {
      "id": "157177c79491ec2ad3748e11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1183.6005835214746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.893076712087,
        1220.3080903308626
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 350.7628531386368
      }
    },
    {
      "id": "f1d23ed1d6eeecba0aa009b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1325.5435667879997,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.6500474978898,
        1337.4370860781096
      ],
      "voteCount": 2440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.8234589271622
      }
    },
    {
      "id": "49669c43e9422750040b2e66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1291.4118478617827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.608353072083,
        1303.2153426514822
      ],
      "voteCount": 2249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.268119939208255
      }
    },
    {
      "id": "cd41dea10532208765c25ffb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1305.352526683023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.3549940898847,
        1316.3500592761611
      ],
      "voteCount": 3105,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.484321134876424
      }
    },
    {
      "id": "9f02effb933834de2b39bf28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1317.8257866739896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.131725386293,
        1323.519847961686
      ],
      "voteCount": 16478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.440109724301282
      }
    },
    {
      "id": "e147eb5b734f49b216221620",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1310.2142556776294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.4018923681047,
        1322.026618987154
      ],
      "voteCount": 2432,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.32264029606138
      }
    },
    {
      "id": "3d3f83765720877240c56ed5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-max-0919",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1324.1488522656282,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.5641742949642,
        1362.7335302362922
      ],
      "voteCount": 222,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 387.5552084743762
      }
    },
    {
      "id": "f5ae0ff84251f3161c421d8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1375.4741216886778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.4187644760577,
        1402.5294789012983
      ],
      "voteCount": 459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.55061841590174
      }
    },
    {
      "id": "d56bb56b31d32d67a1223c85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1379.6917987732181,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.275054393575,
        1398.1085431528613
      ],
      "voteCount": 893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.29366378157175
      }
    },
    {
      "id": "90db70cd34beb9acc852b845",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1316.9007541138903,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.795137118782,
        1335.0063711089988
      ],
      "voteCount": 931,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.33564514804101
      }
    },
    {
      "id": "0809fe9c49c4d82afe4f1cea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1356.5550650903792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.1579237321746,
        1366.9522064485836
      ],
      "voteCount": 3425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.14049387699905
      }
    },
    {
      "id": "b86b1fb301f10866d7090265",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1308.880703082034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.0129844293451,
        1321.7484217347228
      ],
      "voteCount": 3765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.102943713148406
      }
    },
    {
      "id": "5497860d127d4716ab70c274",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1370.1502870097092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.322117645559,
        1399.9784563738594
      ],
      "voteCount": 358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.6098464529852
      }
    },
    {
      "id": "94902b9f51f0ff34b0e8c7b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1367.6708611740028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.240636612109,
        1385.1010857358965
      ],
      "voteCount": 964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.08785241726181
      }
    },
    {
      "id": "923237ba7ba72dd86add052d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1352.818783729515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.5097872423364,
        1367.1277802166933
      ],
      "voteCount": 1481,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.29938183043951
      }
    },
    {
      "id": "2eda3ebc8ede25965734611d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1341.8967063317489,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.4122109097798,
        1365.381201753718
      ],
      "voteCount": 571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.57085445076535
      }
    },
    {
      "id": "d696e3449a64763511f47072",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1294.205695652095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.5703466233563,
        1310.8410446808343
      ],
      "voteCount": 1091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.03899617957245
      }
    },
    {
      "id": "6e791e616e14e854b632d534",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1378.5225580461315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.1368691024386,
        1406.9082469898246
      ],
      "voteCount": 392,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.75035121227756
      }
    },
    {
      "id": "f874219197ba718c714d1e0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1380.9115126632819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.433829167245,
        1399.3891961593188
      ],
      "voteCount": 968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.87893982891167
      }
    },
    {
      "id": "4ac70065f4ee001b6ebd02dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1334.8441231555635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.3517320826109,
        1356.336514228516
      ],
      "voteCount": 627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.2467332317419
      }
    },
    {
      "id": "a5cb78dd44dd9e6ade7d529a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1387.0399576276732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.2495995334805,
        1418.8303157218659
      ],
      "voteCount": 315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.08413416088433
      }
    },
    {
      "id": "ed9fbb24b4c15de17cbf7732",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1380.764452471576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.671319258203,
        1395.8575856849488
      ],
      "voteCount": 1419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.30108347626625
      }
    },
    {
      "id": "c9076a50170750bb6c2ba434",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1321.206947653005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.4952482415665,
        1335.9186470644436
      ],
      "voteCount": 1512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.34164250481599
      }
    },
    {
      "id": "c96f3de08b68c80ad77289dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1331.982026761827,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.8418770527978,
        1344.1221764708557
      ],
      "voteCount": 2249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.36647529935164
      }
    },
    {
      "id": "41d015545e39977980b118ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1277.9831859507074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1239.7967460090617,
        1316.169625892353
      ],
      "voteCount": 206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 379.59646672807924
      }
    },
    {
      "id": "191a889f81ea7db013a71ea2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1362.4069069186085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.4906437952548,
        1383.3231700419624
      ],
      "voteCount": 690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.88643832092843
      }
    },
    {
      "id": "9f7f663ccd14ec51df14c17c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1324.1313397421422,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.7995381197363,
        1343.463141364548
      ],
      "voteCount": 732,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.28558118463052
      }
    },
    {
      "id": "73fc29530bbc37321bf7616e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1352.8981883187298,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.8295540997474,
        1371.9668225377118
      ],
      "voteCount": 842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.65487668865167
      }
    },
    {
      "id": "9875d1e68b2edd7534ac0403",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1346.1379757796508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.803777359029,
        1354.4721742002725
      ],
      "voteCount": 5819,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.081376517721374
      }
    },
    {
      "id": "ea62672bb8ead812e2d5d09c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen-plus-0125",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1352.2787000270646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.306451933332,
        1374.2509481207971
      ],
      "voteCount": 578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.67613212245682
      }
    },
    {
      "id": "8f1fb7c4e98e3814b2b13c32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1278.6881700238046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.4937632009664,
        1291.8825768466427
      ],
      "voteCount": 2906,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.31933818181635
      }
    },
    {
      "id": "d515021ab71aaecef65c6825",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1278.6912194424367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.3795941529177,
        1289.002844731956
      ],
      "voteCount": 4763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.679488724087726
      }
    },
    {
      "id": "beaa244fdd282facd1182d55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1192.767807965095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.0849875529475,
        1204.4506283772425
      ],
      "voteCount": 3677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.530328230312094
      }
    },
    {
      "id": "23ca142c6c19de324411d47e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1256.1101284767224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.8645898945329,
        1263.3556670589116
      ],
      "voteCount": 13896,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.666117950604532
      }
    },
    {
      "id": "56370a5980026aefa975076e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1128.817208391633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.0744296947769,
        1137.5599870884892
      ],
      "voteCount": 16506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.8976958780439
      }
    },
    {
      "id": "9cf2f6023db514561bd67302",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1224.715375113888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.1824867158075,
        1241.2482635119686
      ],
      "voteCount": 1411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.15432223584207
      }
    },
    {
      "id": "4ca2dd3cacb83cdae12703f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1228.2594888503313,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.4661378860399,
        1261.052839814623
      ],
      "voteCount": 375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 279.94673837812576
      }
    },
    {
      "id": "d9798f73590393ed09b3ddc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1188.1865347316395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.348186201354,
        1209.024883261925
      ],
      "voteCount": 928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.0395481868485
      }
    },
    {
      "id": "38a818495f70bcc128eb8981",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1263.445404179901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.063511929518,
        1273.8272964302842
      ],
      "voteCount": 4572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.058009139113867
      }
    },
    {
      "id": "b0693d44cc5d3fe012620e5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1245.1089232669806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.3423013249603,
        1253.875545209001
      ],
      "voteCount": 7695,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.006373583988385
      }
    },
    {
      "id": "d557c85d0f5fa0d0996226e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1220.4778925453775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.0207577884282,
        1232.9350273023265
      ],
      "voteCount": 3117,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.39616551837703
      }
    },
    {
      "id": "4248970a335ce54ecc7305f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1191.1956977024688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.0673694445559,
        1202.3240259603817
      ],
      "voteCount": 3882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.23767209184469
      }
    },
    {
      "id": "81b103e1f9dc2dfbd4da69f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1269.939645825141,
      "unit": "Arena rating",
      "confidenceInterval": [
        1252.7498340403888,
        1287.1294576098933
      ],
      "voteCount": 1506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.92120181098686
      }
    },
    {
      "id": "2e1fe7965305512554646930",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1247.3199657342523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.2748269995295,
        1258.365104468975
      ],
      "voteCount": 4398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.757489892141006
      }
    },
    {
      "id": "301b0414fe693281e36ea128",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1231.2676006365011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.6426495050264,
        1242.8925517679759
      ],
      "voteCount": 2860,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.17921058561761
      }
    },
    {
      "id": "9caee8a7e45c80f3af782e3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1245.9433234143823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.6541423361118,
        1263.232504492653
      ],
      "voteCount": 1431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.81309036737842
      }
    },
    {
      "id": "9012dcc7d927c0471a71431c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1259.3027422544899,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.359739437675,
        1268.2457450713048
      ],
      "voteCount": 7665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.819512355753393
      }
    },
    {
      "id": "9220e1e678b1b240daed0a69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1217.4841977524916,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.9809595962947,
        1226.9874359086887
      ],
      "voteCount": 6502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.50969766144207
      }
    },
    {
      "id": "6fd56525d2e07001b8dc5fdc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1216.2093988747201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.1077167200942,
        1224.3110810293456
      ],
      "voteCount": 9518,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.086543627901982
      }
    },
    {
      "id": "5f882e67f03709f2047628b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1137.442733921628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.738616429146,
        1164.1468514141097
      ],
      "voteCount": 599,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 185.63517776390464
      }
    },
    {
      "id": "bd45028f6424708290af7861",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1120.9355365085044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.753957400552,
        1142.1171156164569
      ],
      "voteCount": 1434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.79398750534564
      }
    },
    {
      "id": "3fd3688545907dccf1378081",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1226.6917339276797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.7973660888651,
        1238.586101766494
      ],
      "voteCount": 3345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.82871348844999
      }
    },
    {
      "id": "ec52fb3b55a005c5df7cb770",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1220.989476525399,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.7445827265888,
        1232.2343703242093
      ],
      "voteCount": 3188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.916566973291786
      }
    },
    {
      "id": "eb5a82bea17a5034b34dad45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1211.7876351534878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.328697022421,
        1223.2465732845544
      ],
      "voteCount": 3740,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.18161412645055
      }
    },
    {
      "id": "2f7683b812004a53767e9fef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1233.2813333139025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.728072962098,
        1238.834593665707
      ],
      "voteCount": 26195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.027861803123985
      }
    },
    {
      "id": "99bcb54b01aca31454d9d744",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1173.816439798381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.4490280352338,
        1186.1838515615282
      ],
      "voteCount": 2898,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.8163512505362
      }
    },
    {
      "id": "352ef671983e54ade2f12ba4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-110b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1208.1160993599763,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.5915537204007,
        1238.6406449995518
      ],
      "voteCount": 487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 242.5505335325106
      }
    },
    {
      "id": "d810b873a2d6c391573cfe9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1239.3380386850124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.381442847483,
        1253.2946345225419
      ],
      "voteCount": 3152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.70640516118959
      }
    },
    {
      "id": "6a502c21cee5e4df24fe670d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1238.242108817552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.3959889664447,
        1251.0882286686588
      ],
      "voteCount": 3208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.95836632167453
      }
    },
    {
      "id": "67f9f4c4fb6e150b6f3e740c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1136.6742332033195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.4640395916517,
        1150.8844268149878
      ],
      "voteCount": 2391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.565864143404866
      }
    },
    {
      "id": "9ad317799e10d7f4e2854a34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1207.2067275073896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.3038439058907,
        1216.1096111088887
      ],
      "voteCount": 9520,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.63313447351135
      }
    },
    {
      "id": "edda3c9f2136016c1e8cd9b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1065.220171037572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1054.2120516184275,
        1076.2282904567169
      ],
      "voteCount": 11501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.54496736847828
      }
    },
    {
      "id": "b9027f47b661b0e0ef9e8d26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1189.5490954904608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.526078123025,
        1209.5721128578966
      ],
      "voteCount": 944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.36691975893618
      }
    },
    {
      "id": "ed293333c09c42d3f094a980",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1195.1573815188096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.078943184751,
        1234.2358198528682
      ],
      "voteCount": 279,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 397.5376058704891
      }
    },
    {
      "id": "25b852be25e585d83bf38a80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1108.7625464364626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1082.7936578150818,
        1134.7314350578433
      ],
      "voteCount": 540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.5539256588522
      }
    },
    {
      "id": "851f33f5592c27e77b1d9430",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1207.8288509357499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.0701557981486,
        1220.5875460733512
      ],
      "voteCount": 3024,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.3756466520804
      }
    },
    {
      "id": "2f651b7a869ea49c8dae9c82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1198.8479932132216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.125211502444,
        1209.5707749239991
      ],
      "voteCount": 4910,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.93082914167687
      }
    },
    {
      "id": "d32024fa9b135a7804bde266",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1171.267995538275,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.6208845689962,
        1186.915106507554
      ],
      "voteCount": 1866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.73414192702181
      }
    },
    {
      "id": "0c5a124754968aa50730c6b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1124.3667101457231,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.5743247061173,
        1138.159095585329
      ],
      "voteCount": 2453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.52022265340222
      }
    },
    {
      "id": "106416b40330a0ce9b7ff4b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1206.530583370999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.9422944244739,
        1226.1188723175237
      ],
      "voteCount": 1037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.88420591300701
      }
    },
    {
      "id": "4ac56cb9e7fbd74ed284cf94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1191.0308360549438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.6190408312978,
        1204.44263127859
      ],
      "voteCount": 3116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.82498486044331
      }
    },
    {
      "id": "3cab0bd03ff7ba376ecbe15c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1184.0791483892358,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.318140092898,
        1197.8401566855737
      ],
      "voteCount": 1972,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.29516576144431
      }
    },
    {
      "id": "2e6462cd80e9805390c52e6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1208.7161819965554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.1939751563907,
        1229.2383888367199
      ],
      "voteCount": 939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.63568614133875
      }
    },
    {
      "id": "be15f0fb8719466b5b1eebac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1230.2308987479882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.350301863381,
        1241.1114956325955
      ],
      "voteCount": 5248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.818341180065396
      }
    },
    {
      "id": "e19703544c465eb1ca0a0f72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1163.4370801568261,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.959222083785,
        1174.914938229867
      ],
      "voteCount": 4502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.29458236937913
      }
    },
    {
      "id": "b533df3b18af1d29a9844971",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1165.923619672909,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.9095038063242,
        1175.9377355394936
      ],
      "voteCount": 6231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.105321251696655
      }
    },
    {
      "id": "d68de2d69a2dfcdd62f078ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1083.2746187360917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1042.654141560699,
        1123.8950959114845
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 429.53035369476214
      }
    },
    {
      "id": "55d9bcb1f41e622130fc0ac7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1190.1743630453734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.3038214371404,
        1205.0449046536064
      ],
      "voteCount": 2102,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.564851803418016
      }
    },
    {
      "id": "591f1bea270da1ebad063d16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1166.6516093402658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.1607617035534,
        1180.1424569769783
      ],
      "voteCount": 2184,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.37860756870068
      }
    },
    {
      "id": "16339091969db580afa6e958",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1164.0510254702713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.7233279846387,
        1178.3787229559039
      ],
      "voteCount": 2568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.438791048321384
      }
    },
    {
      "id": "eb9af7b790e7357dcdad822f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1190.0982974684603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.977540767566,
        1197.2190541693544
      ],
      "voteCount": 17839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.199458424538442
      }
    },
    {
      "id": "8add2d137962511763184735",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1104.7684179513021,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.0813419507704,
        1120.4554939518337
      ],
      "voteCount": 1741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.0601305214534
      }
    },
    {
      "id": "8b8b69533ab08a6d0925c508",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-14b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1152.71487902884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.727736219022,
        1188.7020218386579
      ],
      "voteCount": 293,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 337.1308942940126
      }
    },
    {
      "id": "3b7720dc61643551a5efe3ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1264.8538524632208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.4498763325946,
        1278.257828593847
      ],
      "voteCount": 3241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.77040272891196
      }
    },
    {
      "id": "e8fde074ecbdbfb8036df4c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1260.5665554974476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.661651905164,
        1271.471459089731
      ],
      "voteCount": 3930,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.956188236716194
      }
    },
    {
      "id": "733d271898744a9b6a1f2ed2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1131.0142782711605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.4884417657406,
        1143.5401147765806
      ],
      "voteCount": 3022,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.84296812328223
      }
    },
    {
      "id": "0e8c22d0e70365394d8873a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1222.8863527198953,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.188569645698,
        1230.5841357940928
      ],
      "voteCount": 11877,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.425354539318949
      }
    },
    {
      "id": "1258fa70b8e09623de6ad9a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1083.2864761632009,
      "unit": "Arena rating",
      "confidenceInterval": [
        1073.7536614118587,
        1092.8192909145428
      ],
      "voteCount": 14160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.65626219754263
      }
    },
    {
      "id": "4ad1a22a90b27f52a91ae8a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1218.7711908379388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.6007148454594,
        1236.941666830418
      ],
      "voteCount": 1176,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.94812887610472
      }
    },
    {
      "id": "62ede3470956e30a6bb7207c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1181.922241848974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.7522430428216,
        1217.0922406551263
      ],
      "voteCount": 313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 321.99455304879314
      }
    },
    {
      "id": "139964e4e64dc38ad678301d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1129.672199284014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.0938029445153,
        1152.2505956235127
      ],
      "voteCount": 777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.7058300136549
      }
    },
    {
      "id": "55c9006befb8c3c1f09ad495",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1234.6359199165936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.5566552558419,
        1245.7151845773453
      ],
      "voteCount": 3830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.95403391069101
      }
    },
    {
      "id": "4dbf2e2a2690ee088a790fe0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1219.5986030188265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.2736896979852,
        1228.9235163396677
      ],
      "voteCount": 6072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.635673711449734
      }
    },
    {
      "id": "69cf8a742148592f5ae3a425",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1183.6376665207385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.9125086366812,
        1197.3628244047961
      ],
      "voteCount": 2307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.03865113104721
      }
    },
    {
      "id": "9e20b4e8883d59676e2ead46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1139.1574246082191,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.95150039623,
        1151.3633488202083
      ],
      "voteCount": 3063,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.78333540014429
      }
    },
    {
      "id": "e74d248b38a14312daa9c1a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1229.503997084797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.5356304455568,
        1247.4723637240372
      ],
      "voteCount": 1227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.0467683638538
      }
    },
    {
      "id": "a81790b7a1244d9881a2ca0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1220.7359135959155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.1598379270822,
        1232.3119892647487
      ],
      "voteCount": 3861,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.88402040617
      }
    },
    {
      "id": "75e2cb660946ab1650178c61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1213.6146344240856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.20182770191,
        1226.0274411462615
      ],
      "voteCount": 2405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.10918193163167
      }
    },
    {
      "id": "035fcafd4d0bcc70ac5b17d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1213.469481255379,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.9775414511362,
        1231.961421059622
      ],
      "voteCount": 1187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.01614040000347
      }
    },
    {
      "id": "f8bcd6a3cd0c5146d4e2646c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1241.4522669265502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.9969372675178,
        1250.9075965855827
      ],
      "voteCount": 6351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.273257148914304
      }
    },
    {
      "id": "a93c44e0d148919378b4f3d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1170.7187632146602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.3783873979582,
        1181.0591390313623
      ],
      "voteCount": 5401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.834053941860656
      }
    },
    {
      "id": "e21cce5bbbdaed4534060aeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1182.2550194112264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1173.6400113353611,
        1190.8700274870914
      ],
      "voteCount": 7653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.320359168606878
      }
    },
    {
      "id": "8f07fd4be05a5548a06fb03d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1100.1220599788421,
      "unit": "Arena rating",
      "confidenceInterval": [
        1066.4130584072532,
        1133.831061550431
      ],
      "voteCount": 324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 295.7982474866308
      }
    },
    {
      "id": "47b894a3b755f536083b99bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1096.0741092249068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1063.7080678004745,
        1128.440150649339
      ],
      "voteCount": 395,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.69865079505996
      }
    },
    {
      "id": "ec178b58e77d75fc572df16e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1221.784990658294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1209.0713430468024,
        1234.4986382697855
      ],
      "voteCount": 2574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.07694085341722
      }
    },
    {
      "id": "df1d198f8aeec732604f5ad8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1200.2253180504044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.5908483428739,
        1211.8597877579348
      ],
      "voteCount": 2649,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.23684404639394
      }
    },
    {
      "id": "fe158d2f9243ec68d0f68f9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1191.591310194976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.1661983977492,
        1204.0164219922024
      ],
      "voteCount": 3140,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.18874349033955
      }
    },
    {
      "id": "b43d8450d828d7a6e4e12f25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1202.9456124083945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.8265438514818,
        1209.0646809653072
      ],
      "voteCount": 21741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.747078324122766
      }
    },
    {
      "id": "0e5b1d330f3c1f0507f5771a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1138.5249213601298,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.7271025640202,
        1152.3227401562394
      ],
      "voteCount": 2175,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.55924621778849
      }
    },
    {
      "id": "631754844d9ed95874a31d20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-32b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1164.3830716377834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.2763409255977,
        1196.4898023499688
      ],
      "voteCount": 369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 268.3465332158711
      }
    },
    {
      "id": "682950632f7d9f9ab84e3657",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1145.6305062458425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.5387888378789,
        1165.722223653806
      ],
      "voteCount": 1028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.08432531590277
      }
    },
    {
      "id": "4ac80f32f1b0fae567e678af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1129.8222321845938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.3829144745393,
        1147.261549894648
      ],
      "voteCount": 1283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.17039239203851
      }
    },
    {
      "id": "accfc8f14ae775bfebec0baf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1048.6140000505088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1029.6909799376558,
        1067.5370201633616
      ],
      "voteCount": 1080,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.21476733329548
      }
    },
    {
      "id": "70ba7c59854ee9b34ec8ef08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1105.4184518663303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1094.5227325710289,
        1116.314171161632
      ],
      "voteCount": 4756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.904066528703705
      }
    },
    {
      "id": "0c154ee394e749074c8e93d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 894.6957529797124,
      "unit": "Arena rating",
      "confidenceInterval": [
        878.7270570639694,
        910.6644488954556
      ],
      "voteCount": 5172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.38083633118227
      }
    },
    {
      "id": "da31cfb0466251c1449b0864",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1102.2164159181184,
      "unit": "Arena rating",
      "confidenceInterval": [
        1071.037362387893,
        1133.395469448344
      ],
      "voteCount": 356,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 253.0635949560985
      }
    },
    {
      "id": "a9479a5c40ed337a60cb6274",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 999.0459197606011,
      "unit": "Arena rating",
      "confidenceInterval": [
        958.4371594810532,
        1039.654680040149
      ],
      "voteCount": 211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 429.2825950803273
      }
    },
    {
      "id": "db8911b99b7ec998b5230e71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1097.9976850035125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1081.776292048661,
        1114.219077958364
      ],
      "voteCount": 1419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.4983496317059
      }
    },
    {
      "id": "eb3e3e1b885e7e825b11b0b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1093.2728195313623,
      "unit": "Arena rating",
      "confidenceInterval": [
        1079.101717252814,
        1107.4439218099105
      ],
      "voteCount": 2075,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.27705128771565
      }
    },
    {
      "id": "dc9b9ee9210061ea756c0939",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1086.309516640491,
      "unit": "Arena rating",
      "confidenceInterval": [
        1062.457708437338,
        1110.1613248436438
      ],
      "voteCount": 738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.0970592461528
      }
    },
    {
      "id": "9168172ad05812edc5e24eb0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1046.3931780575995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1028.0935571688897,
        1064.6927989463093
      ],
      "voteCount": 1147,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.17420654531392
      }
    },
    {
      "id": "a1995bc8ea92b827a4e23fc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1141.2196981688905,
      "unit": "Arena rating",
      "confidenceInterval": [
        1108.9312165867277,
        1173.5081797510534
      ],
      "voteCount": 390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.3932627015102
      }
    },
    {
      "id": "f708d7f872b093dea6277174",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1108.3870871719369,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.7419389170877,
        1127.032235426786
      ],
      "voteCount": 1277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.49727451783203
      }
    },
    {
      "id": "f009520abc8ce7db06303b16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1066.8709778236266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1047.0218810151791,
        1086.720074632074
      ],
      "voteCount": 820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.5617252458079
      }
    },
    {
      "id": "764dc26f93f134dd56e4ffc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1107.1616201733657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.3898679633035,
        1137.933372383428
      ],
      "voteCount": 433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 246.49508904702245
      }
    },
    {
      "id": "2cb6186476d47f107034535b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1117.9575121487194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.3621408719118,
        1132.5528834255272
      ],
      "voteCount": 2193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.454157561260274
      }
    },
    {
      "id": "f6f2467e3af5e2fa6154982c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1074.4169815574865,
      "unit": "Arena rating",
      "confidenceInterval": [
        1059.4222392570077,
        1089.4117238579652
      ],
      "voteCount": 1895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.530445633447584
      }
    },
    {
      "id": "b1b80b9f5df6546f5832d473",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1066.6714697902244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.664849306359,
        1079.67809027409
      ],
      "voteCount": 2636,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.03852398468239
      }
    },
    {
      "id": "ad007132e2fed097c355201b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1075.7375049711795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1051.8379289521804,
        1099.6370809901787
      ],
      "voteCount": 692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.69083870192577
      }
    },
    {
      "id": "37b27e9efef16209e96268e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1085.279770456901,
      "unit": "Arena rating",
      "confidenceInterval": [
        1067.633999061367,
        1102.925541852435
      ],
      "voteCount": 988,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.05599010096435
      }
    },
    {
      "id": "99b201f64de6bc8c32618aa3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1053.6118384818524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1034.7524687111777,
        1072.4712082525273
      ],
      "voteCount": 1136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.58873900482753
      }
    },
    {
      "id": "290afacfc34c78bc5f07cf9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1089.3750528636529,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.0361620493013,
        1098.7139436780044
      ],
      "voteCount": 7597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.70358364185681
      }
    },
    {
      "id": "302071dbf808273f60dd0ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-4b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1039.0876784170937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1014.1476310268463,
        1064.027725807341
      ],
      "voteCount": 564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.91920644235793
      }
    },
    {
      "id": "fa7e45fc7d693ce561c8b2c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1281.6628541830553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.3964351935492,
        1293.9292731725616
      ],
      "voteCount": 4167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.168722573714916
      }
    },
    {
      "id": "d5dd86da73c9998fd468d967",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1273.7291645343657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.1021247433441,
        1283.3562043253874
      ],
      "voteCount": 6370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.1262237769262
      }
    },
    {
      "id": "a3e97b7d9554767479922d52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1187.6741974752067,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.5231028324154,
        1197.8252921179983
      ],
      "voteCount": 5888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.824372525302817
      }
    },
    {
      "id": "aaebac3ff2e5b4e394cf2df5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1250.0917331137844,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.80765835924,
        1256.3758078683286
      ],
      "voteCount": 25039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.279843508400855
      }
    },
    {
      "id": "4ae08d92e2e769af3fde94aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1127.183568797842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.1404149624339,
        1135.2267226332501
      ],
      "voteCount": 25865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.84056152614228
      }
    },
    {
      "id": "67020859ea76bc880338c0a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1230.6602807191045,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.4034191158125,
        1245.9171423223966
      ],
      "voteCount": 1846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.59464303718612
      }
    },
    {
      "id": "9a5ca5d24db894fa882b4f80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1239.7592541079357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1214.5869353482221,
        1264.9315728676493
      ],
      "voteCount": 858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.94921885590617
      }
    },
    {
      "id": "0d4ec1d404360096ad3a49c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1154.3425174858016,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.4939324532797,
        1174.1911025183235
      ],
      "voteCount": 1091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.5564365472136
      }
    },
    {
      "id": "ce647e94fe52e7f98c6a0e0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1251.123029720452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.1271763739733,
        1260.1188830669312
      ],
      "voteCount": 7597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.06631392100477
      }
    },
    {
      "id": "a58d7be12c6cf02a1a505ead",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1238.1667149199002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.259872423181,
        1246.0735574166195
      ],
      "voteCount": 10854,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.27458764653078
      }
    },
    {
      "id": "47bed25d22f03bb2c434b265",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1207.0274534346172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.3417131711199,
        1218.7131936981145
      ],
      "voteCount": 3842,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.54809042082733
      }
    },
    {
      "id": "302f3216620824bf3f5dfcc6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1186.210454383524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.1130737803196,
        1196.3078349867283
      ],
      "voteCount": 5818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.541243783928255
      }
    },
    {
      "id": "28743a140ea398df8916ef82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1261.2160942863688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.1055434178181,
        1276.3266451549193
      ],
      "voteCount": 2091,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.438030760875115
      }
    },
    {
      "id": "377ceb4ce1df5ecdba961d6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1246.9664378054501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.0505746018937,
        1256.8823010090066
      ],
      "voteCount": 6892,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.5955738850999
      }
    },
    {
      "id": "982c0c7ff8cd828f17fecfa4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1222.152269329231,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.9550946478666,
        1232.3494440105956
      ],
      "voteCount": 4522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.068459232753245
      }
    },
    {
      "id": "225a4887cb85532f5cab2bea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1243.5744808188442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.8709469754244,
        1258.2780146622645
      ],
      "voteCount": 2386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.2791162357257
      }
    },
    {
      "id": "39c52ddb8f04d19a2a44762b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1256.4548508998585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.1697624055414,
        1264.7399393941755
      ],
      "voteCount": 10756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.86891245296788
      }
    },
    {
      "id": "896f135ebe8ae7610b9bddff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1212.8402016353843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.2785276609325,
        1221.4018756098367
      ],
      "voteCount": 9492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.081881302469547
      }
    },
    {
      "id": "0f7487147f4bfe4da91b76ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1209.488992671174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.0852922554636,
        1216.8926930868843
      ],
      "voteCount": 13814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.26926134162868
      }
    },
    {
      "id": "cb020ffe7380bfa1ed345730",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1133.5165932945372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.7799106921116,
        1161.2532758969628
      ],
      "voteCount": 495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.2685952647268
      }
    },
    {
      "id": "f2044f2704f3fdfb498f2fad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1136.1210624017694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.8499409662727,
        1164.392183837266
      ],
      "voteCount": 552,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.06062085449503
      }
    },
    {
      "id": "fbe557de74e035b7a03f040e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1234.1445757025049,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.4728643921203,
        1245.8162870128895
      ],
      "voteCount": 3483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.462789339063036
      }
    },
    {
      "id": "7153ff9e125d6925b13c8549",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1208.0612633975475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.4048692626632,
        1217.717657532432
      ],
      "voteCount": 5327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.273577315448467
      }
    },
    {
      "id": "ca0929e822196353ce37bc84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1216.652865258587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1206.3160966633977,
        1226.9896338537765
      ],
      "voteCount": 5502,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.814637609777606
      }
    },
    {
      "id": "a4500aba8a611982e708d41f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1232.4115862709264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.1362197328303,
        1237.6869528090226
      ],
      "voteCount": 39302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.244511371915716
      }
    },
    {
      "id": "15cde58a0a9c5d7751ef46bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1168.1203904359547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.206882284832,
        1181.0338985870771
      ],
      "voteCount": 2666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.410251301087285
      }
    },
    {
      "id": "89cd9f638b804af97aedfd53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-72b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1180.995162278606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.8437582024062,
        1211.1465663548056
      ],
      "voteCount": 501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.656752083054
      }
    },
    {
      "id": "f0923238aff52ae0bfa8b085",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1226.6761492098674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.7671752040574,
        1255.5851232156772
      ],
      "voteCount": 417,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 217.5550531913759
      }
    },
    {
      "id": "30d4bff3686ce090a20026ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1208.2252218530652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.4299721976813,
        1229.0204715084492
      ],
      "voteCount": 772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.57244406738396
      }
    },
    {
      "id": "fc894cb1e606d2f9e2758d98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1080.5013374826449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1057.5082265082171,
        1103.4944484570724
      ],
      "voteCount": 701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.62562009888165
      }
    },
    {
      "id": "9f1b51e95cb857c9236c60f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1162.4888735674872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.1470449254043,
        1173.8307022095698
      ],
      "voteCount": 3243,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.48651721929078
      }
    },
    {
      "id": "3e017c09d81cd5c69c3918c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 992.807693056981,
      "unit": "Arena rating",
      "confidenceInterval": [
        977.2634089215502,
        1008.3519771924116
      ],
      "voteCount": 3136,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.89922150964033
      }
    },
    {
      "id": "2c09779e5603d2eb2b161b6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1143.675239166158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.121952373151,
        1180.2285259591645
      ],
      "voteCount": 231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 347.82170986030917
      }
    },
    {
      "id": "945a6442928b450bbb124643",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1157.3532032490705,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.7055126906735,
        1175.0008938074675
      ],
      "voteCount": 1019,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.07362243926322
      }
    },
    {
      "id": "997905cec5c9a4811118cf33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1149.0727155208924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.405904732565,
        1164.7395263092194
      ],
      "voteCount": 1333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.89472638753842
      }
    },
    {
      "id": "5103b3fcb58949c43fddb2ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1149.4038159977665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.5063781599263,
        1177.301253835607
      ],
      "voteCount": 447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.59674104108612
      }
    },
    {
      "id": "d5bee7a881f19d899655427b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1084.6467986220582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1061.9981884288989,
        1107.2954088152178
      ],
      "voteCount": 708,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.53248534602145
      }
    },
    {
      "id": "a4545caa2b41745cb7a67df1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1179.680529340554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.94375163579,
        1220.4173070453176
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 431.9934522863068
      }
    },
    {
      "id": "789458efa1c201e39ce27081",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1160.4520651934145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.2134572392042,
        1181.6906731476245
      ],
      "voteCount": 828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.42374157511581
      }
    },
    {
      "id": "181c18028f18bab8777048ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1155.143172300545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.0423698601398,
        1178.2439747409503
      ],
      "voteCount": 578,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.91781698032162
      }
    },
    {
      "id": "bde5c3c0b8eefbb7fec9a942",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1164.6440356164303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.5877030101506,
        1200.7003682227105
      ],
      "voteCount": 266,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 338.42849336590757
      }
    },
    {
      "id": "539d96f3eb2fb4a0ec9fd50e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1179.6063718665448,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.034884363089,
        1196.1778593700005
      ],
      "voteCount": 1282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.48695610059012
      }
    },
    {
      "id": "04ff7b3a8430f602beadea0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1111.8755725501478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1093.69509276381,
        1130.056052336486
      ],
      "voteCount": 1093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.04279277467882
      }
    },
    {
      "id": "babfc7e533cd80cfbde0be96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1122.0320586777807,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.8926725998986,
        1136.1714447556633
      ],
      "voteCount": 1715,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.043311666500855
      }
    },
    {
      "id": "68f9cbbc3542327f264fec1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1161.7462119395695,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.8185335719118,
        1191.6738903072269
      ],
      "voteCount": 372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.15775966488562
      }
    },
    {
      "id": "ed2ec76260d5acbf1185f5f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1120.3080066679167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.818485588126,
        1140.7975277477078
      ],
      "voteCount": 690,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.28673029568998
      }
    },
    {
      "id": "3ca85bba9f29d10fc49ee2e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1111.9786395813794,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.974178431832,
        1136.9831007309267
      ],
      "voteCount": 589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 162.75667827313845
      }
    },
    {
      "id": "1bef93e2c7887a38f34c4fa9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1142.956203136229,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.0678985892941,
        1152.844507683164
      ],
      "voteCount": 4737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.453498625625116
      }
    },
    {
      "id": "263d6ac03b416178a49a1723",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen1.5-7b-chat",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1066.8769947052228,
      "unit": "Arena rating",
      "confidenceInterval": [
        1032.2585633268527,
        1101.495426083593
      ],
      "voteCount": 296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 311.9741345769181
      }
    },
    {
      "id": "bd4c83dd7ec126196df1e6d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1298.7085695762553,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.213543585913,
        1310.2035955665979
      ],
      "voteCount": 4078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.3972508066021
      }
    },
    {
      "id": "8427582e999fe981ae32026d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1295.844877991899,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.8885209250084,
        1304.8012350587894
      ],
      "voteCount": 6249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.881736770809628
      }
    },
    {
      "id": "5d92eaa94020a74f671b7491",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1222.4956682822203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.89336400421,
        1232.0979725602308
      ],
      "voteCount": 5504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.00240423007723
      }
    },
    {
      "id": "0a8b54cdff105a7a1fb9d295",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1275.0619402207803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.0221841562811,
        1281.1016962852796
      ],
      "voteCount": 19928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.49604174386686
      }
    },
    {
      "id": "bcb409fd8613eee2cebae546",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1170.9391527619496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.4942911042046,
        1178.3840144196943
      ],
      "voteCount": 23757,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.428363725878576
      }
    },
    {
      "id": "466a03d293f3e1541b5b9a10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1256.7004647496578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.0662888087093,
        1271.3346406906062
      ],
      "voteCount": 1763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.74942110974851
      }
    },
    {
      "id": "31beec6218ab990d04c3d2d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1254.9984715798737,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.4915186129115,
        1281.505424546836
      ],
      "voteCount": 596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.90409669569067
      }
    },
    {
      "id": "d72e386f013c0d6a95b6e6b3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1221.7081597037802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1204.0580305356357,
        1239.358288871925
      ],
      "voteCount": 1340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.09602997017211
      }
    },
    {
      "id": "68a86c649f8ba2edc1ad962e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1283.3863249824333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.6764573888956,
        1292.0961925759707
      ],
      "voteCount": 6483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.74817303475581
      }
    },
    {
      "id": "ba23a89760afcdbd4fac1890",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1272.220277140931,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.9000588102267,
        1279.5404954716355
      ],
      "voteCount": 10780,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.949283048541906
      }
    },
    {
      "id": "807ca6b903252d0140dae515",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1228.61151372539,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.8877020848456,
        1239.3353253659343
      ],
      "voteCount": 4345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.9365791668423
      }
    },
    {
      "id": "a173e08b773f96b27be1d4d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1220.725547766124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.5292455484723,
        1229.9218499837757
      ],
      "voteCount": 5791,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.01558793830896
      }
    },
    {
      "id": "abce31438b03bf26f934dc92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1275.141157087458,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.1910927489957,
        1289.0912214259201
      ],
      "voteCount": 2262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.65895643574002
      }
    },
    {
      "id": "7bbb993640a963df6edcadee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1279.6215254954245,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.2423567799196,
        1289.0006942109299
      ],
      "voteCount": 6456,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.899843496959637
      }
    },
    {
      "id": "f4ae251be9aecff69c37771b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1274.8450016957372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.0433329694406,
        1284.6466704220338
      ],
      "voteCount": 4235,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.00943373452619
      }
    },
    {
      "id": "1f7ad20948b9a6a76cb1e6f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1275.9988965921293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.465730111446,
        1290.532063072813
      ],
      "voteCount": 2067,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.982478744128926
      }
    },
    {
      "id": "fdf11d8333f5b2c1b9e8711f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1281.0064922172724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.420322742737,
        1288.5926616918073
      ],
      "voteCount": 10308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.981279243797582
      }
    },
    {
      "id": "146110660475e56a8220ff7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1241.3510312127469,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.4797713027456,
        1249.2222911227484
      ],
      "voteCount": 9976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.128438560119477
      }
    },
    {
      "id": "9ac76e5475cddf8716c01bc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1240.4635577812878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.6627545222182,
        1247.2643610403575
      ],
      "voteCount": 14194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.039937723507068
      }
    },
    {
      "id": "3ee3e140d9de139880ccbb21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1175.7906255934536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.0353009080004,
        1196.5459502789067
      ],
      "voteCount": 901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.14060150220197
      }
    },
    {
      "id": "273a51871d3f4f25d14d3a54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1171.8187193193612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.4508167824447,
        1193.186621856278
      ],
      "voteCount": 1167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.85777777117185
      }
    },
    {
      "id": "3cd14e112eaffcb7d590b56d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1259.2214408849236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.9804484993308,
        1269.4624332705162
      ],
      "voteCount": 4614,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.301587739737034
      }
    },
    {
      "id": "e0c486ed4906136091989e82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1273.1960642479594,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.839626825762,
        1282.552501670157
      ],
      "voteCount": 4835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.788978177742898
      }
    },
    {
      "id": "d3d042e5b5bd4d4facc30894",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1242.7007236000402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1233.495058514567,
        1251.9063886855133
      ],
      "voteCount": 6698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.06043943758476
      }
    },
    {
      "id": "4c08719d003c8e70ac6390c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1260.967076458911,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.0236377840451,
        1265.9105151337767
      ],
      "voteCount": 37325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.3615379138028585
      }
    },
    {
      "id": "69b4216d6cad0ef8786c22bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1236.2539052022726,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.7710090265991,
        1246.7368013779458
      ],
      "voteCount": 4555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.606609457312636
      }
    },
    {
      "id": "63d5f89b8240f9ec18c255c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2-72b-instruct",
      "organization": "alibaba",
      "license": "Qianwen LICENSE",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1244.5410137749088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.7098805465093,
        1272.3721470033083
      ],
      "voteCount": 596,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.63485095929173
      }
    },
    {
      "id": "4d11aa9e3b60a3b08dfdaa8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1321.4941337465875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.5658755995041,
        1332.422391893671
      ],
      "voteCount": 3329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.088925250464055
      }
    },
    {
      "id": "889b9077ba575e542fbfee55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1355.4599629205868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.8356950939765,
        1363.0842307471971
      ],
      "voteCount": 6688,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.13213146493757
      }
    },
    {
      "id": "b33cbf07ca2f70b5793f6f7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1254.3266587897224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.896410204782,
        1262.756907374663
      ],
      "voteCount": 5684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.500547453753537
      }
    },
    {
      "id": "310956f1d7a0c011a91a5484",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1316.1517640066336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.032155619751,
        1321.2713723935162
      ],
      "voteCount": 20561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.82303032739615
      }
    },
    {
      "id": "b8afa7302c4acff75c77d6c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1237.710306296417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.2665264634697,
        1244.1540861293643
      ],
      "voteCount": 24444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.808992227592116
      }
    },
    {
      "id": "9bce84252c58783c8c3dcc7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1294.0403865096744,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.9242869849236,
        1306.156486034425
      ],
      "voteCount": 2397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.214614433153216
      }
    },
    {
      "id": "e36d38831e6006d278d62e24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1322.4432235864833,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.5968122439785,
        1355.2896349289883
      ],
      "voteCount": 340,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.853391495185
      }
    },
    {
      "id": "61411ef2b4058d905d35fd9e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1264.949106163377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.9598519017227,
        1283.9383604250315
      ],
      "voteCount": 926,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.86844796337137
      }
    },
    {
      "id": "adbf85de0bd3e5320df879e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1327.8129365244288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.0488611856103,
        1335.5770118632472
      ],
      "voteCount": 6208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.692180674204318
      }
    },
    {
      "id": "28e9944886eb3dd4dac26a98",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1317.4507247600914,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.0810598780663,
        1323.8203896421167
      ],
      "voteCount": 10545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.561776815291573
      }
    },
    {
      "id": "4f66baee99d02f44fb886e04",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1299.7736428320804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.4269249729673,
        1309.1203606911936
      ],
      "voteCount": 4656,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.741655921767673
      }
    },
    {
      "id": "d596a7936c0a2525c489fecf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1244.5862633266238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.5659117896225,
        1252.606614863625
      ],
      "voteCount": 6207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.745211072040778
      }
    },
    {
      "id": "fe6267a491e8b370bf52befc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1330.8684756970988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1318.1024068740687,
        1343.634544520129
      ],
      "voteCount": 2386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.424641471204026
      }
    },
    {
      "id": "dd22701c9f3f2ca80c8dea0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1318.2058870451779,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.3381176044427,
        1326.073656485913
      ],
      "voteCount": 6932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.114137587288138
      }
    },
    {
      "id": "9a8406b0d187d79cb3522ca5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1309.8390709804212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.2129462853425,
        1318.4651956754997
      ],
      "voteCount": 4565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.370252481738227
      }
    },
    {
      "id": "8f88d5f6a4b5ec4fcc191cb0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1313.0250952847525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.0376474042405,
        1327.0125431652646
      ],
      "voteCount": 1956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.930833139762605
      }
    },
    {
      "id": "6362259cf8c440c0bf5b2d74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1343.2598070792164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.666328849928,
        1349.8532853085048
      ],
      "voteCount": 10448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.317043131089648
      }
    },
    {
      "id": "d080e8ac37e934ba6f49904b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1281.7347059171432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.9898475061814,
        1288.479564328105
      ],
      "voteCount": 10827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.84266631698615
      }
    },
    {
      "id": "7f21b118783f8bb143fc9bbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1291.7939193563939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.160967677678,
        1297.4268710351096
      ],
      "voteCount": 16363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.259920539513525
      }
    },
    {
      "id": "c1f6a9927fa9a8bace841ed1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1210.3475916337748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.571858244496,
        1231.123325023053
      ],
      "voteCount": 788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.3612455604525
      }
    },
    {
      "id": "b97bf7155acbe3dc56ac80f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1228.4182486881332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.8637937824903,
        1255.9727035937758
      ],
      "voteCount": 527,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.64574360578692
      }
    },
    {
      "id": "06806cecabecd1d52c630ae6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1316.7919528510652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.680868904938,
        1324.9030367971923
      ],
      "voteCount": 6008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.126223617629346
      }
    },
    {
      "id": "3d7192791a61e616bf93799c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1296.4859099731523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.3250687727586,
        1304.646751173546
      ],
      "voteCount": 5415,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.336988942655687
      }
    },
    {
      "id": "0017355f950d0cbdce36ff8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1298.8438339999475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.9837586122335,
        1306.7039093876617
      ],
      "voteCount": 7250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.082636306741783
      }
    },
    {
      "id": "be48d31066e86c4a49810d2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1302.6759108885235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.6144404964034,
        1306.737381280644
      ],
      "voteCount": 39406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.294082669117353
      }
    },
    {
      "id": "ce1e7db0c11808e12f9bc7df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1295.685872815644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.2069460914363,
        1304.1647995398512
      ],
      "voteCount": 5776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.714816883417633
      }
    },
    {
      "id": "16ac72bbb7635a2209639746",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-72b-instruct",
      "organization": "alibaba",
      "license": "Qwen",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1290.4735454431332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.4641785774413,
        1321.4829123088248
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.3165797928075
      }
    },
    {
      "id": "179c57b7b1c0390cdf0338c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1280.1376331721845,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.2557635163766,
        1305.019502827992
      ],
      "voteCount": 528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.16466854556344
      }
    },
    {
      "id": "c8660a20bf670fb4831db2b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1341.983999612326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.4610113378644,
        1360.5069878867876
      ],
      "voteCount": 873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.31531239318261
      }
    },
    {
      "id": "097ca687f9777800829c07b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1206.8829176201866,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.5889624852302,
        1226.176872755143
      ],
      "voteCount": 836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.90503585365572
      }
    },
    {
      "id": "bbae061f91d4cb23b67ef453",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1286.1191537336283,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.9059040706939,
        1297.3324033965628
      ],
      "voteCount": 2652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.73156732175448
      }
    },
    {
      "id": "0350ce5af12ea22d732e5d78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1184.3557251927646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.8136483721812,
        1197.8978020133477
      ],
      "voteCount": 3370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.73911505354646
      }
    },
    {
      "id": "83782786335f52748a217e4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1274.9537070107826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.1365006498834,
        1307.770913371682
      ],
      "voteCount": 267,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.3541788687571
      }
    },
    {
      "id": "8b0c27591272d2fdfb7d934c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1319.19848446101,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.4923120149715,
        1338.9046569070483
      ],
      "voteCount": 759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 101.090041726083
      }
    },
    {
      "id": "92123159aeb79dd466e02f69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1302.903082651892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.3235773802435,
        1317.4825879235404
      ],
      "voteCount": 1386,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.33365939547371
      }
    },
    {
      "id": "abebab6f52175f4b92d01236",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1283.794649259574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.427818298438,
        1306.16148022071
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.23050632458228
      }
    },
    {
      "id": "9e6824ed43a1c8e8a50c3fd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1187.0531255208723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.4706134367048,
        1205.6356376050396
      ],
      "voteCount": 929,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.8902660359206
      }
    },
    {
      "id": "6d98985b17c755e197a6db8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1309.7524551538222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.5416654675537,
        1343.9632448400907
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.670227011992
      }
    },
    {
      "id": "6dcc2f75885251de2019e8ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1277.4799501008288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.4487736480405,
        1295.511126553617
      ],
      "voteCount": 956,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.6353792783433
      }
    },
    {
      "id": "fbeff7919b97acd0eaa11230",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1269.1377472435001,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.3261764124568,
        1289.9493180745435
      ],
      "voteCount": 619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.74921863597473
      }
    },
    {
      "id": "0d541290734938bef1921d7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1255.1656925439202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.9330775693707,
        1291.3983075184697
      ],
      "voteCount": 221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 341.74579220316645
      }
    },
    {
      "id": "3bf726023367e8266e1d9be1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1319.421727159206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.5303520911311,
        1334.313102227281
      ],
      "voteCount": 1381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.72626019664465
      }
    },
    {
      "id": "433f2fd4f9a2de08ab49173d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1227.2250170097197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1212.4626321070282,
        1241.9874019124113
      ],
      "voteCount": 1540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.73053342163298
      }
    },
    {
      "id": "e7a7787d86b41a7480b1fce9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1263.4837313787598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.5704917234248,
        1275.3969710340946
      ],
      "voteCount": 2227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.94567238906377
      }
    },
    {
      "id": "cae367e8c4ca9a703fd826f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1286.470099023319,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.574964732687,
        1305.3652333139512
      ],
      "voteCount": 804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.94023872850023
      }
    },
    {
      "id": "1c08be5d0915fe9ea1740cf8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1269.9158101289613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.647062877662,
        1289.1845573802607
      ],
      "voteCount": 725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.6519850829413
      }
    },
    {
      "id": "60a5631179009ab86add79fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1250.8337488768525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.9155594819633,
        1268.7519382717417
      ],
      "voteCount": 1024,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.57801714847118
      }
    },
    {
      "id": "41798d950589199d0b0d3771",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1270.2434298221376,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.1206239719068,
        1278.3662356723685
      ],
      "voteCount": 5432,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.175760032909796
      }
    },
    {
      "id": "cb68ef0ddd83292544ef5d7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-coder-32b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1269.4978044276447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.8801050832017,
        1288.1155037720878
      ],
      "voteCount": 822,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.23101510624589
      }
    },
    {
      "id": "1f99bf57636ed26b6810b52b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1397.9261312647386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.8586339183134,
        1410.9936286111638
      ],
      "voteCount": 1950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.45172911367404
      }
    },
    {
      "id": "f82dce3b4b57eea9ff3bd7b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1402.9106969022212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.7456373132268,
        1411.0757564912155
      ],
      "voteCount": 5101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.35491676565305
      }
    },
    {
      "id": "a47a7825e50849fd012708a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1354.3725045474982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.8729125552845,
        1362.872096539712
      ],
      "voteCount": 5000,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.80615344486539
      }
    },
    {
      "id": "a4a537f7195ca0a5d6e07d3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1382.3961767054707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.3690931051667,
        1387.4232603057749
      ],
      "voteCount": 18692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.5786386641209464
      }
    },
    {
      "id": "20d9b1e21e96d7ae76bf2325",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1349.6900612230165,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.6991840250084,
        1355.6809384210246
      ],
      "voteCount": 21983,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.342963513826918
      }
    },
    {
      "id": "05bdb9cf83e652768d938174",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1367.1947640532837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.4014280146575,
        1380.98810009191
      ],
      "voteCount": 1668,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.52704895586702
      }
    },
    {
      "id": "825e3363bf7f7f4c896235af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1411.879908336885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.5468771715296,
        1444.2129395022403
      ],
      "voteCount": 328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.14268150112235
      }
    },
    {
      "id": "e97f3035ac07081480d3a54e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1353.420855318684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.3381678922883,
        1374.50354274508
      ],
      "voteCount": 761,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.7059674113071
      }
    },
    {
      "id": "d00e6b7bbe1548e796dedf39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1387.8145689708103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.1618544984847,
        1395.4672834431358
      ],
      "voteCount": 6011,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.24526007657646
      }
    },
    {
      "id": "79c6448d49b9ceaef1529e38",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1385.0940868626487,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.839921399508,
        1391.3482523257894
      ],
      "voteCount": 9673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.182221772007155
      }
    },
    {
      "id": "945ba18d3d944626ca7962ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1368.833142813545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.9327710890293,
        1378.7335145380607
      ],
      "voteCount": 3681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.515660809785526
      }
    },
    {
      "id": "99de75817d8f7da32af95408",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1339.7819294976498,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.109855932961,
        1347.4540030623389
      ],
      "voteCount": 5991,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.322489587787267
      }
    },
    {
      "id": "28f40f4bb4b33e548062294d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1386.5326504334353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.6127595519924,
        1400.4525413148779
      ],
      "voteCount": 1868,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.44004665817622
      }
    },
    {
      "id": "c79f0a2c44345330d9c065b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1389.7392965742347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.678024684018,
        1397.8005684644518
      ],
      "voteCount": 5699,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.916517271492914
      }
    },
    {
      "id": "1466d21e38546c0a7a26217c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1368.0953439699379,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.649827904979,
        1378.540860034897
      ],
      "voteCount": 2942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.402961207222262
      }
    },
    {
      "id": "7cc926e826d62c4388cabb56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1394.4260046107647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.567596256165,
        1409.2844129653643
      ],
      "voteCount": 1600,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.47095286892682
      }
    },
    {
      "id": "cada44e345f425c63b217d31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1397.6667303034578,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.0480722329353,
        1404.28538837398
      ],
      "voteCount": 8629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.40364551573531
      }
    },
    {
      "id": "8f7e955b6020503ae64a0eb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1362.549352224412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.7983955429772,
        1369.3003089058466
      ],
      "voteCount": 8196,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.864090763928113
      }
    },
    {
      "id": "50f8887a0f120b43d85dffdb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1356.7095962022227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.7178849482284,
        1362.701307456217
      ],
      "voteCount": 10959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.345565168587255
      }
    },
    {
      "id": "945fe8f673369ad9fb64a6a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1310.179104570665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.9560569479609,
        1332.4021521933694
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.56153578440336
      }
    },
    {
      "id": "f43999e084eff8f49be8ecae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1315.1373087532716,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.051989463374,
        1343.2226280431692
      ],
      "voteCount": 470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.33479504355716
      }
    },
    {
      "id": "6b3a2a1eb5e716fcdc05f9d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1384.0906683559465,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.442007900841,
        1392.739328811052
      ],
      "voteCount": 4516,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.471594297655646
      }
    },
    {
      "id": "5fe74903b4e4a72c03cb504f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1364.1950321058634,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.3435105822036,
        1374.046553629523
      ],
      "voteCount": 3306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.264484369402847
      }
    },
    {
      "id": "aef977cca4ed62af16bededa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1372.476008802187,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.022130925937,
        1380.9298866784368
      ],
      "voteCount": 4870,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.604403816993788
      }
    },
    {
      "id": "b8c1dae423be068035d7a023",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1374.2992869824288,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.21604717839,
        1378.3825267864677
      ],
      "voteCount": 32623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.340238455107146
      }
    },
    {
      "id": "5b2855c355337e5e30e5d780",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1365.5957947871625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.8737004069449,
        1376.3178891673797
      ],
      "voteCount": 2808,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.926992130952332
      }
    },
    {
      "id": "0139df43e5445e2e7b458355",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-max",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1375.5727293061823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.5149304520162,
        1412.6305281603481
      ],
      "voteCount": 249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 357.4893081029246
      }
    },
    {
      "id": "1863d07b9b61e5b3ce6f7fd9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1329.2880928520585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.54087447937,
        1352.035311224747
      ],
      "voteCount": 621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.69777182234066
      }
    },
    {
      "id": "247d6a9cfde9aed5ab77feeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1357.0818989583076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.152774405115,
        1371.0110235115003
      ],
      "voteCount": 1553,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.50698702616719
      }
    },
    {
      "id": "2864529ddf9bbf0cc0449500",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1274.5328446413678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.2186098645052,
        1288.8470794182304
      ],
      "voteCount": 1591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.338413038127754
      }
    },
    {
      "id": "c47bb357e13e1eaf6035516d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1331.7234626803443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.8540349169377,
        1339.592890443751
      ],
      "voteCount": 5804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.12093119152156
      }
    },
    {
      "id": "dfda68876e1f3e199b0ce4f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1259.79490979939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.6086945959996,
        1269.9811250027806
      ],
      "voteCount": 6369,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.010306504088824
      }
    },
    {
      "id": "12215086ba3e657c1883d8f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1321.633039311136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.371664752758,
        1342.8944138695138
      ],
      "voteCount": 664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.67561991721517
      }
    },
    {
      "id": "a7f85f68ed00f5f61ff5c576",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1249.1170755265227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1213.5489405145186,
        1284.685210538527
      ],
      "voteCount": 257,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 329.3259897560375
      }
    },
    {
      "id": "f18e0e38468781c7639a4163",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1344.0998525282384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.016737038813,
        1357.1829680176636
      ],
      "voteCount": 1713,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.55804914204742
      }
    },
    {
      "id": "cda4456c9f7774e105da989a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1326.3461073567528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.6449665209448,
        1337.0472481925613
      ],
      "voteCount": 2671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.810137380858585
      }
    },
    {
      "id": "feb666e249d596ddac31aa3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1314.9334971168466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.4813009518502,
        1332.385693281843
      ],
      "voteCount": 1078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.28736586755436
      }
    },
    {
      "id": "cc370582716c1de3f905de13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1255.0439351481552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.069010491542,
        1268.0188598047685
      ],
      "voteCount": 1872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.82415059036657
      }
    },
    {
      "id": "9cd707dbe3bff250bcf00fd0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1325.0485286910982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.1711572357353,
        1348.9259001464611
      ],
      "voteCount": 588,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.41467635838538
      }
    },
    {
      "id": "0ebff326e56e1c9b1cca2a97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1337.0222107347615,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.4296627025042,
        1350.6147587670189
      ],
      "voteCount": 1771,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.09562476992538
      }
    },
    {
      "id": "df4e54e1496c64ec7f2abe40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1316.9896871608626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.2908655422927,
        1331.6885087794321
      ],
      "voteCount": 1265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.243049075686905
      }
    },
    {
      "id": "6a533fb94dc011c488faa6cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1329.2182370794108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.8858143379368,
        1355.550659820885
      ],
      "voteCount": 474,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 180.50342846325523
      }
    },
    {
      "id": "f008587c9f9399e1c06aa054",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1345.9007625332952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.4998675133966,
        1357.3016575531935
      ],
      "voteCount": 2391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.83620997172572
      }
    },
    {
      "id": "4f2c021ccca45fcbc1d7a2d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1289.2856633911429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1278.3540964187232,
        1300.2172303635623
      ],
      "voteCount": 2823,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.107754124226016
      }
    },
    {
      "id": "3516ee30e008fb4303e14006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1295.17877525129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1286.1222457288695,
        1304.2353047737106
      ],
      "voteCount": 4234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.35145287738704
      }
    },
    {
      "id": "781a94721eafa97e229e19fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1232.7370736329567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.2197894119606,
        1265.2543578539528
      ],
      "voteCount": 300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 275.25318439258496
      }
    },
    {
      "id": "6cc92061bc373e7cb257006a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1307.8222512619918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.5449858936895,
        1322.0995166302941
      ],
      "voteCount": 1586,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.06325432901281
      }
    },
    {
      "id": "3944b3459669073046fe0b05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1304.5198629919046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1290.8110280449673,
        1318.2286979388418
      ],
      "voteCount": 1404,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.922079963468256
      }
    },
    {
      "id": "caecbca4e90b1410332c982f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1306.9636118656426,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.6637197544987,
        1320.2635039767865
      ],
      "voteCount": 1789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.046863554847526
      }
    },
    {
      "id": "ef0f5ce0b48b949d6923244a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1315.0216515949323,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.680081200037,
        1321.3632219898275
      ],
      "voteCount": 10187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.468813268743043
      }
    },
    {
      "id": "443d70e80c1d458ef0d616e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen2.5-plus-1127",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1297.2412008161543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.09656403116,
        1312.385837601149
      ],
      "voteCount": 1397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.70649017863574
      }
    },
    {
      "id": "9b2fce609b591c91a7e44eb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1472.1849619553484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.0506286230818,
        1481.3192952876152
      ],
      "voteCount": 4836,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.719885418395126
      }
    },
    {
      "id": "3f5a066de5d1e247dcf29293",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1472.3783478502758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.683165942541,
        1477.0735297580104
      ],
      "voteCount": 20628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.738635808865847
      }
    },
    {
      "id": "7cdb5241f0bb2380bb0ccdf5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1380.8034038669755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.191866324858,
        1386.414941409093
      ],
      "voteCount": 13335,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.197238355636895
      }
    },
    {
      "id": "03cfc9749f6cf9fa46dcca3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1430.164175834801,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.686319212212,
        1433.64203245739
      ],
      "voteCount": 44195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.1486701411783797
      }
    },
    {
      "id": "b5987f85f4cd379cb834aad7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1414.9095594103462,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.2099124982492,
        1418.6092063224435
      ],
      "voteCount": 67463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.563070154612732
      }
    },
    {
      "id": "5a22db4964bcd5a4a9737c55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1450.6516751776398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.393420041964,
        1458.9099303133157
      ],
      "voteCount": 5735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.75335388694688
      }
    },
    {
      "id": "f3400b51f048e51549f3810b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1458.3712666498122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.7583902633594,
        1473.9841430362653
      ],
      "voteCount": 1883,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.45555697369523
      }
    },
    {
      "id": "9f5a1dc33f7e1fb9ef8ee3a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1426.7059513573156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.5487623196416,
        1441.8631403949898
      ],
      "voteCount": 1694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.805503650374845
      }
    },
    {
      "id": "5870ce85fb0c9916c7f2a46c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1450.3641968521679,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.9858642911852,
        1454.7425294131508
      ],
      "voteCount": 24874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.990238581055326
      }
    },
    {
      "id": "100d381e60521fb9559f03cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1448.18995642773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.7898035786122,
        1451.5901092768477
      ],
      "voteCount": 50840,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.009544013613664
      }
    },
    {
      "id": "8d8c5c9f4518b3dd254cee80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1431.9711207822495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.9318518948016,
        1437.0103896696971
      ],
      "voteCount": 17548,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.610569605275576
      }
    },
    {
      "id": "762817643f9fe2c8cc756fa1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1377.703320542939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.7053225095574,
        1382.7013185763208
      ],
      "voteCount": 17269,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.502733859105516
      }
    },
    {
      "id": "c3c3780d88de011251b288ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1433.733980837449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.9634227197719,
        1441.504538955126
      ],
      "voteCount": 6382,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.718396650490728
      }
    },
    {
      "id": "e84ff2391db6278924fc9d79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1444.8961344196541,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.6148163495902,
        1450.177452489718
      ],
      "voteCount": 15055,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.2608667329520244
      }
    },
    {
      "id": "c86d366157479308be526a32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1433.6774277432016,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.8381032305776,
        1442.5167522558256
      ],
      "voteCount": 4802,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.339579697839394
      }
    },
    {
      "id": "f60352cefc33ef5c38db6616",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1456.7554648364285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.324886371399,
        1465.1860433014576
      ],
      "voteCount": 5587,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.50199535450791
      }
    },
    {
      "id": "30dac1e6a3f574c0c634a6dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1462.718614941316,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.82692133367,
        1466.610308548962
      ],
      "voteCount": 33847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 3.9425853152983783
      }
    },
    {
      "id": "0db76aeb8dc4c9a348cd524a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1397.400531599158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.8163246385207,
        1401.9847385597955
      ],
      "voteCount": 21265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.470565855020665
      }
    },
    {
      "id": "9385ebccaead171eb94fe8c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1415.886361330532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.6576989175644,
        1420.1150237435
      ],
      "voteCount": 26216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.654894569353995
      }
    },
    {
      "id": "a106478a743977f31b1f86b1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1380.8337637072593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.9282613893822,
        1398.7392660251367
      ],
      "voteCount": 1244,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.45970325866368
      }
    },
    {
      "id": "83ebc7a319c30aaaae219a72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1384.400907647789,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.5946514391221,
        1400.2071638564557
      ],
      "voteCount": 1698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.03720253048907
      }
    },
    {
      "id": "0222aaa1c8374c0d37ab796c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1434.7020636701773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.2602569692754,
        1439.143870371079
      ],
      "voteCount": 24643,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.135977681679467
      }
    },
    {
      "id": "8b73d5a2b89b134792f8e278",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1419.7260577068055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.7776167408456,
        1427.6744986727651
      ],
      "voteCount": 5844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.446281670131693
      }
    },
    {
      "id": "663fb3508e5fd7fe906fc388",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1437.512974214957,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.3557421602018,
        1442.670206269712
      ],
      "voteCount": 16638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.923682826772444
      }
    },
    {
      "id": "11c6498b65ea820a716ce653",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1423.1819635491654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.56127191444,
        1425.8026551838905
      ],
      "voteCount": 95473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 1.7878688708882737
      }
    },
    {
      "id": "ccdcab368c5d61d67bf8019f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1417.866911121268,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.0745055091622,
        1424.6593167333738
      ],
      "voteCount": 8258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.010222197573645
      }
    },
    {
      "id": "667a8c4a4c5534465449b439",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1425.0760794703936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.5344834765854,
        1438.6176754642017
      ],
      "voteCount": 2463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.73572505103343
      }
    },
    {
      "id": "c7a2d8f3f715be070c9c9f6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1439.849705207527,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.2671761148008,
        1453.4322343002534
      ],
      "voteCount": 2003,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.024749233527864
      }
    },
    {
      "id": "90c958d3ae0ac480190e4937",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1446.0820593501596,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.5556380617068,
        1453.6084806386127
      ],
      "voteCount": 6975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.74622534181985
      }
    },
    {
      "id": "3c8f6a5c1f2d3c2fa2ef8e6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1368.3874234909601,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.354652996562,
        1377.4201939853583
      ],
      "voteCount": 4623,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.23957241580628
      }
    },
    {
      "id": "ca90739220d62e03667e1c45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1407.612145486438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.1536965767884,
        1413.0705943960875
      ],
      "voteCount": 18628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.75608066882004
      }
    },
    {
      "id": "91f332e0f6f90ad5850472a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1386.063358828009,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.9959588939553,
        1392.130758762063
      ],
      "voteCount": 27214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.583167145106701
      }
    },
    {
      "id": "ddf1624674783b1d28d44476",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1395.6771798258696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.9917777184198,
        1409.3625819333195
      ],
      "voteCount": 1878,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.754975540450964
      }
    },
    {
      "id": "9d7de29f8eb2e2fdb028fd39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1389.1639268727051,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.5205668836488,
        1416.8072868617612
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.9232182753096
      }
    },
    {
      "id": "51b042221f56fc135535dc20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1378.3377435267812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.1518611285464,
        1397.5236259250162
      ],
      "voteCount": 1012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.82247281057224
      }
    },
    {
      "id": "681aecb53742caef75d0c11b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1420.2801198222787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.3092627479941,
        1427.2509768965635
      ],
      "voteCount": 8646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.649581999508563
      }
    },
    {
      "id": "830a593ee90435661a1a8912",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1420.9601467561324,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.3194504496698,
        1426.6008430625952
      ],
      "voteCount": 16575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.282648938038582
      }
    },
    {
      "id": "07c4036ab4c11510bca49346",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1413.576652970387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.5169596478324,
        1421.6363462929417
      ],
      "voteCount": 6367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.909892695893664
      }
    },
    {
      "id": "4e731db861d2f42924556eba",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1360.1548797307944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.5109616508494,
        1367.7987978107394
      ],
      "voteCount": 6675,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.210232971429695
      }
    },
    {
      "id": "8e99a21d5639d4876f9f5d4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1404.6151477336593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.7333796333335,
        1416.496915833985
      ],
      "voteCount": 2572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.75072928789329
      }
    },
    {
      "id": "4463ac0b856807623b141c7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1417.179973654509,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.9869281768692,
        1425.3730191321486
      ],
      "voteCount": 6319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.474089228045447
      }
    },
    {
      "id": "e036ee0046f27670c4a0dd79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1403.5451209781224,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.2995525710887,
        1415.7906893851564
      ],
      "voteCount": 2304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.03567696822257
      }
    },
    {
      "id": "9ddf439938483b1a1147453a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1427.1943955564861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.4340678275078,
        1439.9547232854645
      ],
      "voteCount": 2346,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.38649204666262
      }
    },
    {
      "id": "4d301997c57e69afae42bd1d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1438.6930681061676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.5679433058563,
        1444.8181929064792
      ],
      "voteCount": 12759,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.766381880051306
      }
    },
    {
      "id": "384986550ee482b5d5ce3c86",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1379.2477051948706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.1109103866813,
        1386.38450000306
      ],
      "voteCount": 8096,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.258983764140869
      }
    },
    {
      "id": "fb860bfd93eb8c95dce52ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1380.7660376293943,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.980088551273,
        1387.5519867075159
      ],
      "voteCount": 9274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.987400370606553
      }
    },
    {
      "id": "7c2c54e0aa00b0b938a1d834",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1366.3021144956174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.6102421028024,
        1387.9939868884323
      ],
      "voteCount": 794,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.48922866785944
      }
    },
    {
      "id": "ac12d8fbfec0211dee5fb3c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1360.6242445130829,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.2299784357124,
        1384.0185105904534
      ],
      "voteCount": 705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.46975194697495
      }
    },
    {
      "id": "80db476e88eea70d9f23d7f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1411.1116397727226,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.5862437989497,
        1418.6370357464955
      ],
      "voteCount": 7146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.742207896906377
      }
    },
    {
      "id": "1738737117799c8a04a8263f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1394.4265862248806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.4494862053064,
        1406.4036862444548
      ],
      "voteCount": 2390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.34282510230407
      }
    },
    {
      "id": "9e20454f5489d3a49ae4fdef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1410.5294975334732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.6872464070639,
        1418.3717486598825
      ],
      "voteCount": 6756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.00977795163655
      }
    },
    {
      "id": "2d596a8b415c05324a65b379",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1403.0972927931368,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.5996792798837,
        1407.59490630639
      ],
      "voteCount": 38226,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.265845153831866
      }
    },
    {
      "id": "0f74db004b608089251ea912",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1406.5894258310268,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.7582254716358,
        1418.4206261904178
      ],
      "voteCount": 2401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.438579320436965
      }
    },
    {
      "id": "e8b9ab54dab2c8eeaaa0f102",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-no-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1412.7221386531403,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.823408765226,
        1436.6208685410543
      ],
      "voteCount": 677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.6803105056522
      }
    },
    {
      "id": "41c2ec36c996dca91ed88f07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1449.498176791063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.1700167282481,
        1478.8263368538778
      ],
      "voteCount": 413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 223.9099812905628
      }
    },
    {
      "id": "05b5fab9cb390f0ff1c9cfe9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1441.5487455961147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.9103067044744,
        1456.1871844877553
      ],
      "voteCount": 1611,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.781905569295034
      }
    },
    {
      "id": "e85a2791c4c5ba3808c3629c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1373.8373774553493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1355.6403521250884,
        1392.0344027856102
      ],
      "voteCount": 1077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.19947429511336
      }
    },
    {
      "id": "6ec5ac0f0502226fa4443d00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1405.142297812048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.125787156378,
        1414.1588084677176
      ],
      "voteCount": 4374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.163174772524663
      }
    },
    {
      "id": "67389a06cdffa0cfac5ce90d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1380.7160692660407,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.3523246662567,
        1390.0798138658247
      ],
      "voteCount": 6352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.824587486829067
      }
    },
    {
      "id": "1b70a3d0cf785f5b5dd126ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1464.3003930350908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.7619952225657,
        1492.838790847616
      ],
      "voteCount": 411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.01324489501548
      }
    },
    {
      "id": "3ac53f9528cb6d688781bed5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1395.0738732989491,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.636968344465,
        1435.5107782534333
      ],
      "voteCount": 203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 425.6568555386792
      }
    },
    {
      "id": "600279b1818bef86f29f5b24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1428.0107014790972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.9767796302096,
        1441.0446233279845
      ],
      "voteCount": 2010,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.22359491340536
      }
    },
    {
      "id": "0ae3cce3666f1f8a4fb8135a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1418.2132098387513,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.7715210958531,
        1427.6548985816491
      ],
      "voteCount": 3845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.20615434884678
      }
    },
    {
      "id": "8d50dd7513732e058e6f2ff7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1402.041246269723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.9875025362794,
        1417.0949900031665
      ],
      "voteCount": 1546,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.99196398290223
      }
    },
    {
      "id": "088d4475aaa0ed66a567872d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1352.0811807656264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.312682534262,
        1366.8496789969909
      ],
      "voteCount": 1541,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.77752910817435
      }
    },
    {
      "id": "2321e74760571f6d7184bf10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1389.577837738269,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.0577494861147,
        1414.0979259904227
      ],
      "voteCount": 539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.51208458998425
      }
    },
    {
      "id": "6adc35dac76c33c790eae019",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1410.468018310751,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.2981097067413,
        1425.6379269147606
      ],
      "voteCount": 1514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.90592058785229
      }
    },
    {
      "id": "ee6a36094135f8b65db8f08a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1426.1157326815944,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.191705933312,
        1451.0397594298768
      ],
      "voteCount": 492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.71125042461057
      }
    },
    {
      "id": "b82e978bd0f5331fa2bc1cb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1433.1652350810687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.2579586433746,
        1459.0725115187627
      ],
      "voteCount": 522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.72189700521534
      }
    },
    {
      "id": "611316db2236a703f4f28572",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1432.711175502848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.9162532534897,
        1443.5060977522062
      ],
      "voteCount": 2992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.33492009388049
      }
    },
    {
      "id": "e49af9688937dc333cdbb587",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1378.4335828322505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.757405972179,
        1392.109759692322
      ],
      "voteCount": 1868,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.68926682237868
      }
    },
    {
      "id": "b1bace1a190dd374a48cebc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1385.9760264541494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.5111872842474,
        1398.4408656240514
      ],
      "voteCount": 2100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.44614891991668
      }
    },
    {
      "id": "3b9c619080d9218c58e47223",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1374.2938155813974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.5158229273247,
        1405.07180823547
      ],
      "voteCount": 403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 246.5950765139219
      }
    },
    {
      "id": "1bde491deb13a7f574ef35cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1347.546958354939,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.328944402264,
        1389.7649723076145
      ],
      "voteCount": 199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 463.9801662083738
      }
    },
    {
      "id": "e9d80e672cc28d598d3f119b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1401.288826894212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.946574775838,
        1415.6310790125858
      ],
      "voteCount": 1624,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.547416600924194
      }
    },
    {
      "id": "543fe1e8accf17e68f17890c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1398.4316714951658,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.9916577662268,
        1422.8716852241048
      ],
      "voteCount": 490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.49152000614106
      }
    },
    {
      "id": "5dcad200045c60938b7e9af8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1394.2148460822334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.6829475957493,
        1409.7467445687175
      ],
      "voteCount": 1401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.79902554073408
      }
    },
    {
      "id": "373029b487f03bfa512078db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1399.6609149392239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.1307368706362,
        1406.1910930078113
      ],
      "voteCount": 8993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.100789465122368
      }
    },
    {
      "id": "9d5413672d03571e99a3b443",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1402.8563104172852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.4732280761532,
        1429.2393927584171
      ],
      "voteCount": 438,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.19861914676852
      }
    },
    {
      "id": "2653c3353d599577ac9c1355",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b-thinking-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1382.374566076799,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.9451735046935,
        1426.8039586489049
      ],
      "voteCount": 154,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 513.859712277118
      }
    },
    {
      "id": "0819c47c7eaddabaaef8b021",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1394.0904544115897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.602062573603,
        1410.5788462495761
      ],
      "voteCount": 1254,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.77182864447776
      }
    },
    {
      "id": "f1d45e4d8cb18ee0d9d7c086",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1433.3370731310363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.356554765783,
        1442.3175914962897
      ],
      "voteCount": 4339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.99455281784875
      }
    },
    {
      "id": "9d3767a52e622ca91356127d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1323.6392017760188,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.5905489088382,
        1333.6878546431994
      ],
      "voteCount": 3579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.285697480638422
      }
    },
    {
      "id": "8c416b8a97e9cc540e41f089",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1387.3515534908988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.5029874193715,
        1393.200119562426
      ],
      "voteCount": 13454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.904358133100528
      }
    },
    {
      "id": "eaa88eeadd669d6f9e92d335",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1345.5044748808025,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.958892714928,
        1352.050057046677
      ],
      "voteCount": 18074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.153222744289058
      }
    },
    {
      "id": "9e17429d5dc6158786caf2da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1384.9803139621586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.0131002313503,
        1400.947527692967
      ],
      "voteCount": 1319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.36851420920473
      }
    },
    {
      "id": "f15e9aa4e6d5d00bf7efe5e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1375.1144123935114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.313976421809,
        1407.9148483652139
      ],
      "voteCount": 326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.0677164982191
      }
    },
    {
      "id": "f2b1bc8e0dacd731760b4b4e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1381.6344190333696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.3766184891142,
        1403.8922195776252
      ],
      "voteCount": 725,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.96394525930108
      }
    },
    {
      "id": "f2999d689575901ddb84c9f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1402.8334359994642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.9140083021223,
        1410.7528636968063
      ],
      "voteCount": 5751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.326436903492795
      }
    },
    {
      "id": "982d2a5cb9e63388f24acc82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1391.61798704153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3462313938653,
        1397.8897426891945
      ],
      "voteCount": 10494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.239578436221635
      }
    },
    {
      "id": "3753fa4b7efe68e20db56258",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1369.0056623485207,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.5434543122078,
        1378.4678703848333
      ],
      "voteCount": 3963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.30713020796666
      }
    },
    {
      "id": "c50cb0ee0a700b06cd24fde7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1324.4544887301593,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.8685622751416,
        1333.0404151851772
      ],
      "voteCount": 4743,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.190140134745302
      }
    },
    {
      "id": "da0a00ac067bb416d5d3e77c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1364.332295197204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.4012867692502,
        1378.2633036251577
      ],
      "voteCount": 1735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.520649804766286
      }
    },
    {
      "id": "9a6771c6ef4d7ea1ac780c20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1382.7676087258365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.8182040163485,
        1391.7170134353246
      ],
      "voteCount": 4592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.849330525879473
      }
    },
    {
      "id": "f597194afee202b06042b183",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1400.89874907287,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.093391486685,
        1415.704106659055
      ],
      "voteCount": 1501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.06129454622048
      }
    },
    {
      "id": "82932963bdd9a263bf0b8c7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1381.7106988630003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.5219584813315,
        1396.8994392446693
      ],
      "voteCount": 1549,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.054746165430316
      }
    },
    {
      "id": "bcb783159ffa4ef5ad8ad9a6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1416.4809029297214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.4961568288945,
        1423.4656490305485
      ],
      "voteCount": 8097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.700039326258254
      }
    },
    {
      "id": "92f04895d6ac5fc39c3d0bd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1345.3089042160204,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.4626610085272,
        1353.1551474235134
      ],
      "voteCount": 6167,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.026081586371788
      }
    },
    {
      "id": "0c6990c543589705a1132a88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1356.8314813947152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.0980097686343,
        1364.5649530207963
      ],
      "voteCount": 6191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.568716517074185
      }
    },
    {
      "id": "30b6264d20d053627cd69e84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1308.5670676270618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.3139307476395,
        1332.820204506484
      ],
      "voteCount": 646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.12272653379924
      }
    },
    {
      "id": "ea8f2fa2768633e1b2b23237",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1317.8519290779514,
      "unit": "Arena rating",
      "confidenceInterval": [
        1289.9382915838667,
        1345.765566572036
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 202.83209960594658
      }
    },
    {
      "id": "7fdbb6eb294d2251ae37307e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1378.275150646584,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.5057347811708,
        1387.0445665119971
      ],
      "voteCount": 4584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.01912768302512
      }
    },
    {
      "id": "8d033cdf651047bbe1716644",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1393.2327995043108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.332578424594,
        1407.133020584028
      ],
      "voteCount": 1604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.297596586000786
      }
    },
    {
      "id": "6d49f8cf53e0aba041a2555e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1372.0528574194643,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.8826098893019,
        1381.223104949627
      ],
      "voteCount": 4282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.891016847932026
      }
    },
    {
      "id": "2f6f4147fca9a7613902fdd4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1374.8204776256082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.1308228916446,
        1379.510132359572
      ],
      "voteCount": 26268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.725132703574103
      }
    },
    {
      "id": "297c5ff3a7f847d8f3e48b97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1354.1579221957982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.1670755030636,
        1367.1487688885322
      ],
      "voteCount": 1858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.93177323286562
      }
    },
    {
      "id": "6ae2b2c07abe32ac5ea9a528",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-235b-a22b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1369.1487945442125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.5646240732547,
        1397.7329650151705
      ],
      "voteCount": 421,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.69388522695272
      }
    },
    {
      "id": "ee8e7aa4111a648109b8325e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1437.9479406936557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.3933338442994,
        1454.502547543012
      ],
      "voteCount": 1329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.34138896931722
      }
    },
    {
      "id": "c1dad397d61bc79b72a8e286",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1439.9243126615008,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.087488964212,
        1448.7611363587894
      ],
      "voteCount": 4660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.32807240735974
      }
    },
    {
      "id": "848d9878cf60f357ad8ce19d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1321.6168406481684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1310.6652790995472,
        1332.5684021967895
      ],
      "voteCount": 2984,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.22165457225092
      }
    },
    {
      "id": "c342a8efdbdadebbc2960a64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1393.0281154609852,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.738434238573,
        1399.317796683397
      ],
      "voteCount": 11056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.298194442811889
      }
    },
    {
      "id": "fd00ff294e8fb131922144af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1359.4761545798794,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.73728802927,
        1366.2150211304888
      ],
      "voteCount": 16706,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.821634568170614
      }
    },
    {
      "id": "61b6eeab04c80574061e5cf4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1393.4284469080264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.2800265360456,
        1410.576867280007
      ],
      "voteCount": 1145,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.55121009497816
      }
    },
    {
      "id": "3d757c44f841ff51eadcf14e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1419.8141185990655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.3154166867434,
        1453.3128205113878
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 292.1189793225081
      }
    },
    {
      "id": "03a3ec54131f13e34eaf61d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1358.4479636910455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.5298875407007,
        1385.3660398413904
      ],
      "voteCount": 486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.62178600806647
      }
    },
    {
      "id": "79152241c270091c619439be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1416.2624518584612,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.1303523970716,
        1424.394551319851
      ],
      "voteCount": 5625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.21508539768315
      }
    },
    {
      "id": "54595afd79fde693d6408691",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1407.775852584032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.4708967356655,
        1414.0808084323983
      ],
      "voteCount": 11072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.34827395147417
      }
    },
    {
      "id": "22d9b0cd3ff93712d5fc8e62",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1397.1438999139755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.7956154813858,
        1406.492184346565
      ],
      "voteCount": 4177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.749279873005847
      }
    },
    {
      "id": "81ff36459a2cf20b6f1f28bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1333.2270405835343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.001928299493,
        1342.4521528675755
      ],
      "voteCount": 4145,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.15374435220205
      }
    },
    {
      "id": "91c45fffaa598cd75042febc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1382.3334849483858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.0941649262027,
        1397.572804970569
      ],
      "voteCount": 1493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.45538572154925
      }
    },
    {
      "id": "1fa88481e7e144c5ff353049",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1393.8144657225243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.9748117606568,
        1403.6541196843918
      ],
      "voteCount": 3683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.203651687667584
      }
    },
    {
      "id": "9b097179d53b49f95968ba7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1400.4301913765892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.8843015506363,
        1416.976081202542
      ],
      "voteCount": 1211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.26627745110154
      }
    },
    {
      "id": "1a959f732dc9e4ee53b3cc1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1399.084061818039,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.7250062031512,
        1415.4431174329268
      ],
      "voteCount": 1347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.66590378876808
      }
    },
    {
      "id": "1a559fbbc5381310fc9c5ba1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1429.6241160078832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.5633235107475,
        1436.684908505019
      ],
      "voteCount": 8199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.978088016728814
      }
    },
    {
      "id": "c86b5cac27fcef2a9ff20dd5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1343.6712337886556,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.1513319446733,
        1352.1911356326382
      ],
      "voteCount": 5100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.896135770102752
      }
    },
    {
      "id": "6ac5bef1a2e4103d4e77679c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1366.8599021724149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.9715258989227,
        1374.7482784459073
      ],
      "voteCount": 5966,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.198658670237844
      }
    },
    {
      "id": "2007f97be88e93fa6ebfb96a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1324.6001516344306,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.9684544394988,
        1348.2318488293622
      ],
      "voteCount": 704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.37631102655845
      }
    },
    {
      "id": "be9fb703081cad1b41163e0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1313.5204309934672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.4664593596044,
        1339.57440262733
      ],
      "voteCount": 566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.70616023302222
      }
    },
    {
      "id": "7c5c797ef1058d4fe64a0376",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1382.1551873368194,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.5218475782112,
        1390.7885270954278
      ],
      "voteCount": 4882,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.40266936770046
      }
    },
    {
      "id": "89310623a9fe73c1497d987a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1380.8137426817652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.7590330399084,
        1395.8684523236223
      ],
      "voteCount": 1427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.99953454653082
      }
    },
    {
      "id": "b4a185001228e771749ce9fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1383.2756082449246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.8299686232017,
        1392.7212478666474
      ],
      "voteCount": 4073,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.22557966333695
      }
    },
    {
      "id": "80627ac0a6b9a2f02b0e4f93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1383.5048929129096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.62872590813,
        1388.3810599176893
      ],
      "voteCount": 23746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.189576868665931
      }
    },
    {
      "id": "a7a9231d6da145e7daddbee9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1365.818446133168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.5316717928274,
        1382.1052204735086
      ],
      "voteCount": 1227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.05163657728464
      }
    },
    {
      "id": "27e038bff88b628032f0e37d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b-instruct-2507",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1386.9432841688663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.6565998099425,
        1411.2299685277903
      ],
      "voteCount": 633,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.54662504059337
      }
    },
    {
      "id": "d1cf62662dea5b915049cb2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1371.1721348432966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.3761625326952,
        1387.9681071538982
      ],
      "voteCount": 1253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.43686318821985
      }
    },
    {
      "id": "17089385715cfa4efef0791f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1386.8533747407587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.04658578114,
        1395.6601637003769
      ],
      "voteCount": 4531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.19012448120985
      }
    },
    {
      "id": "ee899130636ffc3c95f87d77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1284.745389664904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.35021041547,
        1295.1405689143382
      ],
      "voteCount": 3366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.12987374633391
      }
    },
    {
      "id": "3a1f4e42f47ef8a7e2f00f41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1346.4032489712076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.4589228214627,
        1352.3475751209528
      ],
      "voteCount": 13396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.198331942071457
      }
    },
    {
      "id": "67d3ec7893d771d9d89851e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1275.9939927011542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1269.3082309874233,
        1282.6797544148849
      ],
      "voteCount": 18355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.636050724269406
      }
    },
    {
      "id": "506daa9cbfab1476f1a96b60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1343.8170450966263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.2864101333932,
        1360.3476800598596
      ],
      "voteCount": 1315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.13492687090402
      }
    },
    {
      "id": "a8599a59d9ebbfa28e46930b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1366.542598257327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.2815904596291,
        1398.8036060550244
      ],
      "voteCount": 322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 270.9316102821198
      }
    },
    {
      "id": "b93365bead302dc7f991f78a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1302.7846451192108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.708681781802,
        1324.8606084566195
      ],
      "voteCount": 727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.8653863082564
      }
    },
    {
      "id": "1449a03dfb91250e11d28d92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1362.3671127274843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.3039163763624,
        1370.4303090786063
      ],
      "voteCount": 5814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.924595168509498
      }
    },
    {
      "id": "135ca4c5221bca8e6283e4fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1345.329168513419,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.979076699327,
        1351.6792603275117
      ],
      "voteCount": 10694,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.496966889291562
      }
    },
    {
      "id": "1cecb9429735eafb33919076",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1329.6843488332438,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.1915267267393,
        1339.1771709397483
      ],
      "voteCount": 4014,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.458190169914864
      }
    },
    {
      "id": "99e10ef97d2dce12802eefb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1271.125693927518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1262.263753992222,
        1279.9876338628135
      ],
      "voteCount": 4573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.443790518779227
      }
    },
    {
      "id": "4c7120f5d2afb185274b9231",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1322.5948519015417,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.7211014611173,
        1336.468602341966
      ],
      "voteCount": 1769,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.106212318682516
      }
    },
    {
      "id": "519c7210c12224fad9a2f164",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1332.8075560057982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.702461045732,
        1341.912650965864
      ],
      "voteCount": 4612,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.581060243368196
      }
    },
    {
      "id": "b29e40829d5c995b0e491ed6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1367.7899821655787,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.3486099528336,
        1382.2313543783239
      ],
      "voteCount": 1579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.29011246028677
      }
    },
    {
      "id": "429834c1727b491840d3d141",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1336.4421059829046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.4957702298877,
        1351.3884417359218
      ],
      "voteCount": 1622,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.15315557685683
      }
    },
    {
      "id": "dbb7b68419f8c67faa7fb37e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1371.3547236564327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.437779605626,
        1378.2716677072394
      ],
      "voteCount": 8314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.454673402784076
      }
    },
    {
      "id": "58190ea108783f83ad37c5ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1304.894419931203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.9183650305067,
        1312.8704748318992
      ],
      "voteCount": 5970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.560753283676576
      }
    },
    {
      "id": "4ae1effa488c0e9ce6328847",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1311.390226117043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.5484044878363,
        1319.23204774625
      ],
      "voteCount": 6129,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.008024382045843
      }
    },
    {
      "id": "93ee4d835b5314dd3d70b160",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1250.6834629652412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.4601785242967,
        1273.9067474061858
      ],
      "voteCount": 665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.39482535115872
      }
    },
    {
      "id": "cb038d22bdc6319d5d07e00e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1266.8590114595293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1238.3864091549785,
        1295.33161376408
      ],
      "voteCount": 440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 211.03677530679016
      }
    },
    {
      "id": "a860deae1ff16214ca1da708",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1339.6689120279993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.772454477603,
        1348.5653695783956
      ],
      "voteCount": 4460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.60335946324184
      }
    },
    {
      "id": "109ff6905a24f44104bb514e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1352.6640107212766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.062609099951,
        1366.2654123426023
      ],
      "voteCount": 1708,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.158299932308225
      }
    },
    {
      "id": "f2306ea7efe03701f22db1e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1320.740045038107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.6818361198798,
        1329.7982539563338
      ],
      "voteCount": 4523,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.359372216678654
      }
    },
    {
      "id": "df2507e04ec2756623ecf63a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1327.3568838410831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.6345304342399,
        1332.0792372479264
      ],
      "voteCount": 26495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.805248146612655
      }
    },
    {
      "id": "e4c622615529ead8033ecb11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1306.4851251989057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.474263090688,
        1319.4959873071232
      ],
      "voteCount": 1908,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.06725171362446
      }
    },
    {
      "id": "df4c123796dd8a9ac64edf64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-30b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1324.199546541273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.2440147602751,
        1354.155078322271
      ],
      "voteCount": 410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 233.5919571617938
      }
    },
    {
      "id": "ed7bd6c4740bdb9972eacd0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1364.8676462961353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.0738439406985,
        1403.6614486515718
      ],
      "voteCount": 187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 391.76759961226145
      }
    },
    {
      "id": "52fd71990224f254a14ab8e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1407.6735330940583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.3003267934587,
        1432.0467393946574
      ],
      "voteCount": 513,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.64260144385295
      }
    },
    {
      "id": "96a2d08d32b72d3d40fc166d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1305.0097058000122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.3582652499467,
        1327.6611463500776
      ],
      "voteCount": 616,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.5658620701906
      }
    },
    {
      "id": "cdbf8a69ebfd270ec2047987",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1365.6472450052286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.234364544524,
        1378.0601254659332
      ],
      "voteCount": 2230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.1096584718573
      }
    },
    {
      "id": "57a1b020d6f1ea4746e4d5b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1307.3438321831889,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.7281650093953,
        1321.9594993569822
      ],
      "voteCount": 2544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.60849065577262
      }
    },
    {
      "id": "36d570c37fa9564237de4514",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1397.9421150240087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.461391740329,
        1435.4228383076884
      ],
      "voteCount": 236,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 365.6956076946655
      }
    },
    {
      "id": "31b5e108ed75d2f5b5b024b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1333.014832725145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.7387760136005,
        1374.2908894366897
      ],
      "voteCount": 172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 443.50673459693456
      }
    },
    {
      "id": "81e2c8284b51754db9771aee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1382.1225530622391,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.2853478609995,
        1402.9597582634783
      ],
      "voteCount": 729,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.02714433890537
      }
    },
    {
      "id": "483f298b3ee5eba73eb77608",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1367.5233549780119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.353132775955,
        1383.6935771800688
      ],
      "voteCount": 1207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.06687205790436
      }
    },
    {
      "id": "7a17d0285584ad126cbd8452",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1339.7197019675027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.2643935726896,
        1366.1750103623158
      ],
      "voteCount": 437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.19207205719943
      }
    },
    {
      "id": "5727f504b566a1b13f64b8df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1286.3847829342521,
      "unit": "Arena rating",
      "confidenceInterval": [
        1265.673338989293,
        1307.0962268792114
      ],
      "voteCount": 704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.66692923384632
      }
    },
    {
      "id": "550109bf2edbeb9862b73124",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1326.0651535519546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.4775439853463,
        1358.6527631185627
      ],
      "voteCount": 285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 276.44505559838586
      }
    },
    {
      "id": "b949b519887686e726dd2007",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1378.3194762914704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.8688144968976,
        1398.7701380860435
      ],
      "voteCount": 798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.8725891275943
      }
    },
    {
      "id": "424d2dea6505d2f79003d3ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1425.6152142971614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.5525806980359,
        1457.6778478962872
      ],
      "voteCount": 282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 267.60991625729014
      }
    },
    {
      "id": "c82c41d16fcf7dd76d818988",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1378.5981943282734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.4087394844053,
        1417.7876491721415
      ],
      "voteCount": 212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 399.7995143631582
      }
    },
    {
      "id": "7c59774f36457d05bf1ef4b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1398.4269155851998,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.1161168710282,
        1417.7377142993712
      ],
      "voteCount": 843,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.07430546186839
      }
    },
    {
      "id": "40dc9f4d56a290bf500f4f6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1308.0558445012102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.0566236473164,
        1325.0550653551036
      ],
      "voteCount": 1121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.22494008857667
      }
    },
    {
      "id": "cf8d5e246ece070773e6bf78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1331.5256713276299,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.547423262829,
        1350.5039193924308
      ],
      "voteCount": 858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.75966694445488
      }
    },
    {
      "id": "11a43f380d23510b432b6497",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1355.1843330415725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.4997299500005,
        1379.8689361331444
      ],
      "voteCount": 504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.61933141283723
      }
    },
    {
      "id": "add8164259eeb32c19ab63f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1398.7600971061,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.6666705382067,
        1428.853523673993
      ],
      "voteCount": 316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 235.7475024119978
      }
    },
    {
      "id": "9ba16a4065d4e160cce3ff39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1338.1079881858263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.7475842571039,
        1361.4683921145488
      ],
      "voteCount": 590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.05761331432583
      }
    },
    {
      "id": "b5e2d4b1d8c5380dc2fc3142",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1347.2821374919272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.8243208377846,
        1356.7399541460697
      ],
      "voteCount": 3926,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.28550169053055
      }
    },
    {
      "id": "f2c036a14e1da0f60e79e271",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1327.928418393201,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.2781704533413,
        1353.5786663330605
      ],
      "voteCount": 412,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.27223018295683
      }
    },
    {
      "id": "34f623cf7ce027e5dd4fa541",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1406.1947068878674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.6004744781767,
        1422.7889392975578
      ],
      "voteCount": 1354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.6833271213009
      }
    },
    {
      "id": "1eac4a351056da9056393878",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1457.0799450256532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.0839413207293,
        1466.0759487305768
      ],
      "voteCount": 4849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.06701813983766
      }
    },
    {
      "id": "53ecb7ffc65c18afacc3019c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1365.5177269829335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.8658781781294,
        1376.1695757877374
      ],
      "voteCount": 3280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.536144536856597
      }
    },
    {
      "id": "6e5301a45e18e421a8dad1c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1399.7340303701317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.5039657163952,
        1405.9640950238681
      ],
      "voteCount": 12374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.103897347706924
      }
    },
    {
      "id": "f3de511a87d3943f83f42f14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1364.485847621777,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.743798450737,
        1371.2278967928173
      ],
      "voteCount": 18418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.832803407875533
      }
    },
    {
      "id": "fea910153ef04b663f0f70ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1379.1071086775503,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.5169329797893,
        1395.6972843753113
      ],
      "voteCount": 1319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.64828325111293
      }
    },
    {
      "id": "b1557b3561bbff15d763f303",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1428.9314891320664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.538654976196,
        1460.3243232879367
      ],
      "voteCount": 408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.5457765755527
      }
    },
    {
      "id": "f011f0b8eed77d14f033b7d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1348.2608510360374,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.8791597930701,
        1374.6425422790044
      ],
      "voteCount": 543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.17951156729757
      }
    },
    {
      "id": "6b4c70713fbdb8deb9978350",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1427.5048577211585,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.3326396728692,
        1435.677075769448
      ],
      "voteCount": 6040,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.385360860570387
      }
    },
    {
      "id": "ebf4b024632ed36fd6589424",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1413.9375449971853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.5222571222864,
        1420.3528328720843
      ],
      "voteCount": 11645,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.713616997823005
      }
    },
    {
      "id": "d5876f9d7acd2c3d2b520ad2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1391.7062700651704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.221804063482,
        1401.1907360668586
      ],
      "voteCount": 4414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.416909964669724
      }
    },
    {
      "id": "878f706104b4a12473e7eca6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1354.706576133825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.6544312466635,
        1363.7587210209863
      ],
      "voteCount": 4537,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.33078366394046
      }
    },
    {
      "id": "136fd877aa0c4c73ade7344a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1400.4828228642418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.3044646990797,
        1415.6611810294041
      ],
      "voteCount": 1591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.972673753227284
      }
    },
    {
      "id": "4e1148c3ec1f83e6eb684e3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1397.2476119041387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.5556056384223,
        1406.939618169855
      ],
      "voteCount": 4075,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.452946091378866
      }
    },
    {
      "id": "0402f070cf68e66f398044e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1381.2213687650608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.7262560361135,
        1396.7164814940081
      ],
      "voteCount": 1460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.50191130238447
      }
    },
    {
      "id": "9747b52de31a4e88f1885452",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1411.0397060920266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.9830823154712,
        1427.096329868582
      ],
      "voteCount": 1517,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.11386979159568
      }
    },
    {
      "id": "e05f57556a4258bbdb7f4d73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1435.636265452887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.5043054442788,
        1442.7682254614956
      ],
      "voteCount": 8665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.241025334015658
      }
    },
    {
      "id": "8e8f8f6a3e159615b0e94182",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1367.6436269665046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.193981938776,
        1376.0932719942332
      ],
      "voteCount": 5365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.585778066916127
      }
    },
    {
      "id": "9a0a656aca9478a1fad0daaf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1384.868899904493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.9779229851508,
        1392.7598768238354
      ],
      "voteCount": 6223,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.20934120291895
      }
    },
    {
      "id": "61730a98a92405fad07f82a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1317.977034370693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1296.5444714518394,
        1339.4095972895464
      ],
      "voteCount": 850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.5782057576782
      }
    },
    {
      "id": "05afff9521753d2cae709777",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1325.256016455618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.1673296890744,
        1351.3447032221618
      ],
      "voteCount": 593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 177.17737166315433
      }
    },
    {
      "id": "4da896b3d18c8b5ae341c498",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1408.8097130874119,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.0725684489803,
        1417.5468577258432
      ],
      "voteCount": 4883,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.872059026544044
      }
    },
    {
      "id": "9306ebaabb5e9b2b6a003955",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1376.882946373881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.1920813520196,
        1391.5738113957425
      ],
      "voteCount": 1627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.18217587753654
      }
    },
    {
      "id": "43689ccc9b35ab5df8da98e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1399.031273886547,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.60021316626,
        1408.462334606834
      ],
      "voteCount": 4420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.153939808124473
      }
    },
    {
      "id": "d5ff7fb8b80f3c9f721003e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1387.5560396909982,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.608982263982,
        1392.5030971180145
      ],
      "voteCount": 25741,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.370855013297828
      }
    },
    {
      "id": "92273241ccd7e0eff2398796",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1387.769131306235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.3483486327527,
        1403.1899139797174
      ],
      "voteCount": 1425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.90370621226833
      }
    },
    {
      "id": "b876c071d5a26bb350417a4b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-coder-480b-a35b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1378.0793419318693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.0505047201416,
        1403.108179143597
      ],
      "voteCount": 602,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.0741656780203
      }
    },
    {
      "id": "848fefdd6f366963c14ec581",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1440.5301414663193,
      "unit": "Arena rating",
      "confidenceInterval": [
        1410.260967654188,
        1470.7993152784506
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.50909928625907
      }
    },
    {
      "id": "d5f80de3ba318181272d572f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1474.6644163744775,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.7210127995481,
        1487.6078199494068
      ],
      "voteCount": 2042,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.61147780655449
      }
    },
    {
      "id": "a0fb1984751fc989f1077960",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1394.8428351693499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.9374264951873,
        1411.7482438435122
      ],
      "voteCount": 1158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.39695589104528
      }
    },
    {
      "id": "ffd7627222c0182315e5f2d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1433.9669389673882,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.2863943844256,
        1442.6474835503507
      ],
      "voteCount": 4483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.615426788092897
      }
    },
    {
      "id": "31b991f68178ac1b339011d6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1415.6503055093583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.494769314334,
        1424.8058417043826
      ],
      "voteCount": 6395,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.820836023761927
      }
    },
    {
      "id": "d38bf8ed5ed0c3360897ecbe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1418.8287099745633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.931179194389,
        1445.7262407547375
      ],
      "voteCount": 449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.33396265320187
      }
    },
    {
      "id": "c6bb90ed3deaf08a966030a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1437.4653148012715,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.7707291447794,
        1479.1599004577636
      ],
      "voteCount": 193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 452.54642941934105
      }
    },
    {
      "id": "0703862ffda79e1ceee69268",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1458.0369605272929,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.4090678081272,
        1469.6648532464587
      ],
      "voteCount": 2528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.19701639389104
      }
    },
    {
      "id": "5aa03fc8fbe62457dc0d5b13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1448.0933941503242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.6253647680708,
        1456.5614235325781
      ],
      "voteCount": 4871,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.666742236678378
      }
    },
    {
      "id": "023654f5a363972c81c090b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1420.3445799682859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.6111388614183,
        1434.0780210751534
      ],
      "voteCount": 1782,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.09785928714403
      }
    },
    {
      "id": "772fa773948278befb045c1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1390.1574750435182,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.1124058348364,
        1404.2025442521997
      ],
      "voteCount": 1657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.351316852334136
      }
    },
    {
      "id": "c6e28688752a5e8c3cffe047",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1417.4399726734728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.2287903719985,
        1441.6511549749468
      ],
      "voteCount": 570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.59342239396898
      }
    },
    {
      "id": "a316f249d870f94aec74a83d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1431.560920289723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.0531257321902,
        1447.068714847256
      ],
      "voteCount": 1432,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.60426136630907
      }
    },
    {
      "id": "cc39d1309da2e08f9f2e92ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1410.501762462033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.531507383242,
        1436.4720175408238
      ],
      "voteCount": 478,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.57240109516505
      }
    },
    {
      "id": "04ab644e55a44c67afe42255",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1433.977875374717,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.4007097939134,
        1461.5550409555208
      ],
      "voteCount": 451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 197.9716813243491
      }
    },
    {
      "id": "50607e52c27b91e5ee24111d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1463.400278864671,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.3790234375435,
        1473.4215342917985
      ],
      "voteCount": 3393,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.142558080991112
      }
    },
    {
      "id": "f6a1badc5650c34114f51928",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1404.2151995705096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.2337295641569,
        1417.1966695768624
      ],
      "voteCount": 1968,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.86837693482979
      }
    },
    {
      "id": "a92af153c7d2fa129a9ed98b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1415.5639953600676,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.2598611992228,
        1426.8681295209121
      ],
      "voteCount": 2632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.26430272739114
      }
    },
    {
      "id": "9ce8adf4740292af6eefcda6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1366.292008711265,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.8527953706066,
        1403.7312220519232
      ],
      "voteCount": 250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 364.88603965147865
      }
    },
    {
      "id": "15d1845729d01ffc8c9f1444",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1432.4709409250756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.6227041972827,
        1445.3191776528686
      ],
      "voteCount": 2065,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.97252546978478
      }
    },
    {
      "id": "f87518c010c839019861973d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1429.0617624719246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.4619080846746,
        1452.6616168591743
      ],
      "voteCount": 584,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.98479694720658
      }
    },
    {
      "id": "b9bcad92f6648546c29bcd44",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1450.7932365664014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.2684402569296,
        1465.318032875873
      ],
      "voteCount": 1686,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.919164223534125
      }
    },
    {
      "id": "4a14fc0cbfbafa90d99d2ff4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1424.1884774433724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.7405780513566,
        1430.6363768353883
      ],
      "voteCount": 9158,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.82281719267445
      }
    },
    {
      "id": "d1f930c58b4b4073518b9eda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1431.6096032279108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.9818837439518,
        1455.23732271187
      ],
      "voteCount": 573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.3273753724077
      }
    },
    {
      "id": "aae90109097b8ffd887b66cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-2025-09-23",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1407.4934335685325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.3106346245522,
        1437.676232512513
      ],
      "voteCount": 388,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.1498419259721
      }
    },
    {
      "id": "8e352d6edc0d4bc08f1ad672",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1489.386579399467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.732459751404,
        1505.0406990475306
      ],
      "voteCount": 1505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.7912505102949
      }
    },
    {
      "id": "579de756e2ec5c9b61d9b1e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1482.0070105443315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.6643011090705,
        1490.3497199795922
      ],
      "voteCount": 5366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.118325347195654
      }
    },
    {
      "id": "e97c690f3255572bd60f9f01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1394.295849356797,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.3303090045727,
        1404.2613897090214
      ],
      "voteCount": 3755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.852677107148832
      }
    },
    {
      "id": "f69bae5d70c874685be52811",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1439.019715683263,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.1786780832176,
        1444.8607532833087
      ],
      "voteCount": 12987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.881448907209903
      }
    },
    {
      "id": "d3ec46b8078f0328cea4c259",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1431.8757465394756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.5652812232358,
        1438.1862118557153
      ],
      "voteCount": 19720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.366367144934971
      }
    },
    {
      "id": "1a84c58f94c6131282bf5f34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1469.8247986533122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.9436803795716,
        1486.7059169270528
      ],
      "voteCount": 1262,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.18331614980791
      }
    },
    {
      "id": "6e4ff2e5e9cb95678e410653",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1463.00453873092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.8816157253905,
        1493.1274617364495
      ],
      "voteCount": 396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 236.2098704556985
      }
    },
    {
      "id": "2fdb5f4a51277ea9fc56a610",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1450.26538183127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.6058041770636,
        1475.9249594854762
      ],
      "voteCount": 567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 171.39684586629735
      }
    },
    {
      "id": "7fd1ded4264885781d396ae4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1457.391293736708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.9068956687852,
        1464.8756918046306
      ],
      "voteCount": 6837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.582016117773176
      }
    },
    {
      "id": "bc4797e9e945a71db5676a7d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1459.4872586584147,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.6492815000374,
        1465.325235816792
      ],
      "voteCount": 13567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.872144383829772
      }
    },
    {
      "id": "542c1de53a543106f33029cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1445.349533462786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.782831790913,
        1453.9162351346592
      ],
      "voteCount": 5153,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.10429890319994
      }
    },
    {
      "id": "d1085e79c4175084e7f734b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1397.5069075711463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.8642801404453,
        1406.149535001847
      ],
      "voteCount": 4959,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.444438270043555
      }
    },
    {
      "id": "8f891a9e210be27958aae820",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1431.0403378648798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.9702770771194,
        1445.11039865264
      ],
      "voteCount": 1737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.534226920464675
      }
    },
    {
      "id": "3e52ed1431b5db2dc75a395f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1457.1156773702085,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.7000226249331,
        1466.5313321154838
      ],
      "voteCount": 4210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.078356015334418
      }
    },
    {
      "id": "742f1bade3c938c8617c2fab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1440.8916015058776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.1175745020757,
        1456.6656285096797
      ],
      "voteCount": 1320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.77224917166052
      }
    },
    {
      "id": "700edf7df0abfab51c9ac38e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1473.2721579976278,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.3507462203786,
        1489.1935697748768
      ],
      "voteCount": 1462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.98830413465696
      }
    },
    {
      "id": "5ab4331c821c58d620bcf143",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1470.2006159512327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.564398459494,
        1476.8368334429713
      ],
      "voteCount": 9492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.464233941651589
      }
    },
    {
      "id": "239bb1421f61f788b2355166",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1405.8611473055457,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.0575231352702,
        1413.6647714758215
      ],
      "voteCount": 6194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.852454245469811
      }
    },
    {
      "id": "9bcbcb3e1fb3f9fe1d143de3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1426.96949646081,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.6875049516445,
        1434.2514879699756
      ],
      "voteCount": 7283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.80397469156725
      }
    },
    {
      "id": "f2a31c4da6d2587a98e6ff67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1385.3928461387375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.5135439496628,
        1416.2721483278124
      ],
      "voteCount": 372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.22114415166442
      }
    },
    {
      "id": "7d94ba2870de932415eb158e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1383.2507870264817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.0240125215832,
        1407.4775615313802
      ],
      "voteCount": 668,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.7900285561672
      }
    },
    {
      "id": "d1bb5fa3ec2a36292566fcef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1444.0737036048718,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.061504227044,
        1452.0859029826995
      ],
      "voteCount": 6037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.711187563495677
      }
    },
    {
      "id": "eed294d23f6f34f8665e9e88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1438.8768186422935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1423.99281721137,
        1453.7608200732168
      ],
      "voteCount": 1524,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.66910669517464
      }
    },
    {
      "id": "9d19cc5c4ed55253758acac4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1445.4902230408034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.511943684862,
        1454.468502396745
      ],
      "voteCount": 4652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.984085462292875
      }
    },
    {
      "id": "0aa6f3506246f331363b97c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1435.046050938109,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.5482622540587,
        1439.5438396221589
      ],
      "voteCount": 27736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.266255344815678
      }
    },
    {
      "id": "efc4d409f0c3c5d242f5cf7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1419.3067449872187,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.698937798654,
        1434.9145521757835
      ],
      "voteCount": 1418,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.41435808789857
      }
    },
    {
      "id": "c05cea2c036fa052d32ed36a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1450.8482279341936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.529215285842,
        1473.1672405825452
      ],
      "voteCount": 752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.6742588814927
      }
    },
    {
      "id": "2f7a35e23045bf4781fc298c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1455.063178802071,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.6314072829787,
        1472.4949503211633
      ],
      "voteCount": 1183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.10189135879628
      }
    },
    {
      "id": "bf3b1578f2f7162331f2df7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1446.1736383592113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.481250814646,
        1454.8660259037765
      ],
      "voteCount": 4794,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.668986380351033
      }
    },
    {
      "id": "fb9f76b9b4e31dafd7ad1d1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1317.2715656083246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.3566972533483,
        1328.1864339633007
      ],
      "voteCount": 3032,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.01278883029487
      }
    },
    {
      "id": "f321aef48b90b0e3bc3a03fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1411.5021118460359,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.3170982542774,
        1417.6871254377943
      ],
      "voteCount": 10892,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.958298374606764
      }
    },
    {
      "id": "508f974cba90cbf127a71b37",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1384.4645888513573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.8343359217936,
        1391.094841780921
      ],
      "voteCount": 16190,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.443635338005462
      }
    },
    {
      "id": "8f1250c3c5367956ca40071d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1395.8329825705014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.35288418824,
        1414.3130809527631
      ],
      "voteCount": 1004,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.9021728876309
      }
    },
    {
      "id": "d0c427631ca43671a8f405e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1405.748440432818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.4601982109425,
        1438.036682654693
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.38923894285324
      }
    },
    {
      "id": "ef377450583316be6b0363ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1388.3007254274166,
      "unit": "Arena rating",
      "confidenceInterval": [
        1360.9153444219517,
        1415.6861064328818
      ],
      "voteCount": 459,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 195.22767985287857
      }
    },
    {
      "id": "39d937d21d1b1189f9bbf540",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1429.008288137606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.123839492486,
        1436.8927367827262
      ],
      "voteCount": 6060,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.182532037738667
      }
    },
    {
      "id": "8ea1a212f60742c87810d1af",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1421.2652149117434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.176813761586,
        1427.3536160619012
      ],
      "voteCount": 11901,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.649622785372912
      }
    },
    {
      "id": "326d23cb960bc5c7513071fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1411.5015542852923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.19498140223,
        1420.8081271683545
      ],
      "voteCount": 4281,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.546720626332224
      }
    },
    {
      "id": "dfa1b10660bf3a656c62e8e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1329.1345540437735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.9286427544462,
        1338.340465333101
      ],
      "voteCount": 4204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.0616194583219
      }
    },
    {
      "id": "be54322fd440bfb26294a134",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1412.9956579643776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.39555298486,
        1428.5957629438951
      ],
      "voteCount": 1426,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.35178554068003
      }
    },
    {
      "id": "cbe41faba444547699ea8ab1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1417.3923975381592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.2905166248324,
        1427.4942784514858
      ],
      "voteCount": 3508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.564907434982015
      }
    },
    {
      "id": "d40eebd1252ffc517220dc54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1417.1209197114579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1399.101568162434,
        1435.1402712604818
      ],
      "voteCount": 1050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.52440736788695
      }
    },
    {
      "id": "aa2483ed4171e4f0476367ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1439.2480417885672,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.761021223741,
        1456.7350623533932
      ],
      "voteCount": 1177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.60410419794589
      }
    },
    {
      "id": "6da8b726eb2628bfa2de8c13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1443.7159930404653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1436.7426876708614,
        1450.6892984100693
      ],
      "voteCount": 8121,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.658469099236669
      }
    },
    {
      "id": "e5819bfe614d115d3ce4dcec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1344.9103978540888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.410584061058,
        1353.41021164712
      ],
      "voteCount": 5050,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.807134968362053
      }
    },
    {
      "id": "b3422b6efbc4bad0de8a604d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1379.463029618424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.8443666257747,
        1387.081692611073
      ],
      "voteCount": 6314,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.109891451361408
      }
    },
    {
      "id": "f85ad1ba840a18e2ebe6d91e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1378.3697098717118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.1391153378063,
        1414.6003044056174
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 341.7076796994235
      }
    },
    {
      "id": "b886834bb279640d62d729d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1323.6235579232937,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.541747313764,
        1351.7053685328235
      ],
      "voteCount": 484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 205.28349356794726
      }
    },
    {
      "id": "f81578d5d3e3a8e9a43f9c34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1391.2814596735082,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.864257736665,
        1399.698661610351
      ],
      "voteCount": 5217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.443328889516298
      }
    },
    {
      "id": "5ab009f585d643b8c04ae7f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1419.3049491063864,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.5163365568394,
        1436.0935616559336
      ],
      "voteCount": 1212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.37251926805264
      }
    },
    {
      "id": "51bc521d6327c6b4fac6ffd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1404.354312732392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.881491162422,
        1413.827134302362
      ],
      "voteCount": 4084,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.359445639007706
      }
    },
    {
      "id": "88eb7fa322b1b984d5024ba1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1401.9489860419385,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.1733461384508,
        1406.724625945426
      ],
      "voteCount": 22881,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.936998820584074
      }
    },
    {
      "id": "755ab7786687c224a86200f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1387.1991502772833,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.4451523530101,
        1403.9531482015564
      ],
      "voteCount": 1188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.07027344258465
      }
    },
    {
      "id": "b7f108ea055d1cc48ecd52d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1422.4300074829196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.5098576593386,
        1447.3501573065005
      ],
      "voteCount": 615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.66094606671064
      }
    },
    {
      "id": "81350757626e3b22c34ee38f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1412.991837815212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.890455393471,
        1435.0932202369527
      ],
      "voteCount": 718,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.15770954529546
      }
    },
    {
      "id": "0091b51deaa986cad5d699d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1420.9050223832562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.5065713823635,
        1432.303473384149
      ],
      "voteCount": 2677,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.821704535746065
      }
    },
    {
      "id": "91e61bc9ad4910215e2070b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1323.948759321981,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.6282582859876,
        1338.269260357974
      ],
      "voteCount": 1796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.385122552173065
      }
    },
    {
      "id": "420bad28383b09c266626d6d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1387.0733049821001,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.5091874317973,
        1394.6374225324032
      ],
      "voteCount": 6634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.894308903320193
      }
    },
    {
      "id": "08ca5afda2aeaf38ba17931b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1337.521356387474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1329.5201289318693,
        1345.5225838430786
      ],
      "voteCount": 9762,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.665450232459804
      }
    },
    {
      "id": "bcde5827cfe65c0a3e0ecf03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1385.0708897725635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.654161516588,
        1408.487618028539
      ],
      "voteCount": 620,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.74347007450643
      }
    },
    {
      "id": "1a2a3ca1e74192ec70cff049",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1369.3872195301897,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.7928278171958,
        1410.9816112431838
      ],
      "voteCount": 195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 450.37406431481065
      }
    },
    {
      "id": "025855b96a8277611b2f0882",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1366.044822153528,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.936605955529,
        1399.1530383515271
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 285.34836138511093
      }
    },
    {
      "id": "71e635fa399915283bd9c36a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1396.5240168360579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.5636521943993,
        1406.4843814777164
      ],
      "voteCount": 3495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.825830348710223
      }
    },
    {
      "id": "d6990e50795755e67a57cb51",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1384.5898216792066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.070264916325,
        1392.1093784420882
      ],
      "voteCount": 6693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.719338810973255
      }
    },
    {
      "id": "7a729f84203fa6de38f9aa8b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1366.6005753804657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1354.783456130553,
        1378.4176946303785
      ],
      "voteCount": 2497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.351894914085356
      }
    },
    {
      "id": "5adf9aa775ee888c72e1ee67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1316.734603172649,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.73120829086,
        1328.7379980544383
      ],
      "voteCount": 2453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.50697206800388
      }
    },
    {
      "id": "1149e84cdd117f7554559c2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1360.2537952312032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.1068303708246,
        1380.400760091582
      ],
      "voteCount": 868,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.66303376694658
      }
    },
    {
      "id": "28249c62c1c5a491c1e6e0ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1379.982718334758,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.231488478963,
        1392.7339481905526
      ],
      "voteCount": 2125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.32607205351587
      }
    },
    {
      "id": "53d0e96718d1388bb1043f97",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1386.860303552917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.6257969277713,
        1409.0948101780625
      ],
      "voteCount": 671,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.6941518676271
      }
    },
    {
      "id": "17c21f8a9c040143fed36271",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1392.5913118793294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.480140357853,
        1414.7024834008057
      ],
      "voteCount": 721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.27037536323303
      }
    },
    {
      "id": "4c77928a719342eb026fa12b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1409.5766298830736,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.941461867291,
        1418.2117978988558
      ],
      "voteCount": 4835,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.41088793119414
      }
    },
    {
      "id": "9821a6d7c22cb63a49bdfdeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1338.726841711727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.995165122991,
        1349.458518300463
      ],
      "voteCount": 3077,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.98050682850094
      }
    },
    {
      "id": "94c1191da1e921c6d02c2d15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1358.5415488932013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.6562557088164,
        1368.4268420775861
      ],
      "voteCount": 3514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.43799788112505
      }
    },
    {
      "id": "a82c61d5578680b88d420573",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1295.905489478746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.297757105809,
        1341.513221851683
      ],
      "voteCount": 180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 541.4779512918467
      }
    },
    {
      "id": "4cc93cbd2f53b71641b4f707",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1319.182525640998,
      "unit": "Arena rating",
      "confidenceInterval": [
        1285.306799197244,
        1353.058252084752
      ],
      "voteCount": 332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 298.73152249090214
      }
    },
    {
      "id": "15070e674866d550a5492667",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1369.932059014835,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.8900576741353,
        1380.9740603555347
      ],
      "voteCount": 2831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.73945089589277
      }
    },
    {
      "id": "6647bd49faf7e17051569cd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1389.4108929325087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.8998760931204,
        1408.921909771897
      ],
      "voteCount": 829,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.0977115402495
      }
    },
    {
      "id": "357bca25fabc9352a7573eac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1350.0829894602703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.4392456222772,
        1362.7267332982633
      ],
      "voteCount": 2296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.615507468045834
      }
    },
    {
      "id": "64a2c343d71d899007784e06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1369.6612854881546,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.8248789467334,
        1375.4976920295758
      ],
      "voteCount": 13700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.867371201076478
      }
    },
    {
      "id": "503864455ea68cd683973df1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1352.6439998513515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.1208642189576,
        1373.1671354837454
      ],
      "voteCount": 750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.64561013035323
      }
    },
    {
      "id": "768f01125120d8976e00b2ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-next-80b-a3b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1350.4601597481783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.083108926412,
        1380.8372105699445
      ],
      "voteCount": 398,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 240.21218492755563
      }
    },
    {
      "id": "76b0d963c9d9aecba0ef9758",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1455.1753391779243,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.0915715515428,
        1482.2591068043057
      ],
      "voteCount": 494,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.951017068896
      }
    },
    {
      "id": "67be090316b8735429a06e9f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1465.5162166899693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.5320696813305,
        1478.5003636986082
      ],
      "voteCount": 2315,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.88647162732932
      }
    },
    {
      "id": "b7fc467f5c206e062516d1bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1362.2693604122019,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.5237489470385,
        1379.014971877365
      ],
      "voteCount": 1385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.99713895970876
      }
    },
    {
      "id": "dac57873ce4b99ec98fc3082",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1427.3990058973568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.695027752697,
        1436.1029840420165
      ],
      "voteCount": 5644,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.721475376645365
      }
    },
    {
      "id": "071800e790441d6eaa18cc00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1402.324761537013,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.0925284366776,
        1411.5569946373485
      ],
      "voteCount": 8129,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.18795827245888
      }
    },
    {
      "id": "a53b7c1d9c97a1dc13247921",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1449.4225054187484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.5503521012988,
        1474.2946587361982
      ],
      "voteCount": 563,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.03882392651653
      }
    },
    {
      "id": "069cd380f8120257d31937eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1456.6588148810552,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.4238845182574,
        1498.8937452438527
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 464.3520667567783
      }
    },
    {
      "id": "b88d4d056108693bbd3d2d77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1409.139243593105,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.0356074226056,
        1445.2428797636042
      ],
      "voteCount": 259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 339.31706822156025
      }
    },
    {
      "id": "7c18035234861d20aa3ef10c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1452.0014188394725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.2365969369603,
        1463.7662407419848
      ],
      "voteCount": 2952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.0308520430323
      }
    },
    {
      "id": "f98b9c2091805d637329d5a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1440.2732565362853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.670066007021,
        1448.8764470655499
      ],
      "voteCount": 5717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.26739052468932
      }
    },
    {
      "id": "bd9896c8ec85911c4070801e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1438.3929439502842,
      "unit": "Arena rating",
      "confidenceInterval": [
        1424.6710906411945,
        1452.1147972593737
      ],
      "voteCount": 2234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.01504012534313
      }
    },
    {
      "id": "f523e63967ce372b4bb6e990",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1361.4572064510012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.0821543298753,
        1375.832258572127
      ],
      "voteCount": 1911,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.79261710991068
      }
    },
    {
      "id": "bb3b35737490ac3f88f8ead1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1437.6074488074435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.1896245921582,
        1460.0252730227287
      ],
      "voteCount": 753,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 130.82499800339366
      }
    },
    {
      "id": "fa0eec4c0bf1cfe7aea62461",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1440.549218891242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.3295362589581,
        1455.7689015235258
      ],
      "voteCount": 1750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.299680470239956
      }
    },
    {
      "id": "c82b5210455fc48e9f97d40c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1411.3459350870098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.16113994062,
        1435.5307302334
      ],
      "voteCount": 591,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.26098822716517
      }
    },
    {
      "id": "f5d0d25a17adfb148998204a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1435.9067347431671,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.3026032360829,
        1460.5108662502512
      ],
      "voteCount": 628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 157.58682195335993
      }
    },
    {
      "id": "05160f96cfb8523615d5a135",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1455.4204294668532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.42934382606,
        1465.4115151076464
      ],
      "voteCount": 4093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.98538652657698
      }
    },
    {
      "id": "31df5fff2a545e3b9d2e469a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1387.6002531476258,
      "unit": "Arena rating",
      "confidenceInterval": [
        1374.6911967286446,
        1400.5093095666073
      ],
      "voteCount": 2367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.380326435031556
      }
    },
    {
      "id": "6170aab462be3fc7e38dbafe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1413.4783422963644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.1687588908967,
        1424.7879257018321
      ],
      "voteCount": 2925,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.296381082153445
      }
    },
    {
      "id": "22fb59fcad157aab0e6ab643",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1368.2302376028613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.2174887540996,
        1415.242986451623
      ],
      "voteCount": 151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 575.3539625129649
      }
    },
    {
      "id": "7e033c903ca22c0c663de9ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1381.586505281155,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.9812270655043,
        1416.1917834968058
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 311.73711245620115
      }
    },
    {
      "id": "24eb52a142a7b86f245c688f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1424.8339434862312,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.9616427890462,
        1437.7062441834162
      ],
      "voteCount": 2204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.133646089380186
      }
    },
    {
      "id": "8d42d2025347d29d52a9a25a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1410.134269159893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.4325176979462,
        1432.8360206218397
      ],
      "voteCount": 704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 134.15984486510195
      }
    },
    {
      "id": "e64b6b3147685c9b118b8778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1426.1771625900617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.0981340010328,
        1440.2561911790906
      ],
      "voteCount": 2012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.599940351534116
      }
    },
    {
      "id": "b7b02cb720d8f9bbf808531d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1415.4448078088785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.964781232585,
        1421.9248343851723
      ],
      "voteCount": 11515,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.930937018839181
      }
    },
    {
      "id": "9d2c623d345a57ec927b6607",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1400.7656307546335,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.2258481465096,
        1423.3054133627575
      ],
      "voteCount": 717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.25230927496673
      }
    },
    {
      "id": "2594254b0deb27fac897737c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-instruct",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1400.3076823917886,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.4872036875872,
        1430.1281610959902
      ],
      "voteCount": 406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.49042893737118
      }
    },
    {
      "id": "99d957dd74e7fbdabcdfac43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1440.2241434279565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1405.2630669553155,
        1475.1852199005978
      ],
      "voteCount": 296,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 318.18039062175944
      }
    },
    {
      "id": "1363284affcd094a760880bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1455.4707535518587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1441.026383345409,
        1469.9151237583085
      ],
      "voteCount": 1625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.31265579030066
      }
    },
    {
      "id": "8d0c9c66f674aeaa7ef9a8d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1338.756184278804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.8325363890444,
        1356.679832168564
      ],
      "voteCount": 1032,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.62894636419473
      }
    },
    {
      "id": "b9d3918555ccd83043fe6189",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1404.1110807725195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.716862260767,
        1413.5052992842718
      ],
      "voteCount": 3887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.97339254846027
      }
    },
    {
      "id": "397ef70f7df98984611deba8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1373.3314566697072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.6805090329658,
        1382.9824043064486
      ],
      "voteCount": 5589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.2462029751227
      }
    },
    {
      "id": "a3393213c698d63eec3186aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1434.179608116002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.7854357723538,
        1464.5737804596504
      ],
      "voteCount": 378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 240.48304448268672
      }
    },
    {
      "id": "443167a7f43c3a860457a16c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1419.0256144589036,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.7625087900688,
        1464.2887201277383
      ],
      "voteCount": 170,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 533.3257052636874
      }
    },
    {
      "id": "95c137782a2ac53a9b8cfa69",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1419.7140443907972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.9661729584238,
        1432.4619158231706
      ],
      "voteCount": 2096,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.30377927803913
      }
    },
    {
      "id": "8a69f09996aa0ef73403f1dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1419.0041353885472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.8242608914543,
        1428.1840098856399
      ],
      "voteCount": 4040,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.93700354886221
      }
    },
    {
      "id": "dc6805f6ff2bd19aadb2f6cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1393.0628607244782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.532899137936,
        1407.5928223110202
      ],
      "voteCount": 1580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.95823164082243
      }
    },
    {
      "id": "b3d70d986ba73263eea68478",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1361.741611813325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.5493064682364,
        1376.9339171584138
      ],
      "voteCount": 1446,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.0829404847578
      }
    },
    {
      "id": "fa2c32894def9475a19117e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1405.0535726852756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.9578890589828,
        1430.1492563115687
      ],
      "voteCount": 511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.9463979877277
      }
    },
    {
      "id": "a576d2c8d08b38248ce87f0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1406.6875323471984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.0072479274559,
        1423.3678167669411
      ],
      "voteCount": 1250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.4287051639498
      }
    },
    {
      "id": "ee01d6255e8bfe0622373014",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1433.3071093211302,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.3879297221822,
        1462.2262889200779
      ],
      "voteCount": 379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 217.70868508882901
      }
    },
    {
      "id": "d18184bad8647a5715ddcd7a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1415.1703716575598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.3237840802212,
        1443.0169592348982
      ],
      "voteCount": 435,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.858844750615
      }
    },
    {
      "id": "2c13309fb69f45e2510a44f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1437.2847122115752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.3666356159667,
        1448.2027888071837
      ],
      "voteCount": 2834,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.031022877406343
      }
    },
    {
      "id": "76d63448ecdec9238d43e28b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1365.4896668321476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.4183336812187,
        1379.5609999830765
      ],
      "voteCount": 1756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.543547877640286
      }
    },
    {
      "id": "89ce897bc1961f69bc6dd9d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1384.089874812256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.7780336631072,
        1396.4017159614048
      ],
      "voteCount": 2132,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.459340723710845
      }
    },
    {
      "id": "24fcbc8940f6a0af993dfdc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1364.1781806526017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.7882592043866,
        1405.5681021008168
      ],
      "voteCount": 212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 445.9570380556277
      }
    },
    {
      "id": "a1319401561a561cb418f499",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1407.0265586805083,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.2817097350712,
        1420.7714076259454
      ],
      "voteCount": 1730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.17946055158971
      }
    },
    {
      "id": "9b22a5fd4b2a618e6992e87e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1405.254927522579,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.908835115467,
        1433.601019929691
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 209.16557804135104
      }
    },
    {
      "id": "cf0ff06b07b3005ec7e9d4b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1387.587678719333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.1255984105474,
        1404.0497590281188
      ],
      "voteCount": 1287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.54613904306909
      }
    },
    {
      "id": "a90318da133f56958a903bdb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1396.0014798286752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.2139645596023,
        1402.7889950977478
      ],
      "voteCount": 7947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.992934371627998
      }
    },
    {
      "id": "574af979b04174f607dbcacf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1377.1374854805995,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.4117131467456,
        1402.8632578144536
      ],
      "voteCount": 480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.2823003094716
      }
    },
    {
      "id": "b671a80c6d52505a62296d1a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3-vl-235b-a22b-thinking",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1384.2947643120303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.0741531660562,
        1417.5153754580042
      ],
      "voteCount": 331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 287.28903690619165
      }
    },
    {
      "id": "46aef6da34a7b5aca8095bd8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1465.4464594859917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.4546533030336,
        1481.4382656689497
      ],
      "voteCount": 1466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.57311113570192
      }
    },
    {
      "id": "3320c97be7d046612c525277",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1455.327277563782,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.777129109505,
        1462.877426018059
      ],
      "voteCount": 7029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.83934732673258
      }
    },
    {
      "id": "dd91891c93092025ba7e3214",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1368.7827048123254,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.0105683340098,
        1378.554841290641
      ],
      "voteCount": 4100,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.858954841944715
      }
    },
    {
      "id": "f0a1694cee1bdcb6edd12846",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1431.1867735004846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.2927160990141,
        1437.0808309019549
      ],
      "voteCount": 12499,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.04341664804059
      }
    },
    {
      "id": "8a28a2a6c3b72ebdd364fb3a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1404.0266993137354,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.8217120864883,
        1410.2316865409828
      ],
      "voteCount": 18980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.022720088235703
      }
    },
    {
      "id": "9c7af5208b685f2280f9ec5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1443.9534793428984,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.3800540125808,
        1456.5269046732158
      ],
      "voteCount": 2306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.153903221720356
      }
    },
    {
      "id": "ba25235a759f3da077f4d68d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1444.6105543791605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.4723334997325,
        1467.7487752585885
      ],
      "voteCount": 770,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.36821672566063
      }
    },
    {
      "id": "766531307f5ba0d4d96fc5a8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1406.4731223708848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1377.471917775419,
        1435.4743269663506
      ],
      "voteCount": 408,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.94543381727544
      }
    },
    {
      "id": "13675cc06b5baf855bb3a7f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1442.7997436508517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.6511607858647,
        1449.948326515839
      ],
      "voteCount": 8029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.30282045516075
      }
    },
    {
      "id": "918b55cba7c3cddecadbc3ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1431.5003916565395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.0125804809975,
        1436.9882028320815
      ],
      "voteCount": 16289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.839748622624207
      }
    },
    {
      "id": "fd6e39458775c8a30fa873c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1420.513192869451,
      "unit": "Arena rating",
      "confidenceInterval": [
        1411.8188315045925,
        1429.2075542343093
      ],
      "voteCount": 5017,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.677920048374506
      }
    },
    {
      "id": "cf81c8591b3908bc6c8ef31a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1365.4206940121808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.6708075924616,
        1374.1705804318997
      ],
      "voteCount": 5069,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.930061971651938
      }
    },
    {
      "id": "cc83e6362ae680ba25f3adbb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1422.4475734372168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.0956879167766,
        1435.7994589576567
      ],
      "voteCount": 2078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.40759025987002
      }
    },
    {
      "id": "624aff183f23e30df6044052",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1435.2566945840447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.0744720628452,
        1444.4389171052442
      ],
      "voteCount": 4336,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.948227057550366
      }
    },
    {
      "id": "d92153abd0ccfc8662be2428",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1431.1267872492424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.3579506627998,
        1446.895623835685
      ],
      "voteCount": 1443,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.7296297829372
      }
    },
    {
      "id": "d905b425fe825db70b2b5239",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1431.7413857192719,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.8341837772334,
        1445.6485876613103
      ],
      "voteCount": 1944,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.34812941758653
      }
    },
    {
      "id": "fcc54af8d9b900f561275998",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1450.1140621099628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.7030126974314,
        1456.5251115224942
      ],
      "voteCount": 10201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.699465096047016
      }
    },
    {
      "id": "8fdc255571b21443f56759a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1390.598925019054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1382.6069284355951,
        1398.5909216025125
      ],
      "voteCount": 6028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.627019153747632
      }
    },
    {
      "id": "76246fb218432f5e130a4c08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1404.2056116703795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.2280382965705,
        1411.1831850441883
      ],
      "voteCount": 8253,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.673969046501364
      }
    },
    {
      "id": "d4d55dd6531bc592545fc878",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1358.3349600894394,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.172685767927,
        1399.4972344109515
      ],
      "voteCount": 214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 441.0649460022769
      }
    },
    {
      "id": "f5cc0c1cc7da683a35875532",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1349.355907948121,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.3432167219735,
        1379.3685991742684
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 234.48426149556016
      }
    },
    {
      "id": "0bb00d63c722020c001d9b6c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1415.8583044554296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.0244229413743,
        1422.692185969485
      ],
      "voteCount": 9621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.157344052879841
      }
    },
    {
      "id": "83a26dac55cce75b25eb7fa7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1421.8316172907391,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.5624917505945,
        1436.1007428308835
      ],
      "voteCount": 1682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.00276618443929
      }
    },
    {
      "id": "cb6fdc3165c962d3b48f9b09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1417.2227009441945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.0612698972604,
        1426.3841319911285
      ],
      "voteCount": 4538,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.848944045834955
      }
    },
    {
      "id": "42df44ffd23ea27f3c1ba5a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1417.231449675073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1412.7576229746485,
        1421.7052763754975
      ],
      "voteCount": 26670,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.2102928287580825
      }
    },
    {
      "id": "224cd01c0961d2c62f94d805",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1392.7758078601646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.3638758677864,
        1404.187739852543
      ],
      "voteCount": 2800,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.90175396312991
      }
    },
    {
      "id": "ffe893fe29caf82c71adac3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-122b-a10b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1420.728758072339,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.8620012186082,
        1442.5955149260697
      ],
      "voteCount": 778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.47225848793123
      }
    },
    {
      "id": "d49975299d67113d2b4733f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1469.285216805157,
      "unit": "Arena rating",
      "confidenceInterval": [
        1452.9353364018243,
        1485.63509720849
      ],
      "voteCount": 1400,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.58777945587444
      }
    },
    {
      "id": "56b74a591f3e040d571edd8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1448.4611228700337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.8616200578851,
        1456.0606256821823
      ],
      "voteCount": 6863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.033987265655357
      }
    },
    {
      "id": "8fae9e09ee2420192f32a694",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1358.246415120704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.331376825564,
        1368.161453415844
      ],
      "voteCount": 3887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.591315430613243
      }
    },
    {
      "id": "226ffe8d19280ca7f621456a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1425.1810383548896,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.2430596092092,
        1431.11901710057
      ],
      "voteCount": 12115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.178698309664753
      }
    },
    {
      "id": "77e1e220942a9b74d4cee11b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1391.0369546026172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.812891908294,
        1397.2610172969405
      ],
      "voteCount": 18377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.084438811156408
      }
    },
    {
      "id": "bb53bb01b8ecbf96679fff30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1440.1222947283259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.3367934629262,
        1452.9077959937256
      ],
      "voteCount": 2217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.553896901594086
      }
    },
    {
      "id": "69b77e2af80950bc438146d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1407.822696867877,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.3599223233073,
        1432.2854714124467
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.7812712177687
      }
    },
    {
      "id": "84d7a1596912c97cc5c0e19d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1399.8369668916694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.3957845314733,
        1428.2781492518654
      ],
      "voteCount": 424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 210.57126779241725
      }
    },
    {
      "id": "293eb7d3a323d9fbe12b4a14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1439.0574005856126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1431.8583755154784,
        1446.2564256557469
      ],
      "voteCount": 7779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.49121892996307
      }
    },
    {
      "id": "6ab3959cf53c7f9001a79a8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1426.5224575623647,
      "unit": "Arena rating",
      "confidenceInterval": [
        1421.0107653893072,
        1432.034149735422
      ],
      "voteCount": 15752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.908128663748758
      }
    },
    {
      "id": "a02072bacbcd34cb41130b65",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1405.8778767391796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.101814999441,
        1414.653938478918
      ],
      "voteCount": 4948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.049482046975513
      }
    },
    {
      "id": "9795b0d0f98dc35457f9e81d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1358.3331117486518,
      "unit": "Arena rating",
      "confidenceInterval": [
        1349.329282540627,
        1367.3369409566765
      ],
      "voteCount": 4727,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.103685914985437
      }
    },
    {
      "id": "7ebfbbd9bc5ca13e92f00fa8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1407.2229632776093,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.5683918781635,
        1420.8775346770553
      ],
      "voteCount": 1960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.53555089492655
      }
    },
    {
      "id": "b3d7583881a9531b7127550f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1439.079569812855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.759837859512,
        1448.3993017661983
      ],
      "voteCount": 4216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.610525775848544
      }
    },
    {
      "id": "3541b520fa906b5b64d0dc91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1443.2450133733917,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.274011349771,
        1459.2160153970121
      ],
      "voteCount": 1405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.40001039823737
      }
    },
    {
      "id": "c5384e88fedd64198f2f26da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1429.7092331256551,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.5558006142867,
        1443.8626656370236
      ],
      "voteCount": 1831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.14676538369502
      }
    },
    {
      "id": "b3649a2d5533a1aad97bd57c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1443.6320447444014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.1334267682587,
        1450.130662720544
      ],
      "voteCount": 9908,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.993749398623985
      }
    },
    {
      "id": "87b57707e0998cf6aeee75f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1380.222080167947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.1321014519697,
        1388.3120588839242
      ],
      "voteCount": 5812,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.03721390227966
      }
    },
    {
      "id": "eb62759d2689c5e465d989b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1400.4732994451729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.4489497211757,
        1407.49764916917
      ],
      "voteCount": 7934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.844466476957736
      }
    },
    {
      "id": "fdb9d2ade8e4fa5a9968395b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1359.6768825852907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.3299967660366,
        1404.023768404545
      ],
      "voteCount": 192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 511.9529776738851
      }
    },
    {
      "id": "6bab5964f4745e9be25ba3f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1353.482697379244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.2329812996895,
        1383.7324134587984
      ],
      "voteCount": 409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.20255939338972
      }
    },
    {
      "id": "23767f03ab7d1e9bfe70e694",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1422.1505096267113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.2643334337681,
        1429.0366858196544
      ],
      "voteCount": 9157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.344118412725427
      }
    },
    {
      "id": "e01028daa863be60ffbd6203",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1427.9636441093858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.1367456196976,
        1442.790542599074
      ],
      "voteCount": 1561,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.22745682948511
      }
    },
    {
      "id": "9f0f34050bd9ed62447642f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1416.2835470769792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.8254503745195,
        1425.7416437794388
      ],
      "voteCount": 4252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.2868806900065
      }
    },
    {
      "id": "7f2e38fd64d43e717a80be40",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1408.446398713859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.9452654410807,
        1412.9475319866372
      ],
      "voteCount": 25772,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.274090309173293
      }
    },
    {
      "id": "b087f0e58aa7794a93b3de96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1388.5694328443303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.916839241961,
        1400.2220264466998
      ],
      "voteCount": 2653,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.34671175713521
      }
    },
    {
      "id": "f17b17299e53c1ab034f877d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-27b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1402.3704859900035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.305204062865,
        1424.4357679171421
      ],
      "voteCount": 776,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.74264888674027
      }
    },
    {
      "id": "d6bdbf0d8bc0c57a723c5560",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1464.0778655760055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.9749827402281,
        1480.180748411783
      ],
      "voteCount": 1460,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 67.50113634588503
      }
    },
    {
      "id": "e14ec76961bf1d9b941c8d74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1437.079745498504,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.562514471559,
        1444.596976525449
      ],
      "voteCount": 7198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.71023508258068
      }
    },
    {
      "id": "2388e8c263483bcbd5cb9519",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1344.810161709706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.3377074413888,
        1354.2826159780234
      ],
      "voteCount": 4271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.357634183658334
      }
    },
    {
      "id": "416424a4718e62a1eab43c35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1411.9642129009262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.1063957906651,
        1417.8220300111873
      ],
      "voteCount": 12744,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.932549559666104
      }
    },
    {
      "id": "cada7520cd191a2c2b9102fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1375.5382268323278,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.3418987548635,
        1381.734554909792
      ],
      "voteCount": 19402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.994765904228641
      }
    },
    {
      "id": "b27ea1012e49ef442d29d821",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1421.4482425827134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.0323920698559,
        1433.8640930955712
      ],
      "voteCount": 2371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.12885498790094
      }
    },
    {
      "id": "cce6a20d9ecde690ebc9b0a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1426.890865682423,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.3023586674312,
        1450.4793726974149
      ],
      "voteCount": 731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.84540617717147
      }
    },
    {
      "id": "183c04076a844792d6650639",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1348.4346500780525,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.531209515963,
        1375.338090640142
      ],
      "voteCount": 463,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.4167312112678
      }
    },
    {
      "id": "e4b0e99e532f96ffb48e2a4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1424.0610401053057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.9875940818404,
        1431.134486128771
      ],
      "voteCount": 8144,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.024645318945957
      }
    },
    {
      "id": "2c57ec16eeace80afecaa144",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1414.9152644153683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.4886226535575,
        1420.3419061771792
      ],
      "voteCount": 16801,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.665952489817105
      }
    },
    {
      "id": "91489ebba45c4881de5ec8f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1402.4934006182236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.1371445675945,
        1410.849656668853
      ],
      "voteCount": 5425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.17721299198029
      }
    },
    {
      "id": "e03c43148047095fde372127",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1347.2200639227967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.6463798363452,
        1355.7937480092482
      ],
      "voteCount": 5251,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.13545406715817
      }
    },
    {
      "id": "6b89f04c87b29200731d1c2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1400.4755049031412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.140771402159,
        1413.8102384041235
      ],
      "voteCount": 2129,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.28843516018389
      }
    },
    {
      "id": "168a58890708cd93f0504b3f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1412.3179287179396,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.2522273062025,
        1421.3836301296767
      ],
      "voteCount": 4601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.394721620866385
      }
    },
    {
      "id": "b7262864c68d9dfb858d295f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1410.330008315524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.490775900633,
        1426.1692407304151
      ],
      "voteCount": 1437,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.30885666180406
      }
    },
    {
      "id": "a4a98a41690a77cebc98b19e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1427.6833419136033,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.0773083643162,
        1441.2893754628903
      ],
      "voteCount": 2037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.19110592753278
      }
    },
    {
      "id": "c11d98ec68954c7b054f88ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1433.1505798765602,
      "unit": "Arena rating",
      "confidenceInterval": [
        1426.7766988134968,
        1439.5244609396236
      ],
      "voteCount": 10506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.575763454035442
      }
    },
    {
      "id": "68429852722ba99360e2d05f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1366.5193099482096,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.6607196756459,
        1374.3779002207732
      ],
      "voteCount": 6282,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.076559441257494
      }
    },
    {
      "id": "fc41f147a9bdadf85c71714e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1390.987536562349,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.1237134663415,
        1397.8513596583568
      ],
      "voteCount": 8539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.264108426593898
      }
    },
    {
      "id": "3ffb576d637a8c0c759db1c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1330.1628120263372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.187615650058,
        1373.1380084026162
      ],
      "voteCount": 208,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 480.77243302221
      }
    },
    {
      "id": "a77fe01a449beba7c12e6553",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1348.9884234671927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.4273183105333,
        1377.549528623852
      ],
      "voteCount": 449,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.35076720732656
      }
    },
    {
      "id": "aa8c556a28333b3ee80d83a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1403.7883548336372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.0452381015252,
        1410.5314715657494
      ],
      "voteCount": 9872,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.836551004514961
      }
    },
    {
      "id": "ea1893bafff0c72c8f49df7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1401.7110380772667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.3499488357143,
        1416.0721273188192
      ],
      "voteCount": 1666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.68816739432511
      }
    },
    {
      "id": "4f0cec71a1191ba87e4093cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1394.9955859023946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1386.0430602443812,
        1403.948111560408
      ],
      "voteCount": 4793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.863874740926093
      }
    },
    {
      "id": "9fa2401a7468fe49828c551b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1396.4437483347833,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.0161148504928,
        1400.871381819074
      ],
      "voteCount": 27304,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.103253525875135
      }
    },
    {
      "id": "9a712b8f868684176d1f0a92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1377.14156559404,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.8456167136355,
        1388.4375144744442
      ],
      "voteCount": 2933,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.216147058854595
      }
    },
    {
      "id": "086c2aa5fdc3292f96af23e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-35b-a3b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1388.0755270009606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.0212731200663,
        1410.129780881855
      ],
      "voteCount": 810,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.61599068112693
      }
    },
    {
      "id": "4cc77884eae9d143558b7779",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1502.3130316418249,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.731610024677,
        1517.894453258973
      ],
      "voteCount": 1605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.20013071686718
      }
    },
    {
      "id": "10eccacfff0f00418774beb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1493.068742830325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.0744433246957,
        1500.0630423359542
      ],
      "voteCount": 8580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.73480410902998
      }
    },
    {
      "id": "14b04f9d5f8a0c8384dd5b1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1412.558199994298,
      "unit": "Arena rating",
      "confidenceInterval": [
        1403.717840391137,
        1421.3985595974593
      ],
      "voteCount": 4950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.344343532252484
      }
    },
    {
      "id": "5bec70745a4e02c53dc56d15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1453.7013216076773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.1770478598817,
        1459.225595355473
      ],
      "voteCount": 15219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.944273742096182
      }
    },
    {
      "id": "b2f8ad8d7cc916950a2096cc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1445.2426147416613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.332631308574,
        1451.1525981747488
      ],
      "voteCount": 22635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.092354183574644
      }
    },
    {
      "id": "d8b75bd4eefd5588e531aa93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1480.607524015158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.9745494393155,
        1492.2404985910007
      ],
      "voteCount": 2792,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.227788139544955
      }
    },
    {
      "id": "73f333ae24ec484e5e2dea13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1464.0756093835198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.2393897254713,
        1485.9118290415686
      ],
      "voteCount": 900,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.12484715074804
      }
    },
    {
      "id": "00ca2706b2537703b5bb7ec5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1434.7276980181873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.8259401068117,
        1460.629455929563
      ],
      "voteCount": 531,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 174.64746967619033
      }
    },
    {
      "id": "366598c8fa69f86fce1cab06",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1471.5320381170357,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.9565311456975,
        1478.1075450883739
      ],
      "voteCount": 9848,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.25543548643459
      }
    },
    {
      "id": "eaf17ceea38bd8fb985d81ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1465.2669864576583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.0817128645203,
        1470.4522600507962
      ],
      "voteCount": 19679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.999180126792501
      }
    },
    {
      "id": "ba2ae6f76b601520006528e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1441.1322351639337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.1766886419139,
        1449.0877816859538
      ],
      "voteCount": 6093,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.475699315862496
      }
    },
    {
      "id": "ae68cc306961ac26e65d9f84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1409.498170208868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.4855354181818,
        1417.5108049995545
      ],
      "voteCount": 6099,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.713003909623172
      }
    },
    {
      "id": "0c219cd55d1aa462c375cbc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1439.5620574578493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.0185162735258,
        1452.1055986421727
      ],
      "voteCount": 2325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.95850893811972
      }
    },
    {
      "id": "dd6311bb6bcd1f851ccc53ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1466.5897742101545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.1188765714571,
        1475.060671848852
      ],
      "voteCount": 5261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.679389824182604
      }
    },
    {
      "id": "e071037384f2b9ab0088ec61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1461.819184475379,
      "unit": "Arena rating",
      "confidenceInterval": [
        1447.4284978534786,
        1476.2098710972796
      ],
      "voteCount": 1733,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.90969189468667
      }
    },
    {
      "id": "286d12587cca1e126f94254c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1463.8185954252501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.1605109515497,
        1476.4766798989506
      ],
      "voteCount": 2378,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.70996228833278
      }
    },
    {
      "id": "0afef32a1111dfd3149b7aed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1483.671167190626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1477.662277165685,
        1489.6800572155669
      ],
      "voteCount": 12346,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.399231129935647
      }
    },
    {
      "id": "e7241c68d226cf39cfaeb581",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1426.7700563265646,
      "unit": "Arena rating",
      "confidenceInterval": [
        1419.383584980706,
        1434.156527672423
      ],
      "voteCount": 7268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.20292693215155
      }
    },
    {
      "id": "7d2c3a944fc4f3dcd25cee15",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1433.6072475517703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.112072103047,
        1440.1024230004934
      ],
      "voteCount": 9858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.982104996787008
      }
    },
    {
      "id": "282c9dfface1f444ebbc335f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1435.2955655707046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1395.8719137968703,
        1474.7192173445392
      ],
      "voteCount": 247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 404.5922113786237
      }
    },
    {
      "id": "a8edc1e82c414637b87b6f3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1393.1938572190218,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.1819623301035,
        1420.20575210794
      ],
      "voteCount": 484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.93890070078444
      }
    },
    {
      "id": "735ddddda468224c319b8be3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1454.4873746069195,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.1013857386806,
        1460.8733634751584
      ],
      "voteCount": 11640,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.615980992841262
      }
    },
    {
      "id": "4601c25e11af90e6c74010f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1445.6768273306373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.6634811059869,
        1458.6901735552874
      ],
      "voteCount": 2045,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.08408051918713
      }
    },
    {
      "id": "0ce8aace595f0ed3002810bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1451.7160667130172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.2614346081125,
        1460.1706988179217
      ],
      "voteCount": 5383,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.607723619009995
      }
    },
    {
      "id": "ed229b1920bc64717e839189",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1444.5543456071018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.3211608096844,
        1448.787530404519
      ],
      "voteCount": 31970,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.664856338573619
      }
    },
    {
      "id": "ab1c788b0050cde86ed28fc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1438.0021298179108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.579670368037,
        1448.4245892677848
      ],
      "voteCount": 3416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.277710644478184
      }
    },
    {
      "id": "30dc0cad92e3b8ff6b22f47e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-397b-a17b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1453.2413391161979,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.7080449320265,
        1472.7746333003695
      ],
      "voteCount": 1012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 99.32413686955678
      }
    },
    {
      "id": "e05a5ad81b42b2c8ddf3e4ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1458.8073799312297,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.964454029312,
        1474.6503058331473
      ],
      "voteCount": 1472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.33931843327612
      }
    },
    {
      "id": "a2f4677c05ed5cfe0382651b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1432.2252798899892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.0399018591315,
        1439.4106579208471
      ],
      "voteCount": 8187,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.44011737629536
      }
    },
    {
      "id": "3e2e128a62246b3cca5ffd22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1344.5600312273746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1335.0114103378605,
        1354.1086521168884
      ],
      "voteCount": 4292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.73477502882264
      }
    },
    {
      "id": "3a270987192a7cfdc8f00dad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1405.9978515302107,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.1229024109,
        1411.8728006495217
      ],
      "voteCount": 13230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.984874956502814
      }
    },
    {
      "id": "f5e8f9266094ac64072c2770",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1375.2946292605434,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.1971172078595,
        1381.3921413132273
      ],
      "voteCount": 21161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.678524479382043
      }
    },
    {
      "id": "a5c78b7429c6dc8c8c4d374b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1421.6543384967213,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.295485932931,
        1434.0131910605116
      ],
      "voteCount": 2444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.76125837160637
      }
    },
    {
      "id": "734073d2e78ace6e3d932e48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1411.2723105262237,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.23209911128,
        1433.3125219411675
      ],
      "voteCount": 908,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.45480321135933
      }
    },
    {
      "id": "a974b8ac0cffa5c217c248a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1378.0354879685783,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.0448273919042,
        1404.0261485452527
      ],
      "voteCount": 512,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 175.84841299686906
      }
    },
    {
      "id": "b82241f47653ca8ded823edc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1420.2549971447004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1413.270047198008,
        1427.239947091393
      ],
      "voteCount": 8717,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.70078062400926
      }
    },
    {
      "id": "3e0ef4c8d22a05348bca63b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1413.7849077759192,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.4159120145355,
        1419.153903537303
      ],
      "voteCount": 18302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.503950147914882
      }
    },
    {
      "id": "93aca6c2e7318d19c5102e78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1402.0041299020181,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.7528036780234,
        1410.2554561260129
      ],
      "voteCount": 5731,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.723575243865533
      }
    },
    {
      "id": "c129ce2de09abf11550c12c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1342.9874330149855,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.4446222916708,
        1351.5302437383002
      ],
      "voteCount": 5447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.99789076515322
      }
    },
    {
      "id": "9f15ae66a4658b590b4705db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1392.6847198994024,
      "unit": "Arena rating",
      "confidenceInterval": [
        1379.6201517640911,
        1405.7492880347138
      ],
      "voteCount": 2192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.43180274189441
      }
    },
    {
      "id": "6a4286e23266d4a18b8a5d17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1418.357760716353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.440925243608,
        1427.274596189098
      ],
      "voteCount": 4665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.69785426819601
      }
    },
    {
      "id": "7e61da42577471c2a06177fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1412.2601652701642,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.80028593169,
        1427.720044608638
      ],
      "voteCount": 1542,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.21799590109639
      }
    },
    {
      "id": "bd4adf4d7eb9c67d6f51f020",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1411.8887640102591,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.2631300961045,
        1425.5143979244137
      ],
      "voteCount": 2046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.330050699076025
      }
    },
    {
      "id": "b6ed5976b205755daf6b8e84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1429.1410196444322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1422.975754180607,
        1435.3062851082575
      ],
      "voteCount": 11730,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.894808200122124
      }
    },
    {
      "id": "26bbe593281eebb7d3761cea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1370.0246937007369,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.332279508448,
        1377.7171078930257
      ],
      "voteCount": 6571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.403844963001346
      }
    },
    {
      "id": "126b745345fd963ad5c02950",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1378.2922483082102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1371.5568833618795,
        1385.027613254541
      ],
      "voteCount": 9074,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.809352404319684
      }
    },
    {
      "id": "f2884d3d45fca8748fd47d2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1368.7286224017778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.4903420873352,
        1410.9669027162206
      ],
      "voteCount": 210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 464.42573178464323
      }
    },
    {
      "id": "52be5fe4702add2ee3563a31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1348.356413371884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1321.826524199672,
        1374.886302544096
      ],
      "voteCount": 529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.22076386665
      }
    },
    {
      "id": "da1e5821e2a485dc22ba5ccb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1400.8601959420819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1394.2126965970351,
        1407.5076952871286
      ],
      "voteCount": 10528,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.503246450111085
      }
    },
    {
      "id": "b408414b48adb4eb78142964",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1402.6715282166424,
      "unit": "Arena rating",
      "confidenceInterval": [
        1388.7884246597894,
        1416.5546317734954
      ],
      "voteCount": 1865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.173794219009196
      }
    },
    {
      "id": "6da5afaa9855bdc67cb1df33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1392.6722670553336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.9799349224402,
        1401.364599188227
      ],
      "voteCount": 5191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.66873561197739
      }
    },
    {
      "id": "db437e70d9370b516f042d43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1396.2186589070966,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.7947609610524,
        1400.6425568531406
      ],
      "voteCount": 29647,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.094646057790386
      }
    },
    {
      "id": "12952532fa30e3fc5386e237",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1383.6279168620372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.2353610469272,
        1394.0204726771472
      ],
      "voteCount": 3401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.115677249576798
      }
    },
    {
      "id": "bfdb57c059d0505febbc7bfc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-flash",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1405.6300571481972,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.0983423468665,
        1426.1617719495277
      ],
      "voteCount": 960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.73729834412462
      }
    },
    {
      "id": "ae9ea4d6a99952af1f41fcd6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1526.7193281132381,
      "unit": "Arena rating",
      "confidenceInterval": [
        1508.4515225358855,
        1544.9871336905908
      ],
      "voteCount": 1155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.87135179329015
      }
    },
    {
      "id": "e43fbcc6b56e49e2fd6488fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1514.0412049525091,
      "unit": "Arena rating",
      "confidenceInterval": [
        1505.6420727451034,
        1522.4403371599146
      ],
      "voteCount": 5491,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.364227011219626
      }
    },
    {
      "id": "4fc4ab9f09383ec0fa7f6f0e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1446.7858586289851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1435.53624741915,
        1458.03546983882
      ],
      "voteCount": 3016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.944190808631305
      }
    },
    {
      "id": "769599ca0490ee9641958153",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1474.5333748350968,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.8984663869633,
        1481.1682832832303
      ],
      "voteCount": 9483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.459711575708038
      }
    },
    {
      "id": "08dc4be39e4033e6e249059f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1474.2674991017439,
      "unit": "Arena rating",
      "confidenceInterval": [
        1467.2581870559004,
        1481.276811147587
      ],
      "voteCount": 14410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.789530657295316
      }
    },
    {
      "id": "cf327b9c620dc6298643abb8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1501.5180979741149,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.4693157339561,
        1515.5668802142734
      ],
      "voteCount": 1865,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.37847147239042
      }
    },
    {
      "id": "326eb9d70e4f58ca0ceb1e34",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1482.369869008047,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.2016599078763,
        1507.538078108218
      ],
      "voteCount": 631,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 164.8953636825565
      }
    },
    {
      "id": "f8123e7fec9ca1bc922bd4ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1459.1099213919515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1428.0662527696295,
        1490.1535900142737
      ],
      "voteCount": 368,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.87067349023678
      }
    },
    {
      "id": "700ba39c9228b793f2b0c368",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1495.0177894549156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1487.0241256686359,
        1503.0114532411953
      ],
      "voteCount": 6157,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.633956970684043
      }
    },
    {
      "id": "64112990e093de89bde4792f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1492.5285156704113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1486.4533736216438,
        1498.6036577191785
      ],
      "voteCount": 12597,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.607639346250492
      }
    },
    {
      "id": "b92c03fb626f1899af2ed1ed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1458.6689783666843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.9460537686027,
        1468.3919029647657
      ],
      "voteCount": 3960,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.60920893664439
      }
    },
    {
      "id": "1c6220f408a63fb50a64fb12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1443.8916682521876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.8342791228686,
        1453.9490573815065
      ],
      "voteCount": 3778,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.331422727646604
      }
    },
    {
      "id": "bb9f278b2225edcdb84975e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1468.791308845837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1453.7040664863873,
        1483.8785512052864
      ],
      "voteCount": 1555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.254802052423436
      }
    },
    {
      "id": "ca55b17dce6d85e0b90245ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1486.7267610666859,
      "unit": "Arena rating",
      "confidenceInterval": [
        1476.0397440720535,
        1497.413778061318
      ],
      "voteCount": 3238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.73149982196666
      }
    },
    {
      "id": "535ac0d439fc9d1804316431",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1492.793574446367,
      "unit": "Arena rating",
      "confidenceInterval": [
        1474.7464354725087,
        1510.8407134202255
      ],
      "voteCount": 1102,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.78529650954545
      }
    },
    {
      "id": "84c4ae61aa7d2c9aa38de278",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1488.3431958396693,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.3274244792763,
        1504.3589672000621
      ],
      "voteCount": 1445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.77279237944161
      }
    },
    {
      "id": "b41475bdd43148f05e936dff",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1500.7434275832431,
      "unit": "Arena rating",
      "confidenceInterval": [
        1493.5780639390828,
        1507.9087912274038
      ],
      "voteCount": 7849,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.36534856926546
      }
    },
    {
      "id": "b463a1e08afb1e90f2b62e19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1455.33128853459,
      "unit": "Arena rating",
      "confidenceInterval": [
        1446.2316320876337,
        1464.430944981546
      ],
      "voteCount": 4598,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.555287019233894
      }
    },
    {
      "id": "c145be74e438588e0091a525",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1470.662571589391,
      "unit": "Arena rating",
      "confidenceInterval": [
        1462.77641397562,
        1478.5487292031619
      ],
      "voteCount": 6316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.18954798479367
      }
    },
    {
      "id": "fa0ff1e57afbd72a3ce5b874",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1502.0068976506018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1451.7601389525219,
        1552.2536563486815
      ],
      "voteCount": 174,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 657.2338472202761
      }
    },
    {
      "id": "f70e0a49f80e78006c297dc9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1411.4575036014946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.2180790831549,
        1442.6969281198344
      ],
      "voteCount": 370,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.04454135492034
      }
    },
    {
      "id": "6615d8fa1e43508ed00e3dd3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1481.1833152436373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.5480333739094,
        1488.818597113365
      ],
      "voteCount": 7372,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.175882900564453
      }
    },
    {
      "id": "986c20d36e62b3495ebbb25e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1472.3372255467614,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.8535541967697,
        1488.8208968967533
      ],
      "voteCount": 1272,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.73131168576315
      }
    },
    {
      "id": "5f6881baffe30021a918b39d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1479.1452326116378,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.5720143535414,
        1489.7184508697342
      ],
      "voteCount": 3353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.10169015247761
      }
    },
    {
      "id": "1288161e8ea96056988f8972",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1465.542930057821,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.4614552768576,
        1470.6244048387846
      ],
      "voteCount": 20212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.72176565071255
      }
    },
    {
      "id": "7c516db671644b1fb57e4960",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1467.0092907259839,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.114875787348,
        1479.9037056646198
      ],
      "voteCount": 2141,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.281978115718545
      }
    },
    {
      "id": "d69d3956290e96c612400fee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.5-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1451.2949620547708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.9229380227905,
        1474.666986086751
      ],
      "voteCount": 673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.19897514162557
      }
    },
    {
      "id": "b47d2eee7c4840fb2bf09a53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1494.9731939510707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.7051663267896,
        1529.2412215753518
      ],
      "voteCount": 283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 305.69056498340996
      }
    },
    {
      "id": "40ebfb740e2a1bf4314397e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1505.6611240908692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1489.2747396541763,
        1522.047508527562
      ],
      "voteCount": 1327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.89886067777057
      }
    },
    {
      "id": "d1ad06685db0b69e8694ddef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1432.092150251129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1408.648458985111,
        1455.5358415171472
      ],
      "voteCount": 666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.07238104847573
      }
    },
    {
      "id": "fd12fa0fe3ecbc0687ec65e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1462.8384737199624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.193487224329,
        1475.4834602155956
      ],
      "voteCount": 2104,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.623688014923836
      }
    },
    {
      "id": "2b9c375b903d2143709d5e1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1461.9053935926395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.753189623514,
        1474.0575975617653
      ],
      "voteCount": 3338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.44270320215192
      }
    },
    {
      "id": "fd8fef19599eaea7284bce53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1497.0556351589494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1470.5418863154573,
        1523.5693840024412
      ],
      "voteCount": 469,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.9978949530294
      }
    },
    {
      "id": "3df5515c618817a5faf7a9fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1477.457589770104,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.73722848441,
        1493.1779510557978
      ],
      "voteCount": 1394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.33226815329729
      }
    },
    {
      "id": "f26c8d3d1f10f6dfdf16355c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1479.3157927432362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.3948825333841,
        1490.2367029530883
      ],
      "voteCount": 2939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.047132190812025
      }
    },
    {
      "id": "3e1a1ec1184669521552133d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1449.9108017801395,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.0409703127373,
        1469.7806332475416
      ],
      "voteCount": 883,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.77611214159155
      }
    },
    {
      "id": "25c0cc74d7eb9bb78cb3f9ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1427.9563975817416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.353726855883,
        1448.5590683076
      ],
      "voteCount": 826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.49709520547367
      }
    },
    {
      "id": "d74466f63a59a9390535bcc0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1453.0413261868534,
      "unit": "Arena rating",
      "confidenceInterval": [
        1420.3924198654038,
        1485.690232508303
      ],
      "voteCount": 330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 277.4860108468356
      }
    },
    {
      "id": "4dfc6843e117bc2b0ad1ce5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1487.3109599832198,
      "unit": "Arena rating",
      "confidenceInterval": [
        1466.569214403338,
        1508.0527055631017
      ],
      "voteCount": 773,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.9939142345947
      }
    },
    {
      "id": "609acc7b23837e642184fa3b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1504.9938129474003,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.524872271949,
        1537.4627536228518
      ],
      "voteCount": 308,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 274.4353532847412
      }
    },
    {
      "id": "c1a94c55667411466f5c6b2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1490.5424220922994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1457.5427084182807,
        1523.542135766318
      ],
      "voteCount": 319,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 283.4811339642188
      }
    },
    {
      "id": "bdde90dc244f02190de8c490",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1492.3107087341784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1478.7155233552598,
        1505.905894113097
      ],
      "voteCount": 1884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.11429045951979
      }
    },
    {
      "id": "94931e4727bbbf3699efd321",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1452.487104174264,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.544550130947,
        1471.429658217581
      ],
      "voteCount": 989,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.40731488542814
      }
    },
    {
      "id": "a5988c5a2df6e882657b862e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1448.3497062721162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.465187980932,
        1463.2342245633006
      ],
      "voteCount": 1511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.67311198732838
      }
    },
    {
      "id": "e2c5c2172247bc562139129f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1469.9541323147068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1455.4656310496819,
        1484.4426335797318
      ],
      "voteCount": 1760,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.645039477137914
      }
    },
    {
      "id": "6a7f5c08ebe200caf36c0350",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1491.6320765692108,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.7479603680974,
        1522.5161927703239
      ],
      "voteCount": 327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.29854439296406
      }
    },
    {
      "id": "64e9d28b4ae2eb4490a26428",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1466.2082556844387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1444.4098722323236,
        1488.0066391365538
      ],
      "voteCount": 742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.69507088444654
      }
    },
    {
      "id": "a59c39f3452d72b34bc38919",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1459.0448829722452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.4012335795965,
        1467.688532364894
      ],
      "voteCount": 4648,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.449037022226552
      }
    },
    {
      "id": "268bbe7c39fb941586db7f7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1454.772213619392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1427.7474174475153,
        1481.7970097912687
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.12037931972722
      }
    },
    {
      "id": "2a28cc4edca6895d8e86f3e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1452.9900404417979,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.385413292514,
        1491.5946675910818
      ],
      "voteCount": 224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 387.9560622404233
      }
    },
    {
      "id": "6181c06d9c927e3159176006",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1483.5634283637014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.126713845594,
        1504.0001428818089
      ],
      "voteCount": 902,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 108.7241383519906
      }
    },
    {
      "id": "cbab9cd6e4da312914a25ca6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1491.7413749176649,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.1475645660144,
        1500.3351852693154
      ],
      "voteCount": 5403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.22539842475515
      }
    },
    {
      "id": "a434ac027acb0c258ea7eb9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1404.5712354411824,
      "unit": "Arena rating",
      "confidenceInterval": [
        1392.4073846586268,
        1416.7350862237377
      ],
      "voteCount": 2560,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.51642638031392
      }
    },
    {
      "id": "3821477271c4b0378a26f612",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1455.0294768509636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1448.0741214381312,
        1461.9848322637959
      ],
      "voteCount": 8303,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.593384747015197
      }
    },
    {
      "id": "e1b8af4c82cb485961d38ec9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1444.1611589207027,
      "unit": "Arena rating",
      "confidenceInterval": [
        1437.131499789462,
        1451.1908180519436
      ],
      "voteCount": 13424,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.863890987254713
      }
    },
    {
      "id": "15c787d01c5c17168ec5bf49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1474.0994012517476,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.2540701375046,
        1488.9447323659906
      ],
      "voteCount": 1635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.369834268245484
      }
    },
    {
      "id": "cf89794ee0ea1978694b76b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1489.233335628723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.850559148285,
        1514.616112109161
      ],
      "voteCount": 628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 167.7189244838648
      }
    },
    {
      "id": "5cd1c08a47dc464d6483da12",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1450.652523867926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.397198025921,
        1483.9078497099308
      ],
      "voteCount": 290,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 287.8897701311524
      }
    },
    {
      "id": "ab97d9debd420014f1e17e39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1472.014030540986,
      "unit": "Arena rating",
      "confidenceInterval": [
        1463.695848927884,
        1480.3322121540875
      ],
      "voteCount": 5751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.011945091224835
      }
    },
    {
      "id": "e597d61360ab04a4bf615f22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1466.4929625650386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1460.2307066490662,
        1472.755218481011
      ],
      "voteCount": 11934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.208582465045453
      }
    },
    {
      "id": "55c1bea68bab009e2e9c8f93",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1448.9135358348549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.709265794988,
        1459.1178058747219
      ],
      "voteCount": 3708,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.106141678674465
      }
    },
    {
      "id": "ca83359ccf722dcc1bcfa931",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1407.2979484456735,
      "unit": "Arena rating",
      "confidenceInterval": [
        1396.8703589147106,
        1417.7255379766364
      ],
      "voteCount": 3536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.30555486902237
      }
    },
    {
      "id": "a8d98767c51d4a7940b390c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1449.5987037426657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.7332797341187,
        1466.4641277512128
      ],
      "voteCount": 1318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.0454447814897
      }
    },
    {
      "id": "5090caf3f2213bbf49f1d071",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1449.4167195457742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.1833039617711,
        1460.6501351297773
      ],
      "voteCount": 2957,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.84940216022437
      }
    },
    {
      "id": "55fee9c75d60079caf0cbb28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1460.9444418831888,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.6743165756677,
        1479.2145671907099
      ],
      "voteCount": 1048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.89341584357004
      }
    },
    {
      "id": "18ef8a68c19b8769300fadf7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1467.2024293031848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.7982691428956,
        1484.606589463474
      ],
      "voteCount": 1235,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.85150017832635
      }
    },
    {
      "id": "ca8001fdb8be04f0caf780be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1479.7030817697878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1472.3162278706238,
        1487.089935668952
      ],
      "voteCount": 7473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.204398140010634
      }
    },
    {
      "id": "c70887370bae58309e7ff5e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1424.1016531468292,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.4211331193085,
        1433.78217317435
      ],
      "voteCount": 4070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.395020844267567
      }
    },
    {
      "id": "fe316d48dd361a9a169e942f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1438.3611342339466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1430.2614149265903,
        1446.460853541303
      ],
      "voteCount": 6020,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.07826529456512
      }
    },
    {
      "id": "7b119352c694db45ebcbe42c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1429.0548771695483,
      "unit": "Arena rating",
      "confidenceInterval": [
        1376.6649409282686,
        1481.444813410828
      ],
      "voteCount": 130,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 714.4955985417514
      }
    },
    {
      "id": "0e0f3e646e77608e96d6ee92",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1394.144738950653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.793816045928,
        1426.4956618553779
      ],
      "voteCount": 334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.44394945729226
      }
    },
    {
      "id": "59a58259b3490b7bed891706",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1453.1167953244012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1445.3550473032517,
        1460.878543345551
      ],
      "voteCount": 7213,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.682774476009104
      }
    },
    {
      "id": "7d52203fdd179b2836ba5b83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1456.3016103800708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1438.79620344125,
        1473.8070173188914
      ],
      "voteCount": 1112,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 79.7715884504367
      }
    },
    {
      "id": "9329d920bc0af2fffd99e037",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1440.3924730653757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.2993378766764,
        1451.485608254075
      ],
      "voteCount": 3172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.03409279095755
      }
    },
    {
      "id": "f9ba31322c1d3c3a2366f764",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1444.3140536590702,
      "unit": "Arena rating",
      "confidenceInterval": [
        1439.0574339733794,
        1449.570673344761
      ],
      "voteCount": 18202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.193113816849329
      }
    },
    {
      "id": "34cff4598e9f0805797b73f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1438.7994356136453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1425.1124633662814,
        1452.4864078610094
      ],
      "voteCount": 1974,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.76616359674097
      }
    },
    {
      "id": "45989f0d281393b593d77fc4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.6-plus",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1439.156775465126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1414.8436972945794,
        1463.4698536356723
      ],
      "voteCount": 637,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 153.88054323078373
      }
    },
    {
      "id": "6f73e64ab2dac096b033df78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1528.7988438650796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1490.7061694674555,
        1566.8915182627038
      ],
      "voteCount": 268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 377.7345822234308
      }
    },
    {
      "id": "440c62ba7ff6f7eaa623459a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1525.3701283292958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1507.0003276676123,
        1543.7399289909793
      ],
      "voteCount": 1137,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.84412175190549
      }
    },
    {
      "id": "b4c20c0e7b9d1a05623d0f6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1442.9271349353814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.1965607666175,
        1470.6577091041456
      ],
      "voteCount": 496,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.1803949027826
      }
    },
    {
      "id": "8b5da6fbb01de0785a1f3fe7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1475.5813765139217,
      "unit": "Arena rating",
      "confidenceInterval": [
        1461.3962714663044,
        1489.766481561539
      ],
      "voteCount": 1829,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.38041447378531
      }
    },
    {
      "id": "c82e8c440e50cd6fae18d3b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1481.8313819565928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1468.6242791895575,
        1495.0384847236282
      ],
      "voteCount": 2895,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.40659464039637
      }
    },
    {
      "id": "545d522ce952636cbf5fc6c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1508.4002770439383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1475.5998793019724,
        1541.2006747859043
      ],
      "voteCount": 345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.0670636466079
      }
    },
    {
      "id": "e47cd213d536944fa8418040",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1490.5196414605846,
      "unit": "Arena rating",
      "confidenceInterval": [
        1473.4880218283276,
        1507.5512610928415
      ],
      "voteCount": 1312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.5119554413095
      }
    },
    {
      "id": "383aa43d9c2fe94cae78f321",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1495.239734739677,
      "unit": "Arena rating",
      "confidenceInterval": [
        1483.0330765342924,
        1507.446392945062
      ],
      "voteCount": 2558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.78799994949919
      }
    },
    {
      "id": "f7dd951299053dcffbcb50c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1455.8037674126565,
      "unit": "Arena rating",
      "confidenceInterval": [
        1434.7167422425277,
        1476.8907925827853
      ],
      "voteCount": 838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.75358510423779
      }
    },
    {
      "id": "fff29a477d09d15e11fec11f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1439.7768875442996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1416.6712493987761,
        1462.8825256898228
      ],
      "voteCount": 691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.9759825709643
      }
    },
    {
      "id": "77b2e11127e04ac4e8bcaef9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1477.866538896701,
      "unit": "Arena rating",
      "confidenceInterval": [
        1442.6645857834153,
        1513.068492009987
      ],
      "voteCount": 292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 322.5799262286684
      }
    },
    {
      "id": "58c0835a2566a421c44b1c7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1482.8582857084923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1459.4395136533815,
        1506.277057763603
      ],
      "voteCount": 664,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.76838830466423
      }
    },
    {
      "id": "e0859e7a954dddd096e040e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1472.6307664040492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.5987278457562,
        1512.662804962342
      ],
      "voteCount": 227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 417.1759182994659
      }
    },
    {
      "id": "281ae7b39ba6ba8e3efe3ee2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1478.818396522248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1443.6846817101264,
        1513.9521113343692
      ],
      "voteCount": 297,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 321.33050856873194
      }
    },
    {
      "id": "a293f799640d5461b7ca6b8a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1513.2999813705062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1497.7530300563783,
        1528.846932684634
      ],
      "voteCount": 1570,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.92080859015681
      }
    },
    {
      "id": "844c496611805f3af5ac6aca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1453.6269062690703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1432.7351048492342,
        1474.5187076889065
      ],
      "voteCount": 866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.62021225233421
      }
    },
    {
      "id": "607e265cbafc9228944550a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1467.770620461351,
      "unit": "Arena rating",
      "confidenceInterval": [
        1450.716729118632,
        1484.82451180407
      ],
      "voteCount": 1307,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.70957375945889
      }
    },
    {
      "id": "0e0c68176dc82847813e6518",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1494.9428337196186,
      "unit": "Arena rating",
      "confidenceInterval": [
        1479.2214812572802,
        1510.6641861819571
      ],
      "voteCount": 1625,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.3403807724311
      }
    },
    {
      "id": "61d609c5ec786c7195d8a334",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1495.019046782863,
      "unit": "Arena rating",
      "confidenceInterval": [
        1454.971481723636,
        1535.06661184209
      ],
      "voteCount": 220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 417.49958597323064
      }
    },
    {
      "id": "d295e5c25fd1db79c29b5716",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1481.5719594046739,
      "unit": "Arena rating",
      "confidenceInterval": [
        1458.044116630024,
        1505.0998021793237
      ],
      "voteCount": 660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.10134573006198
      }
    },
    {
      "id": "201f8181e03f724dc9baff80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1474.7184047938392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1464.728417958788,
        1484.7083916288902
      ],
      "voteCount": 3755,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.979671167335542
      }
    },
    {
      "id": "b9c614c564cee098f14ada05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwen3.7-max-preview",
      "organization": "alibaba",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1482.027513683334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1449.8289158242287,
        1514.2261115424396
      ],
      "voteCount": 381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 269.88437270428943
      }
    },
    {
      "id": "671563de9322e109f3bf732c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1235.946378087988,
      "unit": "Arena rating",
      "confidenceInterval": [
        1195.9971712412657,
        1275.8955849347103
      ],
      "voteCount": 206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 415.4513173705809
      }
    },
    {
      "id": "c233c3a11804890bb9f8c77e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1172.9340992299683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.7358482569418,
        1197.1323502029948
      ],
      "voteCount": 566,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.43046391624995
      }
    },
    {
      "id": "82142a9dba968e0fbd4d5c58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1106.930187759832,
      "unit": "Arena rating",
      "confidenceInterval": [
        1077.51944009029,
        1136.3409354293742
      ],
      "voteCount": 454,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 225.1728103453108
      }
    },
    {
      "id": "7385a366d7ff884c76cba23c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1175.6543812808568,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.9500723172657,
        1190.3586902444479
      ],
      "voteCount": 1783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.28505007836501
      }
    },
    {
      "id": "6b0eb6910c0e03e2da5bd13d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1012.3030403739915,
      "unit": "Arena rating",
      "confidenceInterval": [
        993.7176177322538,
        1030.8884630157295
      ],
      "voteCount": 2230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.91842705985489
      }
    },
    {
      "id": "f83477dbb79216fc1e881d74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1152.2535080630014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.5738033190771,
        1187.9332128069254
      ],
      "voteCount": 232,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.395282374411
      }
    },
    {
      "id": "975b8e9242b95c1e475c30b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1176.601484046239,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.6909239437678,
        1201.5120441487104
      ],
      "voteCount": 519,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.5365499367009
      }
    },
    {
      "id": "e2feeb4e472c28bbb93c8470",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1168.0279586742706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.6282249407623,
        1187.4276924077792
      ],
      "voteCount": 852,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.9705071686866
      }
    },
    {
      "id": "3efe3393dab3131a9c13167f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1106.7542797401825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.4400781499098,
        1139.0684813304554
      ],
      "voteCount": 374,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 271.82580190410744
      }
    },
    {
      "id": "813e0cc9013d7c1e9f1ad8fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1103.2551695712425,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.2743665722774,
        1130.2359725702077
      ],
      "voteCount": 540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.50189614096345
      }
    },
    {
      "id": "799ff3e84f36256a9c3c2757",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1154.9335575271296,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.5443957795305,
        1197.3227192747288
      ],
      "voteCount": 214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 467.7496538514113
      }
    },
    {
      "id": "a1158268e9526ba09657f988",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1159.281438066583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.5688966269404,
        1184.9939795062255
      ],
      "voteCount": 583,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 172.10513457121263
      }
    },
    {
      "id": "6a23a35393daeec5d91d5dbd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1221.125869026443,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.658457851399,
        1247.5932802014877
      ],
      "voteCount": 422,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.35880872524527
      }
    },
    {
      "id": "ce75d4e7f4b03fdddac1f8a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1166.6927829493202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.0001931988968,
        1187.3853726997436
      ],
      "voteCount": 824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.46371484517414
      }
    },
    {
      "id": "8526b2fb30f4c12b23a50366",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1115.1836745952965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1094.090385194169,
        1136.276963996424
      ],
      "voteCount": 855,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 115.82236814901552
      }
    },
    {
      "id": "5ceb305b756dc4f32fbdc769",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1147.0771985480997,
      "unit": "Arena rating",
      "confidenceInterval": [
        1131.1039532479606,
        1163.0504438482385
      ],
      "voteCount": 1329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.41866471246128
      }
    },
    {
      "id": "d8d3139b0563483e42b83681",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1178.3111150666828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.0431630915455,
        1204.5790670418205
      ],
      "voteCount": 475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 179.62064235884512
      }
    },
    {
      "id": "a9cd9d0d41b23da0178a55e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1212.7947050307796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.3686248100953,
        1237.220785251464
      ],
      "voteCount": 480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 155.31427585093851
      }
    },
    {
      "id": "1cf2716adbb30a18a56facb2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1144.2047150754447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.1322346978,
        1171.277195453089
      ],
      "voteCount": 487,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.7918913121428
      }
    },
    {
      "id": "c764a3edaffe26c11dfe4aa8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1155.4245313226554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.9316447613046,
        1166.9174178840062
      ],
      "voteCount": 3231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.38444811656575
      }
    },
    {
      "id": "fa668f8ffcc576eab4660697",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b-preview",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1112.9252770686235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.5248191700869,
        1139.32573496716
      ],
      "voteCount": 527,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 181.4373678816283
      }
    },
    {
      "id": "0f4a03120ebeb28ed2fccee0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1382.6661467987906,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.6666705183811,
        1398.6656230792
      ],
      "voteCount": 1352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.63698693537667
      }
    },
    {
      "id": "5e82b7875bc681151809afe2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1384.6978137937754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.7147520633137,
        1393.6808755242369
      ],
      "voteCount": 4046,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.006446201785035
      }
    },
    {
      "id": "20f50e86a85b422f2400aaef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1294.7951783221588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.9162178198635,
        1304.674138824454
      ],
      "voteCount": 3684,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.405416317407955
      }
    },
    {
      "id": "5cbd545de3288439166bc78e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1358.7418484091868,
      "unit": "Arena rating",
      "confidenceInterval": [
        1353.156500264994,
        1364.32719655338
      ],
      "voteCount": 13693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.120902851746107
      }
    },
    {
      "id": "54d46923c2bf37f3e86781c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1289.1307647132444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.6233190489402,
        1295.6382103775488
      ],
      "voteCount": 17292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.023637386335688
      }
    },
    {
      "id": "461516ee1b711d6c3dd24c1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1362.3384006607776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.6516399901739,
        1379.0251613313812
      ],
      "voteCount": 1199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.48495810445665
      }
    },
    {
      "id": "3e527efe39386cdb5e85da5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1348.2985375396947,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.5270215863768,
        1382.070053493013
      ],
      "voteCount": 286,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 296.89639874341583
      }
    },
    {
      "id": "8e8bbb709d1e3306cf6fe196",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1302.7185330348932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.7405763816148,
        1325.6964896881716
      ],
      "voteCount": 646,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.44426703617168
      }
    },
    {
      "id": "9099fa87fb6036c130137ade",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1372.6566429621303,
      "unit": "Arena rating",
      "confidenceInterval": [
        1364.4796185009743,
        1380.833667423286
      ],
      "voteCount": 5076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.405816945932802
      }
    },
    {
      "id": "9a7cbf7364b173bb5597af95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1356.8570926554,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.3695056078386,
        1363.3446797029612
      ],
      "voteCount": 8826,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.956458903828484
      }
    },
    {
      "id": "f7aeb7d2213dfb68ecb5bab1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1337.993813679202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.1093752517654,
        1347.8782521066387
      ],
      "voteCount": 3492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.43359894930076
      }
    },
    {
      "id": "1ef94f2bc5b64c4736c4650d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1286.7305635704636,
      "unit": "Arena rating",
      "confidenceInterval": [
        1277.9889572919153,
        1295.4721698490116
      ],
      "voteCount": 4467,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.892359620646793
      }
    },
    {
      "id": "43c8d90bd13a52586eb1b643",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1339.3097131665236,
      "unit": "Arena rating",
      "confidenceInterval": [
        1324.7472909417245,
        1353.872135391323
      ],
      "voteCount": 1639,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.20406464099646
      }
    },
    {
      "id": "052aff4a93280f646399607a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1352.2533735345592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.3245422609268,
        1361.1822048081917
      ],
      "voteCount": 4544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.753581291440383
      }
    },
    {
      "id": "cf33cd1a84a70e776430c589",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1365.1877930276244,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.8968544605088,
        1379.4787315947399
      ],
      "voteCount": 1579,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.164939326921235
      }
    },
    {
      "id": "f131e93899f3fbf37e81c918",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1356.0007853773445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.0170333334063,
        1371.9845374212825
      ],
      "voteCount": 1364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.50607004448696
      }
    },
    {
      "id": "bbe284d89cf0f5096da3348b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1377.4267466663343,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.421629325137,
        1384.4318640075317
      ],
      "voteCount": 7458,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.774227514711239
      }
    },
    {
      "id": "92a925051e047123ee629763",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1308.4001683735587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.7824530895923,
        1316.017883657525
      ],
      "voteCount": 6159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.10613255437411
      }
    },
    {
      "id": "accf7530bd779d809f993dc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1323.8533252233667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1316.8427461524723,
        1330.8639042942611
      ],
      "voteCount": 7173,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.794154825895767
      }
    },
    {
      "id": "35abe9eb8f51b404e7d02f80",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1249.3154978115524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.4806438658093,
        1275.1503517572955
      ],
      "voteCount": 571,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 173.74640977598318
      }
    },
    {
      "id": "cfff0776d68bf4cab8bbec85",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1278.109739147113,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.5571988639074,
        1308.6622794303184
      ],
      "voteCount": 396,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 242.9956329945069
      }
    },
    {
      "id": "81cddfb7f9a9fec2eebe66eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1336.064934963907,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.839092115441,
        1345.2907778123727
      ],
      "voteCount": 4025,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.157253334609155
      }
    },
    {
      "id": "d698d27675669dfdf4b6e96b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1364.089507236034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.4935938431377,
        1377.6854206289308
      ],
      "voteCount": 1720,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.11944357996429
      }
    },
    {
      "id": "7f2f5e93926a105bceba24e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1322.5099596177402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.0473956873714,
        1331.9725235481092
      ],
      "voteCount": 3839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.308883503829552
      }
    },
    {
      "id": "4e21dab95b52f45aff287f01",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1336.0916888818983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.6594533250814,
        1340.5239244387158
      ],
      "voteCount": 25402,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.113867660193845
      }
    },
    {
      "id": "ede881ef84880f02fec8f9a1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1305.0465056740875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1291.8673892817092,
        1318.2256220664658
      ],
      "voteCount": 1916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.21436178052603
      }
    },
    {
      "id": "ac15b736e5b520af823339dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "qwq-32b",
      "organization": "alibaba",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1345.4207226689873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.8987263095396,
        1376.942719028435
      ],
      "voteCount": 348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 258.661175575348
      }
    },
    {
      "id": "fb9f028bffa6c05d72de1b2f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1304.1364654505346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1281.0448506359166,
        1327.228080265153
      ],
      "voteCount": 598,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.80733847105068
      }
    },
    {
      "id": "b45c659a05ba9d0705ba6775",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1315.0944409925994,
      "unit": "Arena rating",
      "confidenceInterval": [
        1299.7071763759427,
        1330.481705609256
      ],
      "voteCount": 1216,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.63489534432505
      }
    },
    {
      "id": "f7807c21261e0d25daeba279",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1267.4605908961694,
      "unit": "Arena rating",
      "confidenceInterval": [
        1249.103928439365,
        1285.8172533529737
      ],
      "voteCount": 1037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.71851327360113
      }
    },
    {
      "id": "c83ff10cd42cdae13eb01d64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1291.8925856811654,
      "unit": "Arena rating",
      "confidenceInterval": [
        1282.4619991354903,
        1301.3231722268406
      ],
      "voteCount": 3934,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.15161160035511
      }
    },
    {
      "id": "f1b4cdc09d20db7fc7f1ed82",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1212.5766160820945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.7626631273888,
        1224.3905690368001
      ],
      "voteCount": 4480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.33241717030296
      }
    },
    {
      "id": "eaf8b1fb2d6b8525fbb410a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1287.869492125898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.2239729480848,
        1312.5150113037112
      ],
      "voteCount": 458,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 158.117435041046
      }
    },
    {
      "id": "09eec38478342cb184ee0dc5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1281.4100629683587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.0729848878666,
        1322.7471410488508
      ],
      "voteCount": 183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 444.81903984693594
      }
    },
    {
      "id": "84a09e83de3b98d32d4b57f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1281.6316768890238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1267.3309714332727,
        1295.9323823447744
      ],
      "voteCount": 1341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.23763342989298
      }
    },
    {
      "id": "01c2d47c1d5961262b53e7bc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1280.043148807048,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.4547369986783,
        1291.6315606154178
      ],
      "voteCount": 2145,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.95840890365156
      }
    },
    {
      "id": "88ba71d01c1c53a97800c91d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1281.0560455001664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.4313056177439,
        1300.680785382589
      ],
      "voteCount": 837,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.25629153644144
      }
    },
    {
      "id": "2503af56dec196d6d4fcf476",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1246.4567508873429,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.2087981809368,
        1263.7047035937487
      ],
      "voteCount": 1092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.44242134259257
      }
    },
    {
      "id": "188ef1f67a6c3ae80fad0721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1329.2383749744124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1300.3287494776682,
        1358.1480004711564
      ],
      "voteCount": 371,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 217.56485891757578
      }
    },
    {
      "id": "5e689726499dc3256722d027",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1320.834279484103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1304.4342472274966,
        1337.2343117407095
      ],
      "voteCount": 1183,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.01534327761661
      }
    },
    {
      "id": "283e385cd70b4acb32665ace",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1269.2568973609555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1253.706491979079,
        1284.8073027428318
      ],
      "voteCount": 1039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.948769940736994
      }
    },
    {
      "id": "013d2f7c02c3ac17b5313fcb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1345.3317981512655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.6035754139716,
        1375.0600208885594
      ],
      "voteCount": 364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.06031520037848
      }
    },
    {
      "id": "6ca9df74ed46e728ca3cae5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1301.0497143275056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.43172477601,
        1313.6677038790012
      ],
      "voteCount": 2006,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.446145267512115
      }
    },
    {
      "id": "ef38a324993d0af618b84904",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1271.4142751531704,
      "unit": "Arena rating",
      "confidenceInterval": [
        1257.8470424178272,
        1284.9815078885135
      ],
      "voteCount": 1890,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.91664122582054
      }
    },
    {
      "id": "8ab24de8710b9c65a010d65a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1260.683192939463,
      "unit": "Arena rating",
      "confidenceInterval": [
        1250.4932919808098,
        1270.8730938981162
      ],
      "voteCount": 3118,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.029856727293826
      }
    },
    {
      "id": "c440c21bc270c91a9e3327fb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1278.5273765879747,
      "unit": "Arena rating",
      "confidenceInterval": [
        1260.288515456194,
        1296.766237719755
      ],
      "voteCount": 951,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.59628305588973
      }
    },
    {
      "id": "39ed115d3737c140e7faa847",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1245.4477863491197,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.1238681158436,
        1259.7717045823956
      ],
      "voteCount": 1207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.41060340105453
      }
    },
    {
      "id": "86347e213c1221322ffdf21d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1264.350894464103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.07531697081,
        1280.626471957396
      ],
      "voteCount": 1255,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.95672584414707
      }
    },
    {
      "id": "b4a9a61bb7d90f6f1eef217d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1287.5847444517856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1280.4074455662947,
        1294.7620433372765
      ],
      "voteCount": 7312,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.40991058244929
      }
    },
    {
      "id": "746a3fa713c93e41632bfc24",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-core-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1293.66754993317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.767990525117,
        1311.5671093412234
      ],
      "voteCount": 976,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.40431121542846
      }
    },
    {
      "id": "bfc2aa61301cea007c5ae80a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1297.246264159502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1274.0252900114122,
        1320.4672383075922
      ],
      "voteCount": 607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.3668932962393
      }
    },
    {
      "id": "c1460013d714884562071b74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1290.44453860138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.1709500456275,
        1305.7181271571324
      ],
      "voteCount": 1207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.72758247822599
      }
    },
    {
      "id": "e823de95523ea2b53da763cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1242.3811770028362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1224.8447014192066,
        1259.917652586466
      ],
      "voteCount": 1037,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.05499739801344
      }
    },
    {
      "id": "e2954933c458dd2cd874d9aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1275.4849983500703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.306961167183,
        1284.6630355329576
      ],
      "voteCount": 4032,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.928223225165237
      }
    },
    {
      "id": "91fab4fc5ad25b80d5486165",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1178.0701590434069,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.9647353952191,
        1190.1755826915946
      ],
      "voteCount": 4562,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.14729990405709
      }
    },
    {
      "id": "0f764cd5deeb5c9c5286a696",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1271.948037857212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.7630387893964,
        1295.133036925028
      ],
      "voteCount": 493,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.93230355062965
      }
    },
    {
      "id": "c9dc0769a051ffd2259bb132",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1227.9395487622114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.5579611968412,
        1267.3211363275814
      ],
      "voteCount": 207,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 403.7292891997383
      }
    },
    {
      "id": "139b9f48109f28a8357374db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1270.3866790555062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.4221524602758,
        1284.3512056507368
      ],
      "voteCount": 1389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.76404879791599
      }
    },
    {
      "id": "06c8d4d991ae9ff8c363f909",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1266.3265186586461,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.075323693025,
        1277.5777136242673
      ],
      "voteCount": 2289,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.953467435983804
      }
    },
    {
      "id": "d3df2c81a30e97a2ff6e1abd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1267.146081637406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1248.4278146160914,
        1285.8643486587205
      ],
      "voteCount": 904,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 91.20845403671987
      }
    },
    {
      "id": "bd0aeb7a2cbbc7dae029fc52",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1227.345386483336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.5834399273429,
        1244.1073330393288
      ],
      "voteCount": 1115,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.13962363266884
      }
    },
    {
      "id": "c6566ddc7e55caef6f469618",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1286.1628902280881,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.3630729560084,
        1315.962707500168
      ],
      "voteCount": 414,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 231.1697589117689
      }
    },
    {
      "id": "a12767a8a3aa0af2488534a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1295.5978872390638,
      "unit": "Arena rating",
      "confidenceInterval": [
        1279.5880112779496,
        1311.607763200178
      ],
      "voteCount": 1277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.7236433485824
      }
    },
    {
      "id": "472921bc3f413914dec888a4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1244.9922236213442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.7291188288686,
        1260.2553284138196
      ],
      "voteCount": 1109,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.644244486262885
      }
    },
    {
      "id": "235ae1e49a878c98e665c6d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1284.602959096077,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.398500494725,
        1312.8074176974292
      ],
      "voteCount": 390,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 207.08057072225657
      }
    },
    {
      "id": "893b04f425491907608b4c45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1285.2554283517247,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.72590503475,
        1297.7849516686993
      ],
      "voteCount": 1975,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.86701481866812
      }
    },
    {
      "id": "4a83d730eb3abbb6e821e7a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1257.7767618240887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.716210682851,
        1270.837312965326
      ],
      "voteCount": 1950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.40448383670511
      }
    },
    {
      "id": "10db9218c6a84a253f57877b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1247.190019496352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1237.1092742672438,
        1257.2707647254606
      ],
      "voteCount": 3246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.453862742651705
      }
    },
    {
      "id": "ab6580649b10e7bf02ba15c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1262.6633777867148,
      "unit": "Arena rating",
      "confidenceInterval": [
        1244.8663242794603,
        1280.4604312939696
      ],
      "voteCount": 992,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.45177895278076
      }
    },
    {
      "id": "4d18edfb3ee2a8fcf1736c76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1231.671072308781,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.5960258303892,
        1245.7461187871727
      ],
      "voteCount": 1284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.57075543844946
      }
    },
    {
      "id": "de1b85767ed926927e2eef6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1236.3619844782006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.3759775935123,
        1252.3479913628887
      ],
      "voteCount": 1302,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.52483549755331
      }
    },
    {
      "id": "6b39e02cf584943778ad38d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1271.5445257896567,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.5490891235904,
        1278.539962455723
      ],
      "voteCount": 7536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.738945393693676
      }
    },
    {
      "id": "e7d4e990238d1c8723baf3b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-20240904",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1264.634973558954,
      "unit": "Arena rating",
      "confidenceInterval": [
        1247.0725983412967,
        1282.1973487766113
      ],
      "voteCount": 1012,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.29163858902085
      }
    },
    {
      "id": "88466a79db00e71f7bf08e64",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1235.4124360448536,
      "unit": "Arena rating",
      "confidenceInterval": [
        1220.191049096408,
        1250.633822993299
      ],
      "voteCount": 2015,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.31318607040108
      }
    },
    {
      "id": "5418b7f72a8d0444dc18926f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1276.3127913579106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.558444438109,
        1289.0671382777123
      ],
      "voteCount": 2879,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.34676797114757
      }
    },
    {
      "id": "37cb07bcf86be2bb889a31ad",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1180.638302049049,
      "unit": "Arena rating",
      "confidenceInterval": [
        1166.0910322875657,
        1195.185571810532
      ],
      "voteCount": 2119,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.08924275677182
      }
    },
    {
      "id": "bb8bbe3615ca99d7ddd006d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1241.392301349468,
      "unit": "Arena rating",
      "confidenceInterval": [
        1232.3043598351112,
        1250.4802428638247
      ],
      "voteCount": 8935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.499822026842754
      }
    },
    {
      "id": "3b6dd7eaa556f52ce9e3f98c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1129.9145687129267,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.7873393392242,
        1141.041798086629
      ],
      "voteCount": 10138,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.23130568730439
      }
    },
    {
      "id": "c259fafccfe40d0206bb9caa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1220.8874083349706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.615954707399,
        1242.1588619625422
      ],
      "voteCount": 830,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.7872158859085
      }
    },
    {
      "id": "794896114ac0567fcf0aff25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1235.6647576911455,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.2985436604126,
        1277.0309717218784
      ],
      "voteCount": 230,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 445.44631170280485
      }
    },
    {
      "id": "26879cfa086881638548560c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1216.7051379508725,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.740185655661,
        1243.6700902460843
      ],
      "voteCount": 501,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 189.27930409303616
      }
    },
    {
      "id": "350df2a423c98ef8c79f75b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1242.0675892347635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.4717137196521,
        1254.6634647498747
      ],
      "voteCount": 2928,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.30099719864076
      }
    },
    {
      "id": "36f315c2341711e008e6cf96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1233.9231899264203,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.1008775642595,
        1244.745502288581
      ],
      "voteCount": 4506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.489053854549862
      }
    },
    {
      "id": "a1854b24224a957f3f177a4f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1225.8178836632364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.1166029829908,
        1241.5191643434819
      ],
      "voteCount": 1678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.17619620748813
      }
    },
    {
      "id": "d50d673b7b9e27b447781121",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1196.6714326454103,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.4181935791403,
        1210.9246717116803
      ],
      "voteCount": 2125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.884811047781945
      }
    },
    {
      "id": "a0d794d1028ce8b11d050087",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1282.1481706260843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1261.158847582176,
        1303.1374936699926
      ],
      "voteCount": 876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.68343210352079
      }
    },
    {
      "id": "c43188eec1f797c342e1580c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1260.3833855566754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1246.812649249211,
        1273.9541218641398
      ],
      "voteCount": 2572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.94139219575304
      }
    },
    {
      "id": "e94110e2c1fc86fd9f42c917",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1216.5042773023256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.9475475290315,
        1231.0610070756197
      ],
      "voteCount": 1867,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.16091453361425
      }
    },
    {
      "id": "f0e5b894b4998532c783ca08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1249.4031854489806,
      "unit": "Arena rating",
      "confidenceInterval": [
        1227.8958152297992,
        1270.910555668162
      ],
      "voteCount": 818,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.41440383352858
      }
    },
    {
      "id": "1b5ea98f437748dadc546c5e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1262.909074444136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1251.9584976808715,
        1273.8596512074005
      ],
      "voteCount": 4673,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.216039802941747
      }
    },
    {
      "id": "3ea86137e41da6a4e6b1cd02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1203.0984726488837,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.8705671854884,
        1215.3263781122787
      ],
      "voteCount": 3632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.92314847064062
      }
    },
    {
      "id": "82bc74171d899f6d070a384a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1199.3210069360696,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.0273718464755,
        1209.6146420256637
      ],
      "voteCount": 5558,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.58299081247914
      }
    },
    {
      "id": "24fb9214ded8aa5d635e0877",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1139.4612179853336,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.9740298773422,
        1174.948406093325
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 327.82871783704553
      }
    },
    {
      "id": "364b4dfc00d8e1873a73db14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1190.1827347025874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.443863760464,
        1225.9216056447108
      ],
      "voteCount": 309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 332.4952721963452
      }
    },
    {
      "id": "b3de1cc2684568d785f3c2e4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1215.03002436402,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.314606279308,
        1230.745442448732
      ],
      "voteCount": 1650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.29181649607484
      }
    },
    {
      "id": "80addffef015e1ce3a5ee1a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1211.093518774778,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.3598604112597,
        1224.8271771382965
      ],
      "voteCount": 2028,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.099412710027906
      }
    },
    {
      "id": "e7b7ef9ebd3f800953a8217c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1203.4776768096617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.6163996592095,
        1218.3389539601137
      ],
      "voteCount": 2021,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.49314748677746
      }
    },
    {
      "id": "d70144764558fd9e2d2cb074",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1232.5387980909004,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.1352540420971,
        1239.942342139704
      ],
      "voteCount": 15450,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.268658611487666
      }
    },
    {
      "id": "2cad3cbf67f7044e2a85bb3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1225.0501179632383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.7013088594047,
        1241.3989270670718
      ],
      "voteCount": 1337,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.57866050098541
      }
    },
    {
      "id": "41f9e2d97a10bb6da26903b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226-online",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1212.576178509144,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.1084526905438,
        1255.0439043277443
      ],
      "voteCount": 217,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 469.4851150006385
      }
    },
    {
      "id": "b300569da63f93247d7e2d67",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1225.060687207803,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.4259284738753,
        1238.695445941731
      ],
      "voteCount": 2774,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.39480374771483
      }
    },
    {
      "id": "55e91689ca1dca7f782a8905",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1265.514433322655,
      "unit": "Arena rating",
      "confidenceInterval": [
        1254.8334591234852,
        1276.1954075218246
      ],
      "voteCount": 4748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.697886966471575
      }
    },
    {
      "id": "24690e9f9d4f80a136787134",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1174.4110615993447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.1714215024806,
        1186.6507016962087
      ],
      "voteCount": 3490,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.9978903050412
      }
    },
    {
      "id": "c48c53158b3d41335ae68ef8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1237.3523127578999,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.9763094665093,
        1244.7283160492905
      ],
      "voteCount": 14444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.162698884475727
      }
    },
    {
      "id": "7b80e5377cac341725ba0e31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1119.5534765284474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.1907387328908,
        1128.916214324004
      ],
      "voteCount": 16076,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.81967948116742
      }
    },
    {
      "id": "4eb1ba748289f6cfdc7a7691",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1211.1665496422256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.999404287717,
        1228.3336949967345
      ],
      "voteCount": 1325,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.71847945765056
      }
    },
    {
      "id": "7c80764e249b6b8a270dd3dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1247.1024081281812,
      "unit": "Arena rating",
      "confidenceInterval": [
        1215.6334049589445,
        1278.5714112974179
      ],
      "voteCount": 430,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 257.79221037868194
      }
    },
    {
      "id": "246a1648e98fc28ff406fe8e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1216.6976528844555,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.9479465592701,
        1238.447359209641
      ],
      "voteCount": 798,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.14325034111222
      }
    },
    {
      "id": "8373dd1e52dc4a9b65e1c490",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1238.9703986799168,
      "unit": "Arena rating",
      "confidenceInterval": [
        1228.4666892374557,
        1249.4741081223779
      ],
      "voteCount": 4796,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.720316213544475
      }
    },
    {
      "id": "60f26486a4c4fcc2d225ea26",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1232.7213287770796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1223.8068912024557,
        1241.6357663517033
      ],
      "voteCount": 7446,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.68672371125541
      }
    },
    {
      "id": "91f4f48c2fd47e63142e2c6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1214.0784516830925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1200.7869284794747,
        1227.36997488671
      ],
      "voteCount": 2702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.988932152703065
      }
    },
    {
      "id": "3cd1f3d105bfc52059b05ea5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1161.5507402392632,
      "unit": "Arena rating",
      "confidenceInterval": [
        1149.7058855904843,
        1173.3955948880423
      ],
      "voteCount": 3476,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.52273477328306
      }
    },
    {
      "id": "1816710019e836b9c31cff48",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1263.5390271970043,
      "unit": "Arena rating",
      "confidenceInterval": [
        1245.4469011082965,
        1281.6311532857123
      ],
      "voteCount": 1350,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.20852147272595
      }
    },
    {
      "id": "1bdd2894b75d2747fcdfdeed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1247.090433957851,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.5632382451954,
        1258.617629670507
      ],
      "voteCount": 4108,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.59004695873896
      }
    },
    {
      "id": "da7f1b70f8c8fc6e630bcdb6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1208.6568782902561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1196.6921514509936,
        1220.6216051295187
      ],
      "voteCount": 2967,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.26570946615101
      }
    },
    {
      "id": "fe542ebb4a30cc6e5498b06a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1247.646700928814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.191823853011,
        1266.1015780046168
      ],
      "voteCount": 1299,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 88.65967430088271
      }
    },
    {
      "id": "1bedaec9ca482e6371caa550",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1252.559246417885,
      "unit": "Arena rating",
      "confidenceInterval": [
        1243.4590716720757,
        1261.6594211636948
      ],
      "voteCount": 7444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.557742584184435
      }
    },
    {
      "id": "370a802b6d9210fa39a8e38a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1196.5906026490009,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.620383434495,
        1206.5608218635068
      ],
      "voteCount": 5831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.87695868293653
      }
    },
    {
      "id": "4b1da8f246f019992d970d79",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1190.2402852286136,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.768951989348,
        1198.7116184678794
      ],
      "voteCount": 9018,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.68131098115572
      }
    },
    {
      "id": "f71c272302319d628dc70ee1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1116.859774237667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1087.4582518785464,
        1146.2612965967871
      ],
      "voteCount": 440,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 225.0315719582943
      }
    },
    {
      "id": "333128fddab1d4007a31ef9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1154.7963229531185,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.7580731930082,
        1181.8345727132287
      ],
      "voteCount": 629,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 190.30971935760763
      }
    },
    {
      "id": "4b297297062f99a58ec5199c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1214.9694450020856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1202.0462754881823,
        1227.8926145159894
      ],
      "voteCount": 2719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.47523117660494
      }
    },
    {
      "id": "2de10ef1a281b6645dd52c66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1198.4313495183328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.095017933988,
        1209.7676811026781
      ],
      "voteCount": 3363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.45406518427796
      }
    },
    {
      "id": "8d7ad0f99973955ad99bb618",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1192.5760935857065,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.4790181266317,
        1204.6731690447816
      ],
      "voteCount": 3366,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.09470346895754
      }
    },
    {
      "id": "886f340641014aab36e3d8aa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1225.8170392987467,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.8704100686875,
        1231.7636685288062
      ],
      "voteCount": 24806,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.20546095907545
      }
    },
    {
      "id": "fdfd8b004dfb1ddafeb6bd5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1223.276410794163,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.0486857930334,
        1236.5041357952928
      ],
      "voteCount": 2328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.5485056257599
      }
    },
    {
      "id": "8fbee4acaade20c940f01ee7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "reka-flash-21b-20240226",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1195.25493308537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.7229316611472,
        1227.786934509593
      ],
      "voteCount": 409,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 275.50239793392024
      }
    },
    {
      "id": "29817b1948acb3c90f357065",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1379.8815985386927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1348.0567063532799,
        1411.7064907241056
      ],
      "voteCount": 317,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 263.65602493433505
      }
    },
    {
      "id": "0b4f9580856b18e011d6e29e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1390.5555667111325,
      "unit": "Arena rating",
      "confidenceInterval": [
        1375.8023111126226,
        1405.308822309643
      ],
      "voteCount": 1539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.66038890809711
      }
    },
    {
      "id": "93fa1d841ac6e4a98bebd7f7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1260.2739120621075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1240.165028272464,
        1280.3827958517509
      ],
      "voteCount": 888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.26397031436039
      }
    },
    {
      "id": "d760188c94aac9d298b28d7b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1349.2971324852915,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.3755704145656,
        1359.218694556018
      ],
      "voteCount": 3470,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.62500303087597
      }
    },
    {
      "id": "88ec3c20c374325eb9401c2e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1268.4865231625818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1258.2056686271721,
        1278.7673776979914
      ],
      "voteCount": 5094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.514539374694127
      }
    },
    {
      "id": "aac41e66a7ffbdc1d300abeb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1361.0646278730474,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.2643789292238,
        1393.864876816871
      ],
      "voteCount": 331,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.064522618622
      }
    },
    {
      "id": "2bd1f9bf6e9b4982ceb2a0a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1379.8916559078234,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.3995800795303,
        1393.3837317361167
      ],
      "voteCount": 1864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.38723455156539
      }
    },
    {
      "id": "bd8bd47cf35e6c90ea9d0bb5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1350.8443526439364,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.0119161820803,
        1360.676789105793
      ],
      "voteCount": 3573,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.166690908057884
      }
    },
    {
      "id": "e8ff40c0f6bbd183ef8f9392",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1322.431163855496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.182081093367,
        1338.680246617625
      ],
      "voteCount": 1334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.73240165641276
      }
    },
    {
      "id": "5ba1c25756f5bcbdb402266d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1272.4120150132862,
      "unit": "Arena rating",
      "confidenceInterval": [
        1255.9166119939955,
        1288.907418032577
      ],
      "voteCount": 1256,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.83202852599064
      }
    },
    {
      "id": "2c1fec36e459f91f8cd98923",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1291.7357754308127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1263.130791862356,
        1320.340758999269
      ],
      "voteCount": 444,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 213.0037371593667
      }
    },
    {
      "id": "734a80af6bc56d53272f16be",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1326.5862538616993,
      "unit": "Arena rating",
      "confidenceInterval": [
        1308.3940108188317,
        1344.7784969045667
      ],
      "voteCount": 1097,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.15417277099912
      }
    },
    {
      "id": "b0d3cb27dc96b8616a8cbf76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1356.340223635884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.1560029497525,
        1386.5244443220156
      ],
      "voteCount": 360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 237.17218404659613
      }
    },
    {
      "id": "dcf438c6065dc2f434c30f31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1324.6672667182322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.9518812467484,
        1355.3826521897158
      ],
      "voteCount": 384,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.59287205670609
      }
    },
    {
      "id": "c15e1d4b64e2b53f050ad782",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1373.8795622289363,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.336274861571,
        1385.4228495963016
      ],
      "voteCount": 2575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.68668791339456
      }
    },
    {
      "id": "3296c5d770dc907bf77f396e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1288.0252837748828,
      "unit": "Arena rating",
      "confidenceInterval": [
        1272.6570999582786,
        1303.393467591487
      ],
      "voteCount": 1488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.482130837539025
      }
    },
    {
      "id": "c224f5edb4e76c96ae74cd84",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1317.1330569566164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.4941587069402,
        1330.7719552062927
      ],
      "voteCount": 1850,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.42419355452378
      }
    },
    {
      "id": "385b1dbd4ad274b3ce65c095",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1243.8136973498172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.3787962462916,
        1286.2485984533425
      ],
      "voteCount": 215,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 468.7596342216187
      }
    },
    {
      "id": "29c284fa16a4c64699b30132",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1330.4659271162095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.154589596566,
        1346.777264635853
      ],
      "voteCount": 1333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.26007647054742
      }
    },
    {
      "id": "0e0f8a5618783106da395b36",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1339.24081458796,
      "unit": "Arena rating",
      "confidenceInterval": [
        1312.4766543334044,
        1366.0049748425156
      ],
      "voteCount": 453,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.47089753316678
      }
    },
    {
      "id": "3e6a93a9f6d176c2af5958c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1283.683988659754,
      "unit": "Arena rating",
      "confidenceInterval": [
        1266.151465710562,
        1301.216511608946
      ],
      "voteCount": 1212,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.01891346798283
      }
    },
    {
      "id": "5ac727bc3a00096ca811f2d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1320.9707756732482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.75789653285,
        1328.1836548136464
      ],
      "voteCount": 7148,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.54319489609683
      }
    },
    {
      "id": "b15cd504baa24159770298f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1227.328316123028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.2207590934095,
        1257.435873152646
      ],
      "voteCount": 381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 235.96894633063624
      }
    },
    {
      "id": "cfcbae0b04ef80f1d26538a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "ring-flash-2.0",
      "organization": "ant-group",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1374.1373456449628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.359097764267,
        1410.9155935256586
      ],
      "voteCount": 273,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 352.116104925338
      }
    },
    {
      "id": "905f700b16721a27250e9c21",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1031.0632994351827,
      "unit": "Arena rating",
      "confidenceInterval": [
        990.3614309948705,
        1071.7651678754946
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 431.2533784321868
      }
    },
    {
      "id": "8afda485af39d93bb89ca722",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1057.8535243032138,
      "unit": "Arena rating",
      "confidenceInterval": [
        1030.6988035528802,
        1085.0082450535474
      ],
      "voteCount": 505,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.95282142718844
      }
    },
    {
      "id": "87c9d98f0d059f042ececee8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1003.1121346540447,
      "unit": "Arena rating",
      "confidenceInterval": [
        980.4402949619605,
        1025.7839743461288
      ],
      "voteCount": 874,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.8065404357734
      }
    },
    {
      "id": "19f982f0de38765bd17fb502",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1058.0349855023499,
      "unit": "Arena rating",
      "confidenceInterval": [
        1045.3773966044803,
        1070.6925744002197
      ],
      "voteCount": 3997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.70669638429769
      }
    },
    {
      "id": "9cf1378fb9d7e448314aa53e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 849.2171207718573,
      "unit": "Arena rating",
      "confidenceInterval": [
        831.8019246611336,
        866.6323168825809
      ],
      "voteCount": 3301,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.95153110613394
      }
    },
    {
      "id": "ca7c13ee3644625343bf916d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1020.6615097565983,
      "unit": "Arena rating",
      "confidenceInterval": [
        998.1249213006212,
        1043.1980982125756
      ],
      "voteCount": 771,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 132.21482851723272
      }
    },
    {
      "id": "9ce40cbd36f377bded4be607",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1015.0778189171758,
      "unit": "Arena rating",
      "confidenceInterval": [
        994.2914098446954,
        1035.8642279896562
      ],
      "voteCount": 876,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.47674966626914
      }
    },
    {
      "id": "980ee98fe7dd75d05aef19ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1011.0151920822127,
      "unit": "Arena rating",
      "confidenceInterval": [
        977.0286797591203,
        1045.0017044053052
      ],
      "voteCount": 360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.68863778136176
      }
    },
    {
      "id": "9f6f56822d3e717b3a140476",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 988.961128918346,
      "unit": "Arena rating",
      "confidenceInterval": [
        966.8336709575524,
        1011.0885868791397
      ],
      "voteCount": 834,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.45793165061706
      }
    },
    {
      "id": "0de464f68b31c666ef7a0932",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1111.3477962317377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1063.8757372060527,
        1158.8198552574227
      ],
      "voteCount": 190,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 586.6511899067829
      }
    },
    {
      "id": "1d3dc7eb8f55da558373f1c2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1062.8709339386587,
      "unit": "Arena rating",
      "confidenceInterval": [
        1039.3580460555518,
        1086.3838218217654
      ],
      "voteCount": 844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.9182150346863
      }
    },
    {
      "id": "bb868a6c7d8ccfbe19e6347e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 992.2239866145142,
      "unit": "Arena rating",
      "confidenceInterval": [
        966.1655025274658,
        1018.2824707015624
      ],
      "voteCount": 488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.767375262986
      }
    },
    {
      "id": "9e87ea834c71e22aed66913b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1099.622891622249,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.6011099424145,
        1148.6446733020832
      ],
      "voteCount": 177,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 625.5787687009773
      }
    },
    {
      "id": "1ec88eb2ca6cd34c0b40ce1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1038.9803043771412,
      "unit": "Arena rating",
      "confidenceInterval": [
        1019.146007461879,
        1058.8146012924035
      ],
      "voteCount": 1072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.40883801838977
      }
    },
    {
      "id": "1bdb3f9de0eb79ae8ee145c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1001.3589585942,
      "unit": "Arena rating",
      "confidenceInterval": [
        981.8966291481545,
        1020.8212880402455
      ],
      "voteCount": 1098,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.6037557986802
      }
    },
    {
      "id": "167676d17f85508bc4081891",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 966.9022206720106,
      "unit": "Arena rating",
      "confidenceInterval": [
        949.8728137770629,
        983.9316275669581
      ],
      "voteCount": 1375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.49233578437466
      }
    },
    {
      "id": "86e8125ebd5512ab3da263dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 982.2795112435529,
      "unit": "Arena rating",
      "confidenceInterval": [
        957.9178730664257,
        1006.64114942068
      ],
      "voteCount": 544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.49584191195927
      }
    },
    {
      "id": "47e0bd622a43f83b030492c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 977.9126940019912,
      "unit": "Arena rating",
      "confidenceInterval": [
        950.6745153585465,
        1005.1508726454359
      ],
      "voteCount": 556,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.1345383205611
      }
    },
    {
      "id": "5ebe44254be4784d94d56105",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "RWKV-4-Raven-14B",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1040.590124720285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1029.1878526040005,
        1051.9923968365702
      ],
      "voteCount": 4845,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.84438451179737
      }
    },
    {
      "id": "cd1090fe3feec006bfd23721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1158.6462600240764,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.7922594440058,
        1191.500260604147
      ],
      "voteCount": 352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.98319011011426
      }
    },
    {
      "id": "a1f2112f9f96975405a0afef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1078.9252870194355,
      "unit": "Arena rating",
      "confidenceInterval": [
        1044.048754790151,
        1113.8018192487202
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 316.64337875696316
      }
    },
    {
      "id": "cab171b99d66fc3af41c21d3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1159.2180109137657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.345833157838,
        1178.0901886696934
      ],
      "voteCount": 1111,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.71454149988205
      }
    },
    {
      "id": "1af2f8fcdf289008b2dd3a0c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 897.809011867207,
      "unit": "Arena rating",
      "confidenceInterval": [
        865.9195012668106,
        929.6985224676034
      ],
      "voteCount": 1601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 264.7277854065448
      }
    },
    {
      "id": "322176eb1ca9682fb67e7cce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1157.8572891319054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.2083869530957,
        1189.506191310715
      ],
      "voteCount": 334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 260.7480792786083
      }
    },
    {
      "id": "359b513453c021faa96c85cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1149.434142416931,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.92013228232,
        1173.9481525515423
      ],
      "voteCount": 572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.4345007793771
      }
    },
    {
      "id": "21813e906b3b379b0839676c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1067.0579193450935,
      "unit": "Arena rating",
      "confidenceInterval": [
        1023.2997260346585,
        1110.8161126555283
      ],
      "voteCount": 252,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 498.4511278575682
      }
    },
    {
      "id": "01bbf02d71f0fa3adcf04f77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1073.6163463904627,
      "unit": "Arena rating",
      "confidenceInterval": [
        1040.2771645863972,
        1106.955528194528
      ],
      "voteCount": 360,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 289.3434747697422
      }
    },
    {
      "id": "f60d0572e8214d36055c7ff9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1151.4445827127379,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.1414813058348,
        1186.7476841196408
      ],
      "voteCount": 352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 324.4363735547955
      }
    },
    {
      "id": "000aabec6487ef8a2b920778",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1176.2125693670673,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.2250178076697,
        1210.2001209264652
      ],
      "voteCount": 240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 300.7070269190057
      }
    },
    {
      "id": "0e435fb9f607c0e67b8ee83a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1146.1127979441974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.6692431041556,
        1172.5563527842392
      ],
      "voteCount": 576,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 182.03021956433238
      }
    },
    {
      "id": "45c34f655d281c24fa8a0d47",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1077.7503240011908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1051.1691512491861,
        1104.3314967531953
      ],
      "voteCount": 627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 183.92979798862942
      }
    },
    {
      "id": "3038578fc120ce66557ea3fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1101.4072257480075,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.1464554759882,
        1122.6679960200267
      ],
      "voteCount": 859,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.66893090836358
      }
    },
    {
      "id": "87db145871f308f9ae9fe6cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1130.0124207894703,
      "unit": "Arena rating",
      "confidenceInterval": [
        1097.283510681938,
        1162.7413308970026
      ],
      "voteCount": 328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.84759588113195
      }
    },
    {
      "id": "a4ced05a8740437875a03f54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1151.7780081797512,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.0951279710816,
        1184.4608883884205
      ],
      "voteCount": 271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.06380559904574
      }
    },
    {
      "id": "0d5f2435e7d09b1ea78c2fec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1053.540768814373,
      "unit": "Arena rating",
      "confidenceInterval": [
        1014.9624178992167,
        1092.1191197295293
      ],
      "voteCount": 339,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 387.4281174941812
      }
    },
    {
      "id": "34788fdcba319fdbfd0eb5bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1113.530460287831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.1455223453424,
        1127.9153982303192
      ],
      "voteCount": 2199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.8666296497877
      }
    },
    {
      "id": "2a9b807588595f69ae6642e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "smollm2-1.7b-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1054.2804945028731,
      "unit": "Arena rating",
      "confidenceInterval": [
        1022.7043845980763,
        1085.85660440767
      ],
      "voteCount": 410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 259.5500207756094
      }
    },
    {
      "id": "b7c0e92b411d9b1696aaba6f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1176.2322319249124,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.3671214559208,
        1190.0973423939045
      ],
      "voteCount": 3128,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.0438237894764
      }
    },
    {
      "id": "5914153fba5e782e14ce376e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1223.011295722858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1211.8369662290293,
        1234.1856252166867
      ],
      "voteCount": 5734,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.50474506299386
      }
    },
    {
      "id": "087ee68b54745d0d61219ed4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1141.6363231575122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.5244588829553,
        1153.7481874320692
      ],
      "voteCount": 4777,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.18790283915672
      }
    },
    {
      "id": "02f47e50b239d6fe230bd68a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1199.933261023437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.433693374468,
        1207.4328286724058
      ],
      "voteCount": 20419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.641186472824845
      }
    },
    {
      "id": "0c0ed625a3144fc7ca051f5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1037.9752079660088,
      "unit": "Arena rating",
      "confidenceInterval": [
        1028.3167785457383,
        1047.6336373862791
      ],
      "voteCount": 21547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.283810713735146
      }
    },
    {
      "id": "1db7ff2dc5321dff49ba2c25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1158.7614618638572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.6016834064508,
        1175.9212403212637
      ],
      "voteCount": 1722,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.65264954058921
      }
    },
    {
      "id": "3eabddb8218a0fc89fa93b33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1218.3500137768724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.6324372323916,
        1249.0675903213532
      ],
      "voteCount": 527,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.62791189716322
      }
    },
    {
      "id": "15f41c79f459b765628f3c73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1145.3401780974732,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.6949466841972,
        1167.9854095107494
      ],
      "voteCount": 947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 133.49264685548872
      }
    },
    {
      "id": "15ee5834c127d72a53c0fc90",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1201.3215986360044,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.5161180717973,
        1212.1270792002115
      ],
      "voteCount": 6488,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.39428916808224
      }
    },
    {
      "id": "1f665011159059afaba73100",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1184.774321981252,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.627596201509,
        1193.921047760995
      ],
      "voteCount": 9592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.778859645486527
      }
    },
    {
      "id": "87a5e91ac55fbd2300c00ae3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1141.297303912478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.8594512787492,
        1154.7351565462066
      ],
      "voteCount": 3261,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.007111577777955
      }
    },
    {
      "id": "e15b67f55c3bbde08688add5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1144.3053348481517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.3918181104953,
        1156.218851585808
      ],
      "voteCount": 4657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.94739099995651
      }
    },
    {
      "id": "289bf4121e97ce48922ca692",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1199.4161535659273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.075802413056,
        1217.7565047187986
      ],
      "voteCount": 1535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.56269326605707
      }
    },
    {
      "id": "eda5c6916191ee16f0d75721",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1194.0290148397805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.3738024319111,
        1205.68422724765
      ],
      "voteCount": 5411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.3626011922224
      }
    },
    {
      "id": "cf2116b42d3c94775771ffe0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1159.9495872405678,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.0589528953676,
        1171.8402215857682
      ],
      "voteCount": 4220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.80559696998332
      }
    },
    {
      "id": "94828274969ecd2d3a6e794d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1193.961983066945,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.0190632103295,
        1212.9049029235607
      ],
      "voteCount": 1626,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.41092263207575
      }
    },
    {
      "id": "001741c6a8f721a2f54f4179",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1204.648163120584,
      "unit": "Arena rating",
      "confidenceInterval": [
        1194.8914958171986,
        1214.4048304239695
      ],
      "voteCount": 9209,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.780314279601765
      }
    },
    {
      "id": "6d547bbf502c479508b01bf9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1158.6579076818584,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.6080678223486,
        1168.7077475413685
      ],
      "voteCount": 7241,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.29190781838041
      }
    },
    {
      "id": "fc7d3d140875edd6ba0799cf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1150.3653989689285,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.8660750752294,
        1158.8647228626273
      ],
      "voteCount": 11736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.804967076791478
      }
    },
    {
      "id": "29a0ea8188387e6deca3d8cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1043.1844051002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1018.2902607471381,
        1068.0785494532615
      ],
      "voteCount": 667,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.3237189300641
      }
    },
    {
      "id": "960f4ea77d5dddca7f0f42fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1064.628099662266,
      "unit": "Arena rating",
      "confidenceInterval": [
        1035.5531399695633,
        1093.703059354969
      ],
      "voteCount": 547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 220.0604823819363
      }
    },
    {
      "id": "3838286b9533bef7a686077d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1126.5527573194472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.295337445723,
        1140.8101771931715
      ],
      "voteCount": 2793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.915840294999036
      }
    },
    {
      "id": "7afbf82401ea9fa4b8ddd5e9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1161.7629192555557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.5051729444806,
        1173.020665566631
      ],
      "voteCount": 4793,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.99185489683981
      }
    },
    {
      "id": "b45646b5025013f541cb42f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1141.68759662505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.0969759016862,
        1154.2782173484136
      ],
      "voteCount": 3963,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.266544195559945
      }
    },
    {
      "id": "84a72b7649942b569d88035d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1178.6579608943073,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.7450542329775,
        1184.570867555637
      ],
      "voteCount": 32832,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.101351027701737
      }
    },
    {
      "id": "b5fe887a7a092061e833270f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1167.562324185393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.1879860515096,
        1180.9366623192764
      ],
      "voteCount": 2784,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.5638000740363
      }
    },
    {
      "id": "8fd01d7c2446fc51951d69fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "snowflake-arctic-instruct",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1171.9431317051274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.6950882227338,
        1202.191175187521
      ],
      "voteCount": 500,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 238.17621825956317
      }
    },
    {
      "id": "54a337df14c7b6bbb4b1e7e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1181.8679262469805,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.7249375566194,
        1209.0109149373416
      ],
      "voteCount": 482,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 191.78699276332304
      }
    },
    {
      "id": "971c9f92b9aec7efd5527435",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1137.8349808892112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.0962271960386,
        1161.5737345823836
      ],
      "voteCount": 698,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.69646434041093
      }
    },
    {
      "id": "e4ad4523ec8e7bc00b632f3c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1183.8734183840493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.3525734153327,
        1198.394263352766
      ],
      "voteCount": 3277,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.88928775433395
      }
    },
    {
      "id": "a49da60649c44b00958f37b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1004.4106632412695,
      "unit": "Arena rating",
      "confidenceInterval": [
        985.2595018298307,
        1023.5618246527084
      ],
      "voteCount": 2831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.47596382686541
      }
    },
    {
      "id": "b5da2f1903d8038b81608c50",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1167.7848405578784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1146.12745298364,
        1189.4422281321167
      ],
      "voteCount": 765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.10008187879613
      }
    },
    {
      "id": "66b3cdcede6a9d811cd522f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1155.9548265905692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.3370847752094,
        1175.572568405929
      ],
      "voteCount": 932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 100.18480267467002
      }
    },
    {
      "id": "fbc3d6fb9960233422db5756",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1126.8471298977202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.6396503781405,
        1161.0546094172996
      ],
      "voteCount": 311,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 304.61127131671617
      }
    },
    {
      "id": "d1adfa2a82ca9b99ae7cefde",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1122.502231199322,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.4943326260368,
        1146.5101297726071
      ],
      "voteCount": 654,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.04174736955733
      }
    },
    {
      "id": "5492857c98e2709340e7f1d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1183.1855148305178,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.6055404013537,
        1222.765489259682
      ],
      "voteCount": 219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 407.8071505996854
      }
    },
    {
      "id": "085c92f0b734486dec68279e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1178.4656972380515,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.0795582960818,
        1201.851836180021
      ],
      "voteCount": 721,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.37078155487822
      }
    },
    {
      "id": "474460a68b8da1fb407901d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1109.2330946325892,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.5767747502377,
        1132.8894145149407
      ],
      "voteCount": 529,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.67941412294277
      }
    },
    {
      "id": "8dcf352da4e1de9b722c9097",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1179.518222269189,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.8687943011068,
        1220.1676502372711
      ],
      "voteCount": 210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 430.14283668247907
      }
    },
    {
      "id": "24c238143182fbf0abd1f53a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1168.4090364206586,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.7139427345921,
        1189.1041301067253
      ],
      "voteCount": 981,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.4906921214065
      }
    },
    {
      "id": "24eb5801d76aff084ab2b290",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1138.1585652453318,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.2523592320256,
        1159.0647712586378
      ],
      "voteCount": 894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.77694523660696
      }
    },
    {
      "id": "01318fac65c24ff835e50d95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1113.6518808624742,
      "unit": "Arena rating",
      "confidenceInterval": [
        1095.0826080124739,
        1132.2211537124745
      ],
      "voteCount": 1188,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.76222582947159
      }
    },
    {
      "id": "c5f84115549450f053265f76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1108.59242047635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.9400844589752,
        1130.2447564937252
      ],
      "voteCount": 604,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 122.04312915805194
      }
    },
    {
      "id": "7dcdb946961d60db727a0e88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1109.6204551921692,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.4348931831564,
        1134.806017201182
      ],
      "voteCount": 601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 165.12282529042224
      }
    },
    {
      "id": "1c93286facfec7d932534499",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "solar-10.7b-instruct-v1.0",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1151.349760376545,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.1674717129295,
        1164.5320490401607
      ],
      "voteCount": 4155,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.23613099137451
      }
    },
    {
      "id": "3b05183f9373fe301c0b3eb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1003.0627814378802,
      "unit": "Arena rating",
      "confidenceInterval": [
        970.3360083974219,
        1035.7895544783385
      ],
      "voteCount": 363,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 278.81118180205755
      }
    },
    {
      "id": "6f675b66da29031ac66d093c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 931.3639143482276,
      "unit": "Arena rating",
      "confidenceInterval": [
        902.7913354535003,
        959.936493242955
      ],
      "voteCount": 536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.5214151190349
      }
    },
    {
      "id": "536a5dc0b6c0718a1519ff1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 975.3199972726293,
      "unit": "Arena rating",
      "confidenceInterval": [
        961.3086906110145,
        989.331303934244
      ],
      "voteCount": 2707,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.10472961684286
      }
    },
    {
      "id": "6ffa069d5cce8602e3fdde9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 701.4361475233395,
      "unit": "Arena rating",
      "confidenceInterval": [
        680.1400856410849,
        722.7322094055942
      ],
      "voteCount": 2206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.05990194393688
      }
    },
    {
      "id": "1220d19e90f80a7c4040649d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 955.8070542423474,
      "unit": "Arena rating",
      "confidenceInterval": [
        928.9246304777422,
        982.6894780069525
      ],
      "voteCount": 497,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.12246627941894
      }
    },
    {
      "id": "989e49366aeb87c768c0f0dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 941.7394578084709,
      "unit": "Arena rating",
      "confidenceInterval": [
        917.3654946541026,
        966.1134209628392
      ],
      "voteCount": 575,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.6522057323922
      }
    },
    {
      "id": "36788f5f305f3f4045f6c839",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 908.268663558079,
      "unit": "Arena rating",
      "confidenceInterval": [
        867.4287025442752,
        949.1086245718828
      ],
      "voteCount": 238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 434.1846401226388
      }
    },
    {
      "id": "cc7bd41dffebaf54b56d40ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 905.1016181295404,
      "unit": "Arena rating",
      "confidenceInterval": [
        876.3270492523186,
        933.8761870067624
      ],
      "voteCount": 514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 215.5368188797552
      }
    },
    {
      "id": "0fe01ddcb20c7531f7a58030",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 935.9573517280087,
      "unit": "Arena rating",
      "confidenceInterval": [
        908.654709448177,
        963.2599940078403
      ],
      "voteCount": 615,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.04978948225647
      }
    },
    {
      "id": "d645e325c6dc15f2f4c638f2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 894.7322303626765,
      "unit": "Arena rating",
      "confidenceInterval": [
        863.2624021383217,
        926.2020585870316
      ],
      "voteCount": 294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 257.80572816122395
      }
    },
    {
      "id": "c0ee527316a427668fe1a209",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 968.4878500391068,
      "unit": "Arena rating",
      "confidenceInterval": [
        944.5911523207892,
        992.3845477574243
      ],
      "voteCount": 742,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 148.65502625314159
      }
    },
    {
      "id": "7b8d22cea2b01d3cfe24ce08",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 929.2029579889686,
      "unit": "Arena rating",
      "confidenceInterval": [
        904.9682789136718,
        953.4376370642655
      ],
      "voteCount": 681,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.88974769655508
      }
    },
    {
      "id": "346d0e295b7154ba5b0d1772",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 907.1401551866782,
      "unit": "Arena rating",
      "confidenceInterval": [
        886.8382727709745,
        927.4420376023818
      ],
      "voteCount": 814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 107.29424649841302
      }
    },
    {
      "id": "9bd898ae6d3eac8eb9dc82fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 889.6866949667137,
      "unit": "Arena rating",
      "confidenceInterval": [
        860.9201306727441,
        918.4532592606835
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 215.41691839080187
      }
    },
    {
      "id": "7ccbd26ed364195003bde690",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 896.5139546521257,
      "unit": "Arena rating",
      "confidenceInterval": [
        862.498137478216,
        930.5297718260355
      ],
      "voteCount": 354,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 301.2073985475595
      }
    },
    {
      "id": "6a0f62a2aea518a27a29c8c8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stablelm-tuned-alpha-7b",
      "license": "CC-BY-NC-SA-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 951.7516913950205,
      "unit": "Arena rating",
      "confidenceInterval": [
        939.0055961550031,
        964.497786635038
      ],
      "voteCount": 3287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.29199151957531
      }
    },
    {
      "id": "3f56b256ca73921c55978297",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1136.0082658057831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.1558424609007,
        1157.8606891506658
      ],
      "voteCount": 858,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 124.30913054996171
      }
    },
    {
      "id": "69c564014770cc8faeb3a097",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1205.8591278456256,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.4914790711982,
        1222.226776620053
      ],
      "voteCount": 1397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.73911186027176
      }
    },
    {
      "id": "1e8cdb90d81a773b6dc32473",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1135.6306105314452,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.9742808482454,
        1151.286940214645
      ],
      "voteCount": 1701,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.80926376942195
      }
    },
    {
      "id": "74c34dcacad2d646a1f4e094",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1195.0611721766159,
      "unit": "Arena rating",
      "confidenceInterval": [
        1185.9815690699916,
        1204.1407752832404
      ],
      "voteCount": 7238,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.46038690554765
      }
    },
    {
      "id": "b50500a756b0dc2f9115dd8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1027.796079138205,
      "unit": "Arena rating",
      "confidenceInterval": [
        1015.883392467754,
        1039.708765808656
      ],
      "voteCount": 6748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.94224260425526
      }
    },
    {
      "id": "303dcae6acb077f69a6839f6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1133.0654378737938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.327093810526,
        1163.8037819370616
      ],
      "voteCount": 318,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 245.96015208125885
      }
    },
    {
      "id": "61a3edb937f41045dd72b73a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1165.0367216780442,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.995768215781,
        1209.0776751403073
      ],
      "voteCount": 210,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 504.91380290646055
      }
    },
    {
      "id": "d1de398a4d1454c2fb9989e7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1083.5868205123388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1041.7357937040904,
        1125.437847320587
      ],
      "voteCount": 199,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 455.9487753634804
      }
    },
    {
      "id": "6057e027d08128544dc14298",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1184.5254079851707,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.2412786809707,
        1198.8095372893706
      ],
      "voteCount": 1894,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.11428795746774
      }
    },
    {
      "id": "879a005dba2adffa9af70145",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1166.6191613609158,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.89843167334,
        1179.339891048492
      ],
      "voteCount": 2471,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.123831423797476
      }
    },
    {
      "id": "34e7588a0d9b3c4302fb13a3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1159.3599832195819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.7789079631407,
        1179.9410584760226
      ],
      "voteCount": 841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.2655731800209
      }
    },
    {
      "id": "da42e4abfa1529ac2f03f34b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1132.937005577171,
      "unit": "Arena rating",
      "confidenceInterval": [
        1117.5341498767548,
        1148.3398612775873
      ],
      "voteCount": 1622,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.75986124067721
      }
    },
    {
      "id": "3e7a7926df2988872c6349d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1204.1343643395817,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.1920407592704,
        1231.0766879198932
      ],
      "voteCount": 504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 188.9617548405831
      }
    },
    {
      "id": "c560d1b0b8a1aace40e06f9b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1195.1863530395626,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.8927925550086,
        1210.4799135241167
      ],
      "voteCount": 1854,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.88650255333167
      }
    },
    {
      "id": "a00649a58b268e05478029d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1133.2675406488315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.0596443911318,
        1150.4754369065317
      ],
      "voteCount": 1103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.08313623475482
      }
    },
    {
      "id": "edce9f0680df0f5a07f7acf2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1211.989017881242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.4519570340633,
        1237.526078728421
      ],
      "voteCount": 568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 169.76401600334717
      }
    },
    {
      "id": "74ae35b62f1889accb9ffb55",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1184.833388320291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.7181057579796,
        1197.9486708826025
      ],
      "voteCount": 2610,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.77742563909399
      }
    },
    {
      "id": "34293cb225b891046160ba56",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1138.8359266271605,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.6211321168273,
        1152.0507211374934
      ],
      "voteCount": 2509,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.4594991386044
      }
    },
    {
      "id": "2d2861589b9c1416e1bd72b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1134.2020693942573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.6875207625183,
        1145.716618025996
      ],
      "voteCount": 3316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.51418754730356
      }
    },
    {
      "id": "f6c6deeefa823ca8c8682c5c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1148.5294030954146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.4102446023196,
        1171.6485615885097
      ],
      "voteCount": 666,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.13867475280387
      }
    },
    {
      "id": "a5de3745c48f0baf690f7068",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1126.066154602449,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.3841716948916,
        1141.7481375100062
      ],
      "voteCount": 1300,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.01854071378115
      }
    },
    {
      "id": "89119c2f26ce914e86d55963",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1131.7104870524684,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.129951225914,
        1149.2910228790224
      ],
      "voteCount": 1270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.45777772854187
      }
    },
    {
      "id": "e2fefd02fdb17b9a592c24b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1166.5737320081078,
      "unit": "Arena rating",
      "confidenceInterval": [
        1158.5084994580893,
        1174.6389645581262
      ],
      "voteCount": 10224,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.933144183522227
      }
    },
    {
      "id": "17ce1678cdcad1e9ebce1660",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-alpha",
      "license": "CC-BY-NC-4.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1152.1543344958902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.8511833580997,
        1179.4574856336808
      ],
      "voteCount": 410,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 194.05702282611722
      }
    },
    {
      "id": "28bbc1aac4de558535a85fef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1175.0687343946151,
      "unit": "Arena rating",
      "confidenceInterval": [
        1160.075128332213,
        1190.0623404570174
      ],
      "voteCount": 2863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.52157559088032
      }
    },
    {
      "id": "369076ec7a476c7257091066",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1233.952441258472,
      "unit": "Arena rating",
      "confidenceInterval": [
        1221.0946911978435,
        1246.8101913190999
      ],
      "voteCount": 2948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.03618607883754
      }
    },
    {
      "id": "a27b983e4c249acf377cd062",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1108.1405034056872,
      "unit": "Arena rating",
      "confidenceInterval": [
        1093.4775526442045,
        1122.80345416717
      ],
      "voteCount": 2376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.96887408383498
      }
    },
    {
      "id": "2e3c217db53340d2ab79b80c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1201.012679004756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1192.0444377479425,
        1209.9809202615693
      ],
      "voteCount": 9101,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.937189488309265
      }
    },
    {
      "id": "c89521666825c1e33ebb202b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1040.4339129297543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1029.4358195625507,
        1051.432006296958
      ],
      "voteCount": 10737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.48753204436844
      }
    },
    {
      "id": "517418b6fd6fc5d4787871d8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1169.8961916163685,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.0547099786272,
        1189.7376732541097
      ],
      "voteCount": 952,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.48304406128956
      }
    },
    {
      "id": "6df1b9ce26c0e6b1b814f536",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1163.9848113253029,
      "unit": "Arena rating",
      "confidenceInterval": [
        1124.2915470051744,
        1203.6780756454314
      ],
      "voteCount": 248,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 410.14502717040466
      }
    },
    {
      "id": "d37a215d5a92b34e6905e09b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1110.1221420541249,
      "unit": "Arena rating",
      "confidenceInterval": [
        1079.0054491176559,
        1141.238834990594
      ],
      "voteCount": 367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 252.05231254504068
      }
    },
    {
      "id": "b36e7b55043afb373f86289c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1206.5465956264572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.801505916936,
        1219.2916853359784
      ],
      "voteCount": 2864,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.28531901180022
      }
    },
    {
      "id": "5b20685f3ee9a1128a1f4f05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1193.5513276753072,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.7440823973436,
        1204.3585729532706
      ],
      "voteCount": 4525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.404217759377364
      }
    },
    {
      "id": "3019453bbbe374614bc87807",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1169.7982021149971,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.2870085932182,
        1186.309395636776
      ],
      "voteCount": 1650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.96770373927123
      }
    },
    {
      "id": "67f5868e7d7807b1955cd9e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1113.3124447353175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.4084277046704,
        1128.2164617659641
      ],
      "voteCount": 2204,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.82431467264134
      }
    },
    {
      "id": "9a66c73d503070a8a84e1613",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1208.7186940692873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.385260215857,
        1230.0521279227178
      ],
      "voteCount": 878,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 118.47462675558607
      }
    },
    {
      "id": "143806bb5f244f494f622ea5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1204.396949123679,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.55537084063,
        1218.2385274067278
      ],
      "voteCount": 2912,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.87409687529957
      }
    },
    {
      "id": "1dbf99921a7956b42625791f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1169.0475324155427,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.4661443981163,
        1183.628920432969
      ],
      "voteCount": 1816,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.34795150461232
      }
    },
    {
      "id": "2ccf161b5cde2f06d7c80b96",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1203.7751674233257,
      "unit": "Arena rating",
      "confidenceInterval": [
        1181.8406671684675,
        1225.7096676781841
      ],
      "voteCount": 853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.24468538841353
      }
    },
    {
      "id": "3b9c4a775b7f5f32f4889d7c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1216.747893638162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.6840270901835,
        1227.8117601861404
      ],
      "voteCount": 4831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.865275330312176
      }
    },
    {
      "id": "324556b4f42148ed8f00bf03",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1127.2189736926464,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.966721096732,
        1139.4712262885607
      ],
      "voteCount": 4016,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.07830349902446
      }
    },
    {
      "id": "47095f18bf68be2d0d3dc64f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1144.303454509126,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.1686452392387,
        1154.4382637790131
      ],
      "voteCount": 5765,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.738373032574167
      }
    },
    {
      "id": "be2256ce190e3640c9f4cd13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1042.3232654160163,
      "unit": "Arena rating",
      "confidenceInterval": [
        998.0651088040023,
        1086.5814220280304
      ],
      "voteCount": 181,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 509.90639705454873
      }
    },
    {
      "id": "4f80dc36b341bf41fd4bdafe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1164.23602606752,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.374713520961,
        1180.0973386140793
      ],
      "voteCount": 1676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.4910666604976
      }
    },
    {
      "id": "9c4367b40ad9bc24fd68377f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1157.8390240287745,
      "unit": "Arena rating",
      "confidenceInterval": [
        1143.9537238144785,
        1171.724324243071
      ],
      "voteCount": 1973,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.18967299675409
      }
    },
    {
      "id": "cc7bbf96bd85e87342abe1db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1144.3021878968561,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.1604545902992,
        1159.4439212034129
      ],
      "voteCount": 2151,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.68359892127277
      }
    },
    {
      "id": "bc46771d9ee41299fed5175b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1170.682374907034,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.2740031013516,
        1178.0907467127165
      ],
      "voteCount": 16056,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.287273500256799
      }
    },
    {
      "id": "7ef006e3c365977c7a9a4122",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "starling-lm-7b-beta",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1137.6127633118717,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.1229135032272,
        1154.1026131205163
      ],
      "voteCount": 1405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.7843450636094
      }
    },
    {
      "id": "d4ee958a216613bf78eecd61",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1353.5332300400291,
      "unit": "Arena rating",
      "confidenceInterval": [
        1326.0901658941712,
        1380.9762941858874
      ],
      "voteCount": 457,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.05098085565353
      }
    },
    {
      "id": "fa0e8835f32596e87b5097df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1353.3387950703293,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.445378968697,
        1368.2322111719616
      ],
      "voteCount": 1504,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.742085371692085
      }
    },
    {
      "id": "3b555dc6f58a8aa711d9de0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1294.9022106771397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.854107796521,
        1313.9503135577584
      ],
      "voteCount": 997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.45115522156522
      }
    },
    {
      "id": "53c5d0e583483e45cac61298",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1334.4736696190466,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.1231543708516,
        1343.824184867242
      ],
      "voteCount": 4364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.760138657670975
      }
    },
    {
      "id": "e1e28303d4f4de2b30da3208",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1266.330960535562,
      "unit": "Arena rating",
      "confidenceInterval": [
        1256.7904932763427,
        1275.8714277947818
      ],
      "voteCount": 6468,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.69425777361143
      }
    },
    {
      "id": "ca6cc00112437a39ec52e3c9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1292.1155453513397,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.94966638065,
        1319.2814243220296
      ],
      "voteCount": 472,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 192.11060555292397
      }
    },
    {
      "id": "a6142d1c6e09817648ab3572",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1301.171261934665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1268.8160889604285,
        1333.5264349089016
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 272.5155382515872
      }
    },
    {
      "id": "98518a66e17536e73e5909d4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1350.6486524038214,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.198751132475,
        1364.098553675168
      ],
      "voteCount": 1887,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.09144433215052
      }
    },
    {
      "id": "a8ebe0e41f1a61b6b05a98a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1333.4316172984145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.552189118972,
        1343.311045477857
      ],
      "voteCount": 3705,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.407821795973014
      }
    },
    {
      "id": "3871a86caf78778b37666174",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1321.5204116698328,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.81386323428,
        1337.2269601053854
      ],
      "voteCount": 1394,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.2192654596219
      }
    },
    {
      "id": "a63c7de205da73b4505237bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1280.0440258386875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1264.9851589364844,
        1295.1028927408906
      ],
      "voteCount": 1486,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.03212372254317
      }
    },
    {
      "id": "34e781083c7ddb667ea51548",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1330.1913422288649,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.81877209422,
        1353.5639123635094
      ],
      "voteCount": 657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 142.20562036382222
      }
    },
    {
      "id": "b18832323b920320149a2792",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1335.393515581196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.0712910711782,
        1350.7157400912138
      ],
      "voteCount": 1521,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.11495004727646
      }
    },
    {
      "id": "f522c7d4fa9861995bc53e7e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1325.7228011641432,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.6273748132026,
        1349.818227515084
      ],
      "voteCount": 569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.13778336134655
      }
    },
    {
      "id": "f157125a08e5cbb3fe45ce25",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1329.8254969122268,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.8493989203773,
        1353.801594904076
      ],
      "voteCount": 605,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.64452353829788
      }
    },
    {
      "id": "73dc4f0801c6ddd91782ccf0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1351.6260217880317,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.5223330585895,
        1362.7297105174737
      ],
      "voteCount": 2847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.09507355282814
      }
    },
    {
      "id": "7ac69d48395db0fa375a2ec9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1302.1229506955713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1288.3947473556473,
        1315.8511540354953
      ],
      "voteCount": 1846,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.06041577929633
      }
    },
    {
      "id": "218b6f5a38438428c12eeeaa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1308.2673825328134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.4979571727672,
        1321.0368078928598
      ],
      "voteCount": 2094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.44695352385188
      }
    },
    {
      "id": "cff4a8f939e4a28975b7da49",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1344.1568145348979,
      "unit": "Arena rating",
      "confidenceInterval": [
        1327.541062520572,
        1360.7725665492237
      ],
      "voteCount": 1265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.86936731282891
      }
    },
    {
      "id": "3221f96e0418cbef669be53a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1299.5161962176867,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.894899802657,
        1323.1374926327162
      ],
      "voteCount": 564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 145.2483731755504
      }
    },
    {
      "id": "5a5ea82803a4c00524f9a73d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1325.593887922173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1309.6173240197313,
        1341.5704518246148
      ],
      "voteCount": 1397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.44626587008031
      }
    },
    {
      "id": "4301bb9c5d7238b5904247d2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1320.300955536617,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.4682677813644,
        1327.1336432918697
      ],
      "voteCount": 9038,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.153097075851118
      }
    },
    {
      "id": "0ba821f0e9f74baa569c028b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-1o-turbo-202506",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1325.1991035224598,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.664145053518,
        1348.7340619914016
      ],
      "voteCount": 544,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 144.18852211846064
      }
    },
    {
      "id": "abb3bf3e34db7ba583b3b8e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1365.4972463696959,
      "unit": "Arena rating",
      "confidenceInterval": [
        1331.6552632130881,
        1399.3392295263034
      ],
      "voteCount": 328,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 298.1366916657899
      }
    },
    {
      "id": "ff769a159da2518a85f5536e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1371.4912654590248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.6073412329092,
        1391.3751896851402
      ],
      "voteCount": 737,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.92195259259906
      }
    },
    {
      "id": "9242adde02d5c718655620a0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1336.586408907603,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.7652673285634,
        1357.4075504866423
      ],
      "voteCount": 751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 112.85294386575582
      }
    },
    {
      "id": "3329e8464e2855dfc61f4d1f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1354.6551614898965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.8883409569771,
        1365.4219820228157
      ],
      "voteCount": 2781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.177187833851384
      }
    },
    {
      "id": "2eaab0bb2c96390a075e699a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1290.2084421837012,
      "unit": "Arena rating",
      "confidenceInterval": [
        1276.240182358933,
        1304.1767020084699
      ],
      "voteCount": 3048,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.791194605852056
      }
    },
    {
      "id": "85aac247d5a554096589341b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1324.9816955895344,
      "unit": "Arena rating",
      "confidenceInterval": [
        1293.5969359543055,
        1356.366455224763
      ],
      "voteCount": 310,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 256.41382176344644
      }
    },
    {
      "id": "d580cd6602f6cca7e033f44c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1346.9391343912046,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.3706184304972,
        1365.5076503519122
      ],
      "voteCount": 786,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.75490850654076
      }
    },
    {
      "id": "b4b15059003b8faa4dadc91e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1338.4371507244023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.1035324402187,
        1353.7707690085858
      ],
      "voteCount": 1221,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.20587533528806
      }
    },
    {
      "id": "eda51edd00234828b1567891",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1311.8063724988688,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.2838656188283,
        1336.3288793789095
      ],
      "voteCount": 506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.5429623876525
      }
    },
    {
      "id": "d1d46d636a4267d86c8d9d9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1302.0423769313084,
      "unit": "Arena rating",
      "confidenceInterval": [
        1283.6732883075592,
        1320.4114655550575
      ],
      "voteCount": 873,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.8373119736266
      }
    },
    {
      "id": "105b55fdba1a13d78e9fcc0a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1347.347498697819,
      "unit": "Arena rating",
      "confidenceInterval": [
        1313.9697884728828,
        1380.725208922755
      ],
      "voteCount": 278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 290.0126206893705
      }
    },
    {
      "id": "236c7565468a8b6e1a09089a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1345.351335877342,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.930388130545,
        1364.772283624139
      ],
      "voteCount": 863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.18488990483623
      }
    },
    {
      "id": "806478da508d70c7b547b016",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1323.6953855967956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.3937297472864,
        1345.9970414463048
      ],
      "voteCount": 543,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.47265006476795
      }
    },
    {
      "id": "b914dbdba983e3da4642e1e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1376.3292471164305,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.8616020784325,
        1412.7968921544286
      ],
      "voteCount": 265,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 346.1937760345738
      }
    },
    {
      "id": "5855542373fe6c28b284a317",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1352.1212943920834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.3694247576914,
        1367.8731640264753
      ],
      "voteCount": 1200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 64.59040915452113
      }
    },
    {
      "id": "3ef39ad8f9159bde9f11601a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1319.2215799472938,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.6968535822666,
        1334.7463063123205
      ],
      "voteCount": 1326,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.7410418694558
      }
    },
    {
      "id": "46b1dce5d8139a6253cfb86a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1315.8629726456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.327147534649,
        1328.398797756551
      ],
      "voteCount": 1950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.908133744865815
      }
    },
    {
      "id": "7988a4b1a16a692e6e48cf11",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1341.863515094645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.731931817629,
        1362.9950983716608
      ],
      "voteCount": 693,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.24329001990253
      }
    },
    {
      "id": "8bcb13f9e8226a87251deccb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1312.5978929723208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.6610864273634,
        1332.5346995172779
      ],
      "voteCount": 642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 103.47013303118658
      }
    },
    {
      "id": "89bcde784db843a3e025c2e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1307.565274546729,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.464942952064,
        1327.6656061413937
      ],
      "voteCount": 805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.17445300701688
      }
    },
    {
      "id": "975172ec84a0adab2b39a6b4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1333.9914073996633,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.4014640242715,
        1342.5813507750554
      ],
      "voteCount": 4833,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.208100525494714
      }
    },
    {
      "id": "bde1414e1ec87b576b5cf5bb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-2-16k-exp-202412",
      "organization": "stepfun",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1341.2771198083883,
      "unit": "Arena rating",
      "confidenceInterval": [
        1319.4667398124718,
        1363.087499804305
      ],
      "voteCount": 642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.83125728270183
      }
    },
    {
      "id": "ce1d7b4d14a0aad775888ee5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1430.3112178260271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1415.0769101606522,
        1445.5455254914018
      ],
      "voteCount": 1592,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.41562356286387
      }
    },
    {
      "id": "1cdd1204b7ef6d2efafe1fa1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1447.4206243188262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1440.460847932426,
        1454.3804007052263
      ],
      "voteCount": 8364,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.609399087594555
      }
    },
    {
      "id": "9a7cb012433ccc00e2670422",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1345.5320713014125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1336.8363514349876,
        1354.2277911678375
      ],
      "voteCount": 5211,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.684069913230044
      }
    },
    {
      "id": "163246ce9bc2182b1e84c016",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1410.3142623783433,
      "unit": "Arena rating",
      "confidenceInterval": [
        1404.8670819818767,
        1415.76144277481
      ],
      "voteCount": 15162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.724090158615593
      }
    },
    {
      "id": "9b38f266aa78f2fbe28861fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1371.3770623300413,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.6558454146,
        1377.0982792454827
      ],
      "voteCount": 24391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.520805381851844
      }
    },
    {
      "id": "ef8f5afedf101bf2309d7ba2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1428.8047496777347,
      "unit": "Arena rating",
      "confidenceInterval": [
        1417.063770948942,
        1440.5457284065274
      ],
      "voteCount": 2704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 35.8849561961607
      }
    },
    {
      "id": "5a699ec4391bf95c76402b3e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1421.3830801992326,
      "unit": "Arena rating",
      "confidenceInterval": [
        1400.0984307758529,
        1442.6677296226123
      ],
      "voteCount": 948,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.93340036229215
      }
    },
    {
      "id": "bf27db159d0d2611d32875fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1381.1484086360942,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.2499875428298,
        1406.0468297293585
      ],
      "voteCount": 607,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.37915356476205
      }
    },
    {
      "id": "853b8cd718976b5f94d08140",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1425.411031132121,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.7839265706587,
        1432.0381356935834
      ],
      "voteCount": 9351,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.432769923749689
      }
    },
    {
      "id": "7ed8cab9235ef6fb313a78b2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1412.1101802130952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.0864656725905,
        1417.1338947535999
      ],
      "voteCount": 20403,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.569823851428649
      }
    },
    {
      "id": "4af3732587e6deb99c7e7792",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1388.6453162302294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.9042025427364,
        1396.3864299177226
      ],
      "voteCount": 6535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.59950110616204
      }
    },
    {
      "id": "30499adadf97f8283086e182",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1347.341986003599,
      "unit": "Arena rating",
      "confidenceInterval": [
        1339.3874906009537,
        1355.296481406244
      ],
      "voteCount": 6285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.471345929791656
      }
    },
    {
      "id": "f06b68323680919e500f7231",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1393.2178365032416,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.9026609787893,
        1405.5330120276942
      ],
      "voteCount": 2492,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.480716903967725
      }
    },
    {
      "id": "c26b12a0d4c9082572480ca4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1405.324337166475,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.0236456571897,
        1413.6250286757604
      ],
      "voteCount": 5514,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.936279613657895
      }
    },
    {
      "id": "80121f43a52e245bc2cdb91e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1420.5005014159856,
      "unit": "Arena rating",
      "confidenceInterval": [
        1406.0972332683564,
        1434.9037695636148
      ],
      "voteCount": 1747,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 54.00399770393033
      }
    },
    {
      "id": "d26d51592edd5f79c4af519d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1396.4435908147773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1383.6504252637674,
        1409.2367563657872
      ],
      "voteCount": 2380,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.60493017232795
      }
    },
    {
      "id": "f0d9745f0a6c8705cc22c55e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1435.6880369854273,
      "unit": "Arena rating",
      "confidenceInterval": [
        1429.8258677412882,
        1441.5502062295664
      ],
      "voteCount": 12786,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 8.945827575139765
      }
    },
    {
      "id": "8f0b7b1a3d2c8394a3edf5b5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1363.7677736095127,
      "unit": "Arena rating",
      "confidenceInterval": [
        1356.63256309651,
        1370.9029841225154
      ],
      "voteCount": 7950,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.253097700957323
      }
    },
    {
      "id": "671b91ad7d469a895cc3ebc1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1386.9239633472628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.5343712356291,
        1393.3135554588966
      ],
      "voteCount": 10231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.627964338213395
      }
    },
    {
      "id": "dfc3b994d874b80973fa157b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1338.2941701672262,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.624278327492,
        1374.9640620069601
      ],
      "voteCount": 291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 350.0443530186845
      }
    },
    {
      "id": "5cf320596714eb9ba7f25770",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1333.4064516181384,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.9324590927818,
        1358.880444143495
      ],
      "voteCount": 580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.92652647638232
      }
    },
    {
      "id": "080d6cb3cf0ba0c71527278f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1407.3690330904687,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.019856027216,
        1413.7182101537214
      ],
      "voteCount": 11283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.493942864458575
      }
    },
    {
      "id": "0a43a3d47f693970eb6958dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1405.950711942641,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.319779455562,
        1418.58164442972
      ],
      "voteCount": 2146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.5312158583337
      }
    },
    {
      "id": "209a07648444753ed7a37db2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1397.550828071435,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.5335221921623,
        1405.5681339507078
      ],
      "voteCount": 6092,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.732495794451065
      }
    },
    {
      "id": "b63a673f22e522c093d3de42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1394.109294534393,
      "unit": "Arena rating",
      "confidenceInterval": [
        1390.0250355942032,
        1398.193553474583
      ],
      "voteCount": 34466,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 4.34240528641325
      }
    },
    {
      "id": "9122c8b24495849b2a763d20",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1374.8685768046505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1365.2020055889257,
        1384.5351480203756
      ],
      "voteCount": 4040,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.32476916459518
      }
    },
    {
      "id": "0bbb4d6f5e8c93bd0f0161c7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3.5-flash",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1404.2191857739097,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.2840088472399,
        1423.1543627005794
      ],
      "voteCount": 1095,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 93.33457469667695
      }
    },
    {
      "id": "4b337c7f3327a3cb1a8a909b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1395.0072067326723,
      "unit": "Arena rating",
      "confidenceInterval": [
        1357.110847977287,
        1432.9035654880572
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 373.8512044383577
      }
    },
    {
      "id": "29365ca77afbf5b1a71da34c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1407.8117631902333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.2314259067273,
        1424.3921004737392
      ],
      "voteCount": 1233,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.5633297834352
      }
    },
    {
      "id": "4308e830d89339bff0ef882a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1308.4039669104022,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.4486495962099,
        1329.3592842245948
      ],
      "voteCount": 786,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.3121257405924
      }
    },
    {
      "id": "fec1d2cfd86baa66ac718bc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1373.2990611197804,
      "unit": "Arena rating",
      "confidenceInterval": [
        1362.9369886882846,
        1383.6611335512764
      ],
      "voteCount": 3159,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.950981667992025
      }
    },
    {
      "id": "bcff2151aec49c7e8c42fd35",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1308.2998827012216,
      "unit": "Arena rating",
      "confidenceInterval": [
        1297.735549133099,
        1318.8642162693436
      ],
      "voteCount": 4650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.052802320132677
      }
    },
    {
      "id": "027e2b8d5146efaffa5115d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1361.040938092708,
      "unit": "Arena rating",
      "confidenceInterval": [
        1325.8643841036694,
        1396.2174920817467
      ],
      "voteCount": 259,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 322.1145945592004
      }
    },
    {
      "id": "6cb3f863742f71604b9e295d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1361.2848643127372,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.4510873056277,
        1408.1186413198466
      ],
      "voteCount": 145,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 570.9816950101599
      }
    },
    {
      "id": "e025f3bb2c9132ceba7913e1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1402.1037670806054,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.3169840481378,
        1416.8905501130728
      ],
      "voteCount": 1564,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.91820807017287
      }
    },
    {
      "id": "184ef69be974742d5d395da2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1378.1324607747524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1367.4700872567187,
        1388.7948342927862
      ],
      "voteCount": 3007,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.594540601511458
      }
    },
    {
      "id": "1e0a730acfb362369ed72d1b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1356.7686442425056,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.028482227492,
        1373.5088062575187
      ],
      "voteCount": 1160,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.94963641918125
      }
    },
    {
      "id": "76a907bf3c698516a4e0c88c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1323.1164685301146,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.7064121587434,
        1340.5265249014856
      ],
      "voteCount": 1103,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 78.90493611995811
      }
    },
    {
      "id": "e79757f16db86e015a1b8645",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1340.2449815096843,
      "unit": "Arena rating",
      "confidenceInterval": [
        1311.9177786175103,
        1368.572184401858
      ],
      "voteCount": 416,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.8868997818377
      }
    },
    {
      "id": "279faa3ca64ca1fc224cc493",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1351.811228817674,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.527757057966,
        1370.0947005773814
      ],
      "voteCount": 1078,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.02041468913289
      }
    },
    {
      "id": "dffe03cecf0803ce73f83db3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1377.7953107124238,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.974149689978,
        1410.6164717348697
      ],
      "voteCount": 306,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 280.4217515122722
      }
    },
    {
      "id": "0423013950a7833c899b65f0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1365.7770121342683,
      "unit": "Arena rating",
      "confidenceInterval": [
        1334.5466513806532,
        1397.0073728878838
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 253.89714645560605
      }
    },
    {
      "id": "bf2fb6755768bd413a5f5367",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1391.2790831996913,
      "unit": "Arena rating",
      "confidenceInterval": [
        1378.7171142182708,
        1403.8410521811115
      ],
      "voteCount": 2180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.07894215605692
      }
    },
    {
      "id": "06e8e157e8a7c67ada0e391f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1317.6426104695352,
      "unit": "Arena rating",
      "confidenceInterval": [
        1302.39858214885,
        1332.8866387902199
      ],
      "voteCount": 1411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.49274775249444
      }
    },
    {
      "id": "cd3513b126d6737bc849cf77",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1344.82942384063,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.4567418354964,
        1359.2021058457635
      ],
      "voteCount": 1641,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.77488023765093
      }
    },
    {
      "id": "070d419762a37264efed226c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1251.0745924995408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1205.5044793559175,
        1296.6447056431643
      ],
      "voteCount": 192,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 540.5850508498772
      }
    },
    {
      "id": "5de96855ec0e2c8cf1670ae3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1347.314761178532,
      "unit": "Arena rating",
      "confidenceInterval": [
        1330.8884311596466,
        1363.7410911974177
      ],
      "voteCount": 1258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.24006516372981
      }
    },
    {
      "id": "3c6b9394d2ca4878cf00a8a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1363.8419723110053,
      "unit": "Arena rating",
      "confidenceInterval": [
        1332.7612002564783,
        1394.9227443655323
      ],
      "voteCount": 353,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 251.47071375632163
      }
    },
    {
      "id": "960dd3f05f79d48749fa63f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1341.2001497806057,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.3685831357448,
        1359.0317164254664
      ],
      "voteCount": 1116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 82.77188012460769
      }
    },
    {
      "id": "9747edfaa163e65707a81e72",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1348.2203674741577,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.8202855640802,
        1355.6204493842351
      ],
      "voteCount": 6545,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.255316751244093
      }
    },
    {
      "id": "5b3cc6788a174c34f978292b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1326.2872632340652,
      "unit": "Arena rating",
      "confidenceInterval": [
        1298.0182088371428,
        1354.5563176309877
      ],
      "voteCount": 405,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 208.03019732794135
      }
    },
    {
      "id": "99adc2fbfd0dabc632c35fb4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "step-3",
      "organization": "stepfun",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1377.2768121545628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.4199407156207,
        1421.1336835935047
      ],
      "voteCount": 194,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 500.701754773551
      }
    },
    {
      "id": "5391de8c7f7d6cd5cf7c274f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1125.699812885007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.4938558668196,
        1147.9057699031948
      ],
      "voteCount": 704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.36387167219365
      }
    },
    {
      "id": "4cf9d337e0c75ace5496c584",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1088.5726826971768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1067.7072498563405,
        1109.4381155380133
      ],
      "voteCount": 869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 113.33358183878292
      }
    },
    {
      "id": "61ff23cbb818268b43f1c029",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1151.401080154129,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.486284845816,
        1163.3158754624417
      ],
      "voteCount": 3987,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 36.95532188819414
      }
    },
    {
      "id": "022837ce326ab193c2c32e09",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 956.0650314778331,
      "unit": "Arena rating",
      "confidenceInterval": [
        939.3962061043123,
        972.733856851354
      ],
      "voteCount": 3433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.32922499029318
      }
    },
    {
      "id": "eb87fa7dd71df05da209207f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1124.240666889259,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.5394936647508,
        1173.941840113767
      ],
      "voteCount": 169,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 643.0386827487093
      }
    },
    {
      "id": "0855c7e2159769b94f979f41",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1121.873763664734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.6281540066668,
        1140.119373322801
      ],
      "voteCount": 1029,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.66037756312545
      }
    },
    {
      "id": "43232a0534981940a107e8ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1106.0793662366332,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.1266597223039,
        1123.0320727509625
      ],
      "voteCount": 1237,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.81383286286379
      }
    },
    {
      "id": "5bdc31181fb7cc3cd73eb3fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1082.6722758306946,
      "unit": "Arena rating",
      "confidenceInterval": [
        1052.7863542855114,
        1112.5581973758779
      ],
      "voteCount": 455,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 232.50758326324
      }
    },
    {
      "id": "ae2ad3333b87cefbfc5659f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1087.2222460549365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.992082702443,
        1108.4524094074304
      ],
      "voteCount": 806,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.33038332872773
      }
    },
    {
      "id": "4f1894dd07ed64887558967b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1114.1837880921667,
      "unit": "Arena rating",
      "confidenceInterval": [
        1078.570419249294,
        1149.7971569350393
      ],
      "voteCount": 309,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 330.1641640686173
      }
    },
    {
      "id": "2042dcc6a9097083573f8284",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1131.9625207930912,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.9960179141428,
        1152.9290236720399
      ],
      "voteCount": 863,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.43419375078008
      }
    },
    {
      "id": "f87271978531ab81e9ae5707",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1081.8872875144625,
      "unit": "Arena rating",
      "confidenceInterval": [
        1058.6417968231667,
        1105.1327782057583
      ],
      "voteCount": 530,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.66344654489322
      }
    },
    {
      "id": "ae901753d4adc11230e954fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1125.9602436373066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1094.9260078744062,
        1156.9944794002072
      ],
      "voteCount": 327,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.71823865425674
      }
    },
    {
      "id": "dff731b90370e87742cff553",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1136.6818390185958,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.9509840835444,
        1154.4126939536472
      ],
      "voteCount": 1324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.83953841552122
      }
    },
    {
      "id": "7cbb566fbc0c082f83c875c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1091.2948975802706,
      "unit": "Arena rating",
      "confidenceInterval": [
        1073.3202263313888,
        1109.2695688291526
      ],
      "voteCount": 1271,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.10575814710951
      }
    },
    {
      "id": "7734e2b4464847e69edfc126",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1087.9721132265206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.7222213256427,
        1103.2220051273982
      ],
      "voteCount": 1660,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.53929349330724
      }
    },
    {
      "id": "0707db8667d1a418e94f5330",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1070.4323220592091,
      "unit": "Arena rating",
      "confidenceInterval": [
        1038.2254370492333,
        1102.639207069185
      ],
      "voteCount": 334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 270.0233141789566
      }
    },
    {
      "id": "ae0f9a92bd5639752cc109f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1084.090315232018,
      "unit": "Arena rating",
      "confidenceInterval": [
        1063.845597101883,
        1104.335033362153
      ],
      "voteCount": 676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 106.69087742415473
      }
    },
    {
      "id": "b6c66f75d7fa317827e05ab7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1073.9194353872076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.933424378019,
        1096.905446396396
      ],
      "voteCount": 738,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 137.5406393186483
      }
    },
    {
      "id": "9e4d1270ea52d33574fff079",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "stripedhyena-nous-7b",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1120.1384203903485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1109.1537665842902,
        1131.1230741964068
      ],
      "voteCount": 5182,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.410624158961625
      }
    },
    {
      "id": "568aeb2c4800caf61b4c638d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1398.9213070666378,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.7453251056877,
        1416.0972890275882
      ],
      "voteCount": 1429,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.79747983595061
      }
    },
    {
      "id": "f1075fa7e6a5f50222d8cddf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1441.261156229095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1433.4876030844791,
        1449.034709373711
      ],
      "voteCount": 6942,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.730515752671282
      }
    },
    {
      "id": "dba04f4dfb0cd1a9eb85b01d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1350.725187560874,
      "unit": "Arena rating",
      "confidenceInterval": [
        1341.1127651267268,
        1360.3376099950212
      ],
      "voteCount": 4357,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.05301458777618
      }
    },
    {
      "id": "e2dd63f8ba81f700db6963a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1397.4272126431276,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.508403519151,
        1403.3460217671043
      ],
      "voteCount": 13247,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.119530647406378
      }
    },
    {
      "id": "e074fdc333025ccfa38512c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1350.6551275911488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.4153716274532,
        1356.8948835548445
      ],
      "voteCount": 21036,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.135356463209561
      }
    },
    {
      "id": "113fc6cf394652b49ff424dd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1402.3347449645114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.5433760688245,
        1415.1261138601983
      ],
      "voteCount": 2445,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.592964252049995
      }
    },
    {
      "id": "fbe6ee2c6c9e629381544458",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1431.244493400665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.5362709874823,
        1454.9527158138476
      ],
      "voteCount": 746,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 146.31936361389108
      }
    },
    {
      "id": "617fbace05ae3d4370349bcf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1372.5375446815153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1343.5360559889289,
        1401.5390333741016
      ],
      "voteCount": 451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 218.94972343715875
      }
    },
    {
      "id": "2c5fb59df9def7f94800970f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1416.980414833011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1409.8131183819594,
        1424.147711284063
      ],
      "voteCount": 8413,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.372559960951952
      }
    },
    {
      "id": "c4f2a1d669a56dcbbee0955c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1402.6070211518727,
      "unit": "Arena rating",
      "confidenceInterval": [
        1397.0930648033773,
        1408.1209775003683
      ],
      "voteCount": 17116,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 7.914627237269048
      }
    },
    {
      "id": "977798285a24b5349d5b3321",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1379.3948198836408,
      "unit": "Arena rating",
      "confidenceInterval": [
        1370.5982767295118,
        1388.1913630377699
      ],
      "voteCount": 5376,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.14317348545036
      }
    },
    {
      "id": "5077ca7032037a1b9d336986",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1351.4399796193834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1342.6568685164266,
        1360.2230907223404
      ],
      "voteCount": 5249,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.081704437729034
      }
    },
    {
      "id": "b22dd6c2b21dbca6a6f21aa8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1395.5461719880473,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.4192807303073,
        1409.6730632457875
      ],
      "voteCount": 2031,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.95137210190199
      }
    },
    {
      "id": "18a0a805ec09cb0461d72cbc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1407.474704583055,
      "unit": "Arena rating",
      "confidenceInterval": [
        1398.1715162381024,
        1416.7778929280078
      ],
      "voteCount": 4569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.530324395361674
      }
    },
    {
      "id": "aecfbc670d283642a75367c3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1377.4586018324974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.2226559690157,
        1393.694547695979
      ],
      "voteCount": 1473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.62131038912827
      }
    },
    {
      "id": "bcf666c28fb6c8fe33daf2fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1416.2369183084893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1401.9891424886532,
        1430.4846941283251
      ],
      "voteCount": 2068,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.84427747051053
      }
    },
    {
      "id": "95dbb880205c6bfb7cd28d6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1425.275049499199,
      "unit": "Arena rating",
      "confidenceInterval": [
        1418.7683517687028,
        1431.7817472296954
      ],
      "voteCount": 10619,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.02110352660096
      }
    },
    {
      "id": "8ed9dd9dd7d1b388c8896b29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1358.6362203777821,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.765659329074,
        1366.5067814264903
      ],
      "voteCount": 6480,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.125574713371225
      }
    },
    {
      "id": "6fb251d8db72fd367adb719e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1370.6965088847387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1363.64824461913,
        1377.7447731503473
      ],
      "voteCount": 8473,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.932073849194209
      }
    },
    {
      "id": "b79e4dbe478fbbe08fdaab31",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1346.5478396712274,
      "unit": "Arena rating",
      "confidenceInterval": [
        1303.270976895607,
        1389.8247024468478
      ],
      "voteCount": 180,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 487.54573174403043
      }
    },
    {
      "id": "5c980d2008b955658df6f623",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1317.7714950921068,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.6663349352204,
        1347.876655248993
      ],
      "voteCount": 431,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 235.93137669194445
      }
    },
    {
      "id": "35ffbfaddb4ce67199b1c21b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1390.9616837391961,
      "unit": "Arena rating",
      "confidenceInterval": [
        1384.0461433071848,
        1397.8772241712074
      ],
      "voteCount": 9676,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.44961919392431
      }
    },
    {
      "id": "1272e74f04e45ed837db5d18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1361.151234199017,
      "unit": "Arena rating",
      "confidenceInterval": [
        1346.770803921288,
        1375.5316644767456
      ],
      "voteCount": 1813,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.83287564052396
      }
    },
    {
      "id": "a300fdd3b4f43c93ef88a1d5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1378.586711042506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.4937431145136,
        1387.6796789704983
      ],
      "voteCount": 4985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.52361110682335
      }
    },
    {
      "id": "97c7039b9ff78a086c7946e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1377.7980233942756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1373.349495178202,
        1382.2465516103491
      ],
      "voteCount": 28284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 5.15153336607339
      }
    },
    {
      "id": "402bfa6617886c62a6d43ac3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1361.9431659867037,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.5220589077421,
        1373.3642730656654
      ],
      "voteCount": 3072,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.9562892634462
      }
    },
    {
      "id": "b4b10780b97bd952c7ef7274",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-preview",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1390.8099299234802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1368.7219687080078,
        1412.8978911389527
      ],
      "voteCount": 839,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 127.00332176619796
      }
    },
    {
      "id": "10b1fc9119e93efb8e9fb8b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1410.783617660492,
      "unit": "Arena rating",
      "confidenceInterval": [
        1393.6763797331887,
        1427.890855587795
      ],
      "voteCount": 1452,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 76.1839715487248
      }
    },
    {
      "id": "eb0e6fc9b1dc556e322d989d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1416.0841347144924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1407.8394101893828,
        1424.3288592396025
      ],
      "voteCount": 6447,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.695226128355454
      }
    },
    {
      "id": "3fa8137baea8a5f609d8f0fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1338.426904557028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1328.0680144039802,
        1348.7857947100756
      ],
      "voteCount": 3756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.933816347280295
      }
    },
    {
      "id": "e27233ad9cf68a64f1ec87f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1386.7277924150353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1380.3156352944654,
        1393.1399495356052
      ],
      "voteCount": 11332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.703162745720975
      }
    },
    {
      "id": "276a3d9af4d443dc7707680a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1346.9627244235337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.1459519421314,
        1353.7794969049357
      ],
      "voteCount": 18070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.09654697139354
      }
    },
    {
      "id": "72970ed1ebba02ab2b112ce4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1401.4743631130445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.7591701592437,
        1415.1895560668452
      ],
      "voteCount": 2131,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.96746953179486
      }
    },
    {
      "id": "cd29bef6c03f016cd7452712",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1415.7303830305582,
      "unit": "Arena rating",
      "confidenceInterval": [
        1391.6339177039843,
        1439.826848357132
      ],
      "voteCount": 768,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.15081752454054
      }
    },
    {
      "id": "c294b649e8337a98ab4018cd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1368.4740673593753,
      "unit": "Arena rating",
      "confidenceInterval": [
        1337.1495208991978,
        1399.798613819553
      ],
      "voteCount": 347,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 255.4308810105964
      }
    },
    {
      "id": "ca94a161ead2ddcebb4fa5ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1397.2971940145826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1389.6982138750598,
        1404.8961741541052
      ],
      "voteCount": 7644,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.031919345272753
      }
    },
    {
      "id": "24d8443c9ed06b58e81243d9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1387.5128523424773,
      "unit": "Arena rating",
      "confidenceInterval": [
        1381.5485072344177,
        1393.4771974505372
      ],
      "voteCount": 15320,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 9.260391488879527
      }
    },
    {
      "id": "2332d924f5a6a68b6566d5db",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1371.2433926841074,
      "unit": "Arena rating",
      "confidenceInterval": [
        1361.8059713086864,
        1380.6808140595285
      ],
      "voteCount": 4704,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.185182081728293
      }
    },
    {
      "id": "4d6be0d932770767f6451bd4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1331.4564041168624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1322.019603313528,
        1340.8932049201971
      ],
      "voteCount": 4762,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.182133027713935
      }
    },
    {
      "id": "a65d7f95e04d7d29fb9c861a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1374.4437382515969,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.7130877691675,
        1389.1743887340263
      ],
      "voteCount": 1828,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.4868904663378
      }
    },
    {
      "id": "a5d5a0aff12186d60ecc863d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1397.319043027087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1387.1967569824028,
        1407.4413290717714
      ],
      "voteCount": 3916,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.672334535632864
      }
    },
    {
      "id": "513ed7114cffdd42c7e0f767",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1387.490144103734,
      "unit": "Arena rating",
      "confidenceInterval": [
        1369.9529631699704,
        1405.0273250374976
      ],
      "voteCount": 1268,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.06143745359451
      }
    },
    {
      "id": "6c5dd64dfcd49cf33a797786",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1400.9621915040307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1385.7406778061475,
        1416.1837052019137
      ],
      "voteCount": 1803,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.314190537900274
      }
    },
    {
      "id": "473d935a73338c58f16f83da",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1409.659395680898,
      "unit": "Arena rating",
      "confidenceInterval": [
        1402.687302356725,
        1416.6314890050705
      ],
      "voteCount": 9401,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.654069089354929
      }
    },
    {
      "id": "f6c35ea2925dda3b4f922726",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1348.8672088729927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.3364962972032,
        1357.3979214487822
      ],
      "voteCount": 5628,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.944120045931452
      }
    },
    {
      "id": "ab6da5b5db2271060a14d5c1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1360.418504391976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1352.9908529671343,
        1367.8461558168183
      ],
      "voteCount": 7853,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.361732941598834
      }
    },
    {
      "id": "d953759d7cc730a86c1dc3ac",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1361.4779115433134,
      "unit": "Arena rating",
      "confidenceInterval": [
        1317.4288370836946,
        1405.5269860029325
      ],
      "voteCount": 191,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 505.10002874336504
      }
    },
    {
      "id": "43a5d0c4b65d5698b1ac9f00",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1322.1114071865618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1292.9413401030713,
        1351.2814742700525
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 221.50252114419138
      }
    },
    {
      "id": "af1cd25f585095210f10da1c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1365.999463819076,
      "unit": "Arena rating",
      "confidenceInterval": [
        1358.655006485791,
        1373.343921152361
      ],
      "voteCount": 9511,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.041814851654559
      }
    },
    {
      "id": "f05e13148443dec93ada64e6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1388.7838791929,
      "unit": "Arena rating",
      "confidenceInterval": [
        1372.4358113408366,
        1405.1319470449637
      ],
      "voteCount": 1358,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.57235127861712
      }
    },
    {
      "id": "93d7609dba8039238c53eb76",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1350.8181335886125,
      "unit": "Arena rating",
      "confidenceInterval": [
        1340.8916320650815,
        1360.744635112144
      ],
      "voteCount": 4322,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.650524213835936
      }
    },
    {
      "id": "5a3c3d686d9715a2889d02ae",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1371.4906115024032,
      "unit": "Arena rating",
      "confidenceInterval": [
        1366.537349740472,
        1376.443873264334
      ],
      "voteCount": 23918,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.386845005349748
      }
    },
    {
      "id": "02ae4bf409bb63cdf6bcd540",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1358.2993210657087,
      "unit": "Arena rating",
      "confidenceInterval": [
        1345.808496850681,
        1370.7901452807369
      ],
      "voteCount": 2536,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 40.61495823676069
      }
    },
    {
      "id": "a4b5f67180abb1dcb7d4a3fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "trinity-large-thinking",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1362.3256439637494,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.1856974494613,
        1386.4655904780377
      ],
      "voteCount": 724,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 151.69680189553503
      }
    },
    {
      "id": "f2178dff2cb2b2018efbc8e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1102.5387002152174,
      "unit": "Arena rating",
      "confidenceInterval": [
        1066.9813779769731,
        1138.0960224534615
      ],
      "voteCount": 274,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 329.12578886525023
      }
    },
    {
      "id": "ecbadc630a5c6aec41ff72f9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1213.1970547680007,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.933121150473,
        1234.4609883855283
      ],
      "voteCount": 805,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 117.70394894117965
      }
    },
    {
      "id": "dfcc099c77dcafb77257bfb9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1145.7372299838028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.3974301615426,
        1165.077029806063
      ],
      "voteCount": 1126,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 97.36609830364178
      }
    },
    {
      "id": "fe30283a0081f565bda15d17",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1204.3413629910501,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.4863581309542,
        1215.196367851146
      ],
      "voteCount": 5039,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.6735373233583
      }
    },
    {
      "id": "6f0e55d4ee0d5654e1ca5541",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1043.1859684969345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1029.0544848192985,
        1057.3174521745707
      ],
      "voteCount": 4397,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.98515466455279
      }
    },
    {
      "id": "2a94f827d51201d1a09e5dbc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1204.8526410267173,
      "unit": "Arena rating",
      "confidenceInterval": [
        1187.1795538294587,
        1222.5257282239763
      ],
      "voteCount": 1200,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.30713503925563
      }
    },
    {
      "id": "5b394c0e4c5a49ff05b8c376",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1186.1104276577028,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.6681315596427,
        1202.5527237557626
      ],
      "voteCount": 1419,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.3766755275089
      }
    },
    {
      "id": "dd54493a36fbe13d9687d021",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1166.6773551243996,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.2681737908292,
        1192.0865364579697
      ],
      "voteCount": 540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 168.0680507530722
      }
    },
    {
      "id": "cdcdcb5f4331daa9b4872b71",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1170.7034919183122,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.6117276008645,
        1190.79525623576
      ],
      "voteCount": 989,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 105.08481601136266
      }
    },
    {
      "id": "c0bacf87d9e7ce4a0ea6e601",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1218.7439855485923,
      "unit": "Arena rating",
      "confidenceInterval": [
        1188.1858489137953,
        1249.3021221833897
      ],
      "voteCount": 377,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 243.0846608482449
      }
    },
    {
      "id": "033cc0c837101aee7c59447c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1189.5480930037202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1170.6904152897737,
        1208.4057707176667
      ],
      "voteCount": 1112,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 92.57212568500789
      }
    },
    {
      "id": "5806d0930db10a9d87e1b934",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1142.0660747233196,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.5481932230832,
        1162.5839562235558
      ],
      "voteCount": 751,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.58947652643847
      }
    },
    {
      "id": "3b9faaf9161dae2a503e7668",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1169.497017126766,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.2096499217946,
        1200.7843843317373
      ],
      "voteCount": 348,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 254.82489655891843
      }
    },
    {
      "id": "b237b98cec82ea84aa99e004",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1196.9759963128784,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.3001701244493,
        1213.6518225013074
      ],
      "voteCount": 1495,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.38999350159615
      }
    },
    {
      "id": "809c786b5ff3ac80f0577e45",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1164.6719683801002,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.8121917543133,
        1181.5317450058874
      ],
      "voteCount": 1547,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 73.99586488865991
      }
    },
    {
      "id": "128c998a6a1584e03ab8a896",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1169.0927126821573,
      "unit": "Arena rating",
      "confidenceInterval": [
        1154.3783270606502,
        1183.8070983036644
      ],
      "voteCount": 2008,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.362219230894055
      }
    },
    {
      "id": "7e3b283f410abffddedce7bf",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1175.499741331569,
      "unit": "Arena rating",
      "confidenceInterval": [
        1142.165736471846,
        1208.833746191292
      ],
      "voteCount": 280,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 289.25362260873084
      }
    },
    {
      "id": "cec09198fb7b5644b52bfe42",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1144.6441100204834,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.5868338453345,
        1163.7013861956325
      ],
      "voteCount": 888,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.54214978420052
      }
    },
    {
      "id": "07095ab7615f5c55ddbe9287",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1134.0495383126574,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.9098473437368,
        1155.189229281578
      ],
      "voteCount": 827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.33250676906019
      }
    },
    {
      "id": "badb580ef32299225713c586",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "tulu-2-dpo-70b",
      "license": "AI2 ImpACT Low-risk",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1176.9395285543537,
      "unit": "Arena rating",
      "confidenceInterval": [
        1167.1271974999902,
        1186.7518596087175
      ],
      "voteCount": 6535,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.06387422448813
      }
    },
    {
      "id": "07de8d8ad5f5f1dc23785906",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1145.6443406210415,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.788869147228,
        1165.4998120948549
      ],
      "voteCount": 1178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.62761254230516
      }
    },
    {
      "id": "bca818a89b02f460bcfc9417",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1161.5822583102145,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.7679349348277,
        1175.396581685601
      ],
      "voteCount": 2389,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.67788000009669
      }
    },
    {
      "id": "5af694acf10a56e1a1a59c83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1125.492526170576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.6854958945028,
        1138.2995564466491
      ],
      "voteCount": 3346,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.69732727803076
      }
    },
    {
      "id": "1846a00eccece82857b54fe5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1161.3129796404437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.7715219147808,
        1168.8544373661068
      ],
      "voteCount": 14788,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 14.805204814791043
      }
    },
    {
      "id": "3340a9c688c522d32f5f40b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 985.0664555983124,
      "unit": "Arena rating",
      "confidenceInterval": [
        974.9158211442357,
        995.2170900523893
      ],
      "voteCount": 13246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.821940473560176
      }
    },
    {
      "id": "df66e75964806057e82ff735",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1111.3697720885345,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.0534527766333,
        1142.6860914004355
      ],
      "voteCount": 321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 255.2967247655535
      }
    },
    {
      "id": "3d03fd596741ac7fe8d742c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1116.7718942573767,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.264425616091,
        1163.2793628986624
      ],
      "voteCount": 198,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 563.0529286864347
      }
    },
    {
      "id": "f4760e92b742ca5eb646e7ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1079.375154653349,
      "unit": "Arena rating",
      "confidenceInterval": [
        1043.322814431126,
        1115.427494875572
      ],
      "voteCount": 283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 338.3535516499596
      }
    },
    {
      "id": "56b502733391691d724315d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1141.3044004661974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.2981907178807,
        1153.3106102145139
      ],
      "voteCount": 3220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.52456534065512
      }
    },
    {
      "id": "046ce9788ea1c71560b2b645",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1130.1454367110728,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.4476036695605,
        1140.8432697525845
      ],
      "voteCount": 3971,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.791711202929687
      }
    },
    {
      "id": "1a9681860f1e9427472ec5ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1119.7529161254495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.5263587408276,
        1136.9794735100713
      ],
      "voteCount": 1638,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.25041271483678
      }
    },
    {
      "id": "06e3280bb6878f5849c390df",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1109.9520457424392,
      "unit": "Arena rating",
      "confidenceInterval": [
        1097.3767134517532,
        1122.527378033125
      ],
      "voteCount": 3239,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.166387459177116
      }
    },
    {
      "id": "e1c0ceec03fe5885d148cb57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1172.2102200438112,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.211332993451,
        1194.209107094171
      ],
      "voteCount": 899,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.98105408482601
      }
    },
    {
      "id": "5ffe32782827752e65924a9a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1153.2903686126592,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.2883162426974,
        1166.2924209826213
      ],
      "voteCount": 3288,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.00759547923166
      }
    },
    {
      "id": "f83ce5a521c583af781c0067",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1083.6595946593225,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.6592252514768,
        1098.6599640671684
      ],
      "voteCount": 1884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.57438355441704
      }
    },
    {
      "id": "df9e8fdf1837b48469ab5bda",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1158.6813407303664,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.4090896526895,
        1180.9535918080433
      ],
      "voteCount": 884,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 129.13145531973802
      }
    },
    {
      "id": "f81812f6f78b1984e99d65dc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1161.120050877064,
      "unit": "Arena rating",
      "confidenceInterval": [
        1150.3766665464032,
        1171.8634352077245
      ],
      "voteCount": 4692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.045957086539865
      }
    },
    {
      "id": "b76130fea4d4259b9e9b828b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1143.7602545077991,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.0157950433477,
        1154.5047139722506
      ],
      "voteCount": 4672,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.051971027605894
      }
    },
    {
      "id": "26c9b9d2b8601d184530e54c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1114.1730928825814,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.529151018576,
        1123.817034746587
      ],
      "voteCount": 5665,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.21101436133912
      }
    },
    {
      "id": "1653750156de95dd65cbf482",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1002.2463201712269,
      "unit": "Arena rating",
      "confidenceInterval": [
        949.0197813520588,
        1055.472858990395
      ],
      "voteCount": 125,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 737.4970205086045
      }
    },
    {
      "id": "5f0b45820752c19279e278bd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1142.1964935196456,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.669335080099,
        1163.7236519591925
      ],
      "voteCount": 756,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.63608439192123
      }
    },
    {
      "id": "5575fd8ae50083276669d921",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1082.1616460734062,
      "unit": "Arena rating",
      "confidenceInterval": [
        1068.4500014139999,
        1095.8732907328124
      ],
      "voteCount": 2146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 48.94213579825696
      }
    },
    {
      "id": "8719503ec179f9cc3dd9ac43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1099.409613465873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.3492710355654,
        1113.4699558961806
      ],
      "voteCount": 2552,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.463060906062395
      }
    },
    {
      "id": "c4a4d23798f62f4e4a27166a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1140.0667852625284,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.3626875411996,
        1146.770882983857
      ],
      "voteCount": 19367,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.699963049194798
      }
    },
    {
      "id": "b29571bf17cc961dceba0026",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1127.1017999028231,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.8352439112894,
        1154.368355894357
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.5371717729644
      }
    },
    {
      "id": "ec33c34971a10d83bb513420",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-13b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1161.7922125288776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.6508703977904,
        1210.933554659965
      ],
      "voteCount": 161,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 628.6339693232002
      }
    },
    {
      "id": "dc55d24e340f17201cb0f727",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1131.9267476404477,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.6748439233895,
        1149.1786513575057
      ],
      "voteCount": 1385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.47790507588041
      }
    },
    {
      "id": "b70d613ea727e7828aece945",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1191.880250276974,
      "unit": "Arena rating",
      "confidenceInterval": [
        1179.1422737554658,
        1204.6182267984823
      ],
      "voteCount": 2866,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.23813229193388
      }
    },
    {
      "id": "64d1ce26413d4fb9d9c27d58",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1171.7287946743447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.6878315970403,
        1183.7697577516492
      ],
      "voteCount": 4010,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.742117928732924
      }
    },
    {
      "id": "728477cfe4368d9cc7c7dc74",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1199.0966439747383,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.7835938665266,
        1206.40969408295
      ],
      "voteCount": 16692,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 13.921977139807256
      }
    },
    {
      "id": "e1fabb832a6e5a555685034c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1038.6891295624873,
      "unit": "Arena rating",
      "confidenceInterval": [
        1029.3545509564638,
        1048.0237081685107
      ],
      "voteCount": 15324,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.6826218421589
      }
    },
    {
      "id": "811d07235b83a997dedf4ee9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1140.9540089275406,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.1520310643004,
        1167.7559867907803
      ],
      "voteCount": 484,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 186.99823450191323
      }
    },
    {
      "id": "b8e52fc9164106e16c5c014f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1167.019593235337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.1398923057454,
        1204.8992941649285
      ],
      "voteCount": 295,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 373.5226145821391
      }
    },
    {
      "id": "39ef0c55b0dfb5caac45e8eb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1130.4125733337887,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.864651622302,
        1159.9604950452751
      ],
      "voteCount": 428,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 227.27815609133003
      }
    },
    {
      "id": "dbcd6cecee1869f38a57b441",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1174.2885052859651,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.9142897882043,
        1185.662720783726
      ],
      "voteCount": 3964,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.6780333274859
      }
    },
    {
      "id": "270573d5eef93202acd28ee2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1162.7314201097488,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.6492245377076,
        1172.81361568179
      ],
      "voteCount": 5071,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.461475261764953
      }
    },
    {
      "id": "0d2843d03088e3298dd3406a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1151.9008687482776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.3707992175903,
        1167.4309382789647
      ],
      "voteCount": 1909,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.78423663653937
      }
    },
    {
      "id": "867368cb4141571b40a10bbd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1164.4704843713826,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.4226525080019,
        1176.5183162347632
      ],
      "voteCount": 3642,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.785190310087415
      }
    },
    {
      "id": "70ff74e8d1238d13c512d359",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1191.169745413876,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.9264264652284,
        1210.4130643625238
      ],
      "voteCount": 1246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.39705680678732
      }
    },
    {
      "id": "6312577d8ccc1c8bc97c3015",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1192.419359894506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.8284766895008,
        1204.0102430995112
      ],
      "voteCount": 3986,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.97332126751655
      }
    },
    {
      "id": "09987bf9f230bc209c29e132",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1129.0674327400484,
      "unit": "Arena rating",
      "confidenceInterval": [
        1115.5840268590314,
        1142.5508386210652
      ],
      "voteCount": 2352,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.326352471321954
      }
    },
    {
      "id": "3fdc9f5766a4dd759d552614",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1175.5275878151447,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.2701940186153,
        1194.7849816116736
      ],
      "voteCount": 1203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.53812084014243
      }
    },
    {
      "id": "dc348914cb42b11709d26beb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1188.040572499152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.8783156087684,
        1198.202829389536
      ],
      "voteCount": 5525,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.88339766908996
      }
    },
    {
      "id": "a4448debe89c6e6960065546",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1170.0852122168071,
      "unit": "Arena rating",
      "confidenceInterval": [
        1159.8861930054632,
        1180.284231428151
      ],
      "voteCount": 5627,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.078252749450936
      }
    },
    {
      "id": "4cea5b0a313bd617784bef7f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1137.3815849181517,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.3343885725517,
        1146.4287812637517
      ],
      "voteCount": 6983,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.307468213611912
      }
    },
    {
      "id": "43df7d7312dcce15355a5715",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1024.8316729900346,
      "unit": "Arena rating",
      "confidenceInterval": [
        983.5002656712131,
        1066.163080308856
      ],
      "voteCount": 195,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 444.69700462535474
      }
    },
    {
      "id": "38be00c9ca6653cb6565c412",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1132.4369446439964,
      "unit": "Arena rating",
      "confidenceInterval": [
        1113.232247567645,
        1151.641641720348
      ],
      "voteCount": 1047,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 96.01050200188843
      }
    },
    {
      "id": "c441eac22edb99f6d767f59f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1115.270622035414,
      "unit": "Arena rating",
      "confidenceInterval": [
        1102.6816168381686,
        1127.8596272326595
      ],
      "voteCount": 2663,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.25595489987252
      }
    },
    {
      "id": "330d22099374299e029e0e4d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1139.218150762631,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.2470860970232,
        1152.189215428239
      ],
      "voteCount": 3114,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 43.79807943092322
      }
    },
    {
      "id": "ec40aedaaa7b52b727f32e5b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1171.8682825339772,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.6630492694144,
        1178.07351579854
      ],
      "voteCount": 22479,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 10.023514936619453
      }
    },
    {
      "id": "4b79a00e800fa10092724ebe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1142.3701494750628,
      "unit": "Arena rating",
      "confidenceInterval": [
        1120.548624530531,
        1164.1916744195948
      ],
      "voteCount": 703,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.95784339523057
      }
    },
    {
      "id": "2c3cfc71ef5d35cc33a277d1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-33b",
      "license": "Non-commercial",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1142.775758925965,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.720774261731,
        1180.8307435901988
      ],
      "voteCount": 275,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 376.9874741318723
      }
    },
    {
      "id": "9ad6486abb9e1f0233bb553f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1085.2503076797902,
      "unit": "Arena rating",
      "confidenceInterval": [
        1050.9757698280564,
        1119.5248455315245
      ],
      "voteCount": 335,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 305.80672598168854
      }
    },
    {
      "id": "74e56df89f0d07edcfafa307",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1130.025772731139,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.130731159728,
        1152.9208143025505
      ],
      "voteCount": 726,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 136.45413188678592
      }
    },
    {
      "id": "35fb76e59437f80155fe0e0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1088.6664337227255,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.5692913868454,
        1106.7635760586054
      ],
      "voteCount": 1323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 85.25577808118261
      }
    },
    {
      "id": "31ae9808643ebc212773b453",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1131.607060285564,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.6863058533331,
        1141.527814717795
      ],
      "voteCount": 5577,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.62083132960641
      }
    },
    {
      "id": "90af2e59e8dba755027ebdd2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 957.8493856245238,
      "unit": "Arena rating",
      "confidenceInterval": [
        944.4344188498778,
        971.26435239917
      ],
      "voteCount": 4750,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.847133332627905
      }
    },
    {
      "id": "719113dda71c27e7c433c986",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1111.56189600967,
      "unit": "Arena rating",
      "confidenceInterval": [
        1092.879803730839,
        1130.2439882885008
      ],
      "voteCount": 1066,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 90.85625753283045
      }
    },
    {
      "id": "3e823ca9892db49f0ceb301e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1103.314395131114,
      "unit": "Arena rating",
      "confidenceInterval": [
        1086.3351444764899,
        1120.2936457857381
      ],
      "voteCount": 1258,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.04829968227115
      }
    },
    {
      "id": "7bbaa90f2d7079b8fabe420d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1085.8218687665799,
      "unit": "Arena rating",
      "confidenceInterval": [
        1058.5682688702204,
        1113.075468662939
      ],
      "voteCount": 555,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 193.35329154371158
      }
    },
    {
      "id": "c30bfd1fb5decf381e0a923f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1096.7105280446135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1079.0027359566122,
        1114.4183201326148
      ],
      "voteCount": 1285,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.62677651070639
      }
    },
    {
      "id": "16485f25d5c39847c018cb19",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1147.4655050774295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1112.3288569746483,
        1182.6021531802107
      ],
      "voteCount": 305,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 321.3841661526916
      }
    },
    {
      "id": "f90468b75868575d3f118358",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1117.3637490758858,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.3548614332003,
        1136.3726367185714
      ],
      "voteCount": 1171,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 94.06265335077966
      }
    },
    {
      "id": "e29759f145f01e287211c984",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1044.081182218657,
      "unit": "Arena rating",
      "confidenceInterval": [
        1020.2404167740585,
        1067.9219476632557
      ],
      "voteCount": 590,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.9599609196545
      }
    },
    {
      "id": "5e62267c2c1f43792948f61b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1135.6009166879167,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.2367950783105,
        1170.965038297523
      ],
      "voteCount": 291,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 325.55889717777603
      }
    },
    {
      "id": "92cb6308a8df13b29d05bc83",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1130.5587098503588,
      "unit": "Arena rating",
      "confidenceInterval": [
        1114.1980528931895,
        1146.9193668075284
      ],
      "voteCount": 1601,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 69.67954325794648
      }
    },
    {
      "id": "1f06d2ac4b616977228f27a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1114.4779954297653,
      "unit": "Arena rating",
      "confidenceInterval": [
        1099.3077228834989,
        1129.6482679760318
      ],
      "voteCount": 1783,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 59.90879503594992
      }
    },
    {
      "id": "33353e2ef1eb976247b0b619",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1073.8806236944524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1059.6347635780237,
        1088.1264838108812
      ],
      "voteCount": 2020,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.83006793241752
      }
    },
    {
      "id": "19a43703442189add960b901",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1140.2147338873156,
      "unit": "Arena rating",
      "confidenceInterval": [
        1095.8090708162838,
        1184.6203969583476
      ],
      "voteCount": 162,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 513.310959408307
      }
    },
    {
      "id": "553d5a916f1f5f344730ce6a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1046.7862465032006,
      "unit": "Arena rating",
      "confidenceInterval": [
        1025.266187977004,
        1068.3063050293972
      ],
      "voteCount": 658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 120.55652307818896
      }
    },
    {
      "id": "27c7d1d1d6336413c182a823",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1059.9224632786286,
      "unit": "Arena rating",
      "confidenceInterval": [
        1038.917567747659,
        1080.927358809598
      ],
      "voteCount": 935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.85366806228578
      }
    },
    {
      "id": "abf45dba52677fd693d832e2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "vicuna-7b",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1113.8081731393095,
      "unit": "Arena rating",
      "confidenceInterval": [
        1104.6551911586498,
        1122.9611551199691
      ],
      "voteCount": 6923,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 21.808662554696085
      }
    },
    {
      "id": "ce725949f96350e25765c16b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1118.752227227366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1084.972187635343,
        1152.5322668193887
      ],
      "voteCount": 287,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 297.04628582545786
      }
    },
    {
      "id": "16e253ce7502ac70feaf7185",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1150.07109313506,
      "unit": "Arena rating",
      "confidenceInterval": [
        1128.0599423903832,
        1172.0822438797368
      ],
      "voteCount": 735,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 126.12155426342375
      }
    },
    {
      "id": "ceb65c6a36be6b74264c206b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1140.2975515244511,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.6095437804067,
        1157.9855592684958
      ],
      "voteCount": 1375,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 81.44448048432919
      }
    },
    {
      "id": "26cc5ff4ff3ade7449d1c53a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1171.3868203556026,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.0261952993517,
        1181.7474454118535
      ],
      "voteCount": 5508,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.943173821870744
      }
    },
    {
      "id": "4455c4d7c930569a4055fe53",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1006.2923760046414,
      "unit": "Arena rating",
      "confidenceInterval": [
        992.8492139965681,
        1019.7355380127146
      ],
      "voteCount": 4797,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.04426448664931
      }
    },
    {
      "id": "0e6e5b59fdef8a1094a8f1fe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1128.052681873382,
      "unit": "Arena rating",
      "confidenceInterval": [
        1109.699268678433,
        1146.4060950683306
      ],
      "voteCount": 1066,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 87.68746240097747
      }
    },
    {
      "id": "10ce0479490331a98b152f22",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1113.0815807446825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.4993877575969,
        1129.6637737317678
      ],
      "voteCount": 1278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.57934969383926
      }
    },
    {
      "id": "4f9d1b9e2d93588426c40695",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1108.2924343356622,
      "unit": "Arena rating",
      "confidenceInterval": [
        1083.7890493882237,
        1132.7958192831002
      ],
      "voteCount": 634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 156.29892233853283
      }
    },
    {
      "id": "005f1d628bc0587f0100afa2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1139.476969063992,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.1995234242468,
        1157.7544147037374
      ],
      "voteCount": 1219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.96306135424888
      }
    },
    {
      "id": "83a7dbfe8009881a9ae2d23a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1195.301016211904,
      "unit": "Arena rating",
      "confidenceInterval": [
        1163.1239440487343,
        1227.4780883750736
      ],
      "voteCount": 365,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 269.52364227263666
      }
    },
    {
      "id": "5baba3c353558d55b58151f3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1171.0128899905453,
      "unit": "Arena rating",
      "confidenceInterval": [
        1152.9861665070478,
        1189.0396134740427
      ],
      "voteCount": 1246,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.59358142794305
      }
    },
    {
      "id": "0b5c4b0d215cc8460324c182",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1069.7527715668768,
      "unit": "Arena rating",
      "confidenceInterval": [
        1046.6285753026555,
        1092.8769678310982
      ],
      "voteCount": 567,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 139.1993192756921
      }
    },
    {
      "id": "31c6f6a193b01dd54a4ffe95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1172.2647140030665,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.0228070235396,
        1207.5066209825936
      ],
      "voteCount": 323,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 323.3125917849127
      }
    },
    {
      "id": "dd84684ba481db43bbc9491d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1156.6784727628271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.7444242673128,
        1172.6125212583413
      ],
      "voteCount": 1618,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.09309465707658
      }
    },
    {
      "id": "2ddff04b32ef0db894ffe388",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1151.7306763937802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1136.421870092457,
        1167.0394826951033
      ],
      "voteCount": 1814,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.00795591219741
      }
    },
    {
      "id": "ac5e52673361943905e24e95",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1121.6277343157444,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.606962694898,
        1135.648505936591
      ],
      "voteCount": 2003,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 51.173797773111005
      }
    },
    {
      "id": "6b141c9ff631020a659aa0b8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1147.6958859614365,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.2577786404408,
        1188.1339932824321
      ],
      "voteCount": 203,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 425.6821692048989
      }
    },
    {
      "id": "f88860b1b92ddcb6705601b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1063.9765103270884,
      "unit": "Arena rating",
      "confidenceInterval": [
        1043.4468130345574,
        1084.5062076196193
      ],
      "voteCount": 669,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.71573316170453
      }
    },
    {
      "id": "1f6357b725fcc9b37a8aaf4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1109.1006894167272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.0986725087776,
        1129.1027063246765
      ],
      "voteCount": 983,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 104.14811118907402
      }
    },
    {
      "id": "faf64582ac8fff9ff7f0dd73",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-13b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1148.3233517860663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.0838687771088,
        1157.5628347950237
      ],
      "voteCount": 7044,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 22.222819573889673
      }
    },
    {
      "id": "208bd09130ddd55d16179c8f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1150.9835794254936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1118.0659529544932,
        1183.901205896494
      ],
      "voteCount": 334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 282.0725622898924
      }
    },
    {
      "id": "44d981e4a2540782f5fb39e0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1191.744451928928,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.9218121650715,
        1211.5670916927845
      ],
      "voteCount": 988,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 102.28849651878427
      }
    },
    {
      "id": "baa8927a671d2b2aa5b5161e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1197.5467607487576,
      "unit": "Arena rating",
      "confidenceInterval": [
        1180.6752104774162,
        1214.4183110200993
      ],
      "voteCount": 1779,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.09924766731486
      }
    },
    {
      "id": "5abf5aa126dc4a87b0caa24b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1212.0645359484936,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.7665961634857,
        1222.3624757335015
      ],
      "voteCount": 6411,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 27.6060654989616
      }
    },
    {
      "id": "62dfef6681f97797578c4300",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1057.8511718923294,
      "unit": "Arena rating",
      "confidenceInterval": [
        1044.5456238258532,
        1071.1567199588053
      ],
      "voteCount": 5678,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.086035959983214
      }
    },
    {
      "id": "85648048713d7bd7dcc8253c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1148.78782530925,
      "unit": "Arena rating",
      "confidenceInterval": [
        1105.4759194424496,
        1192.0997311760502
      ],
      "voteCount": 193,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 488.3356238804134
      }
    },
    {
      "id": "fb23e32f4935d062215b236a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1185.8278831997418,
      "unit": "Arena rating",
      "confidenceInterval": [
        1169.378318165781,
        1202.2774482337027
      ],
      "voteCount": 1475,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 70.43891459901533
      }
    },
    {
      "id": "0612a3452bbd695e4b045028",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1171.1080875515795,
      "unit": "Arena rating",
      "confidenceInterval": [
        1155.8076215942726,
        1186.4085535088861
      ],
      "voteCount": 1752,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 60.941498903899465
      }
    },
    {
      "id": "996a6f9cce4d62457e83e983",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1172.6735112120523,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.715593342915,
        1196.6314290811897
      ],
      "voteCount": 682,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 149.41767058187838
      }
    },
    {
      "id": "bf308fd0c45d429daafdbeca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1174.6334849429618,
      "unit": "Arena rating",
      "confidenceInterval": [
        1157.099970849236,
        1192.1669990366877
      ],
      "voteCount": 1539,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.02796094514267
      }
    },
    {
      "id": "26ebd017f0e0c55fdace195c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1219.877951116739,
      "unit": "Arena rating",
      "confidenceInterval": [
        1190.8241446553131,
        1248.9317575781647
      ],
      "voteCount": 434,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 219.74039272545548
      }
    },
    {
      "id": "a48801401e1e5a3ac9c37140",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1200.7291225908543,
      "unit": "Arena rating",
      "confidenceInterval": [
        1182.8159140561393,
        1218.6423311255692
      ],
      "voteCount": 1334,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 83.53155792782934
      }
    },
    {
      "id": "af5c95a63bf08f6589bcb3c0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1155.4642288099785,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.8384383969237,
        1176.0900192230329
      ],
      "voteCount": 764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.74522727446146
      }
    },
    {
      "id": "b551a29325d9fdaa6f1e5542",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1199.3817288067478,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.8644214937067,
        1229.899036119789
      ],
      "voteCount": 385,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 242.43551450339717
      }
    },
    {
      "id": "aaa51dccc48f006daccdcef6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1186.6758032471366,
      "unit": "Arena rating",
      "confidenceInterval": [
        1171.293390717442,
        1202.0582157768313
      ],
      "voteCount": 1935,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 61.59603064310681
      }
    },
    {
      "id": "ce752c86aadf59e90aa2b1ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1193.575547178749,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.774192325959,
        1208.3769020315394
      ],
      "voteCount": 2313,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 57.030444865898886
      }
    },
    {
      "id": "e70693419e5765fc85a183a2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1161.2338054748825,
      "unit": "Arena rating",
      "confidenceInterval": [
        1147.7427645833734,
        1174.7248463663914
      ],
      "voteCount": 2680,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 47.37996496432048
      }
    },
    {
      "id": "7c5159e61c229e2f83259317",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1179.858110359899,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.2493415906624,
        1211.4668791291356
      ],
      "voteCount": 355,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 260.0871985727884
      }
    },
    {
      "id": "59056d29ae2b904dc9434c6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1157.3834890614175,
      "unit": "Arena rating",
      "confidenceInterval": [
        1138.2234323221605,
        1176.5435458006743
      ],
      "voteCount": 903,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 95.56467774011269
      }
    },
    {
      "id": "ce6c73e47165ca93979860ee",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1164.5160679648502,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.085900639774,
        1183.9462352899263
      ],
      "voteCount": 1178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 98.27813336086587
      }
    },
    {
      "id": "a2ae12863fff4d110e053a9d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1183.7451670424398,
      "unit": "Arena rating",
      "confidenceInterval": [
        1174.3012794738745,
        1193.1890546110053
      ],
      "voteCount": 8214,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 23.21696432804345
      }
    },
    {
      "id": "a6ca41ca1b64e291a9ba7311",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "wizardlm-70b",
      "organization": "microsoft",
      "license": "Llama 2 Community",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1213.7886684165255,
      "unit": "Arena rating",
      "confidenceInterval": [
        1168.0695245597412,
        1259.5078122733098
      ],
      "voteCount": 172,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 544.1266489014813
      }
    },
    {
      "id": "ca6e9f0c34a28793800c5186",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1272.5346809319092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1259.7231534730927,
        1285.3462083907257
      ],
      "voteCount": 2868,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.72731883622045
      }
    },
    {
      "id": "1dd26cca7cd953161afc047e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1247.2815590113983,
      "unit": "Arena rating",
      "confidenceInterval": [
        1236.8004507094258,
        1257.7626673133707
      ],
      "voteCount": 3841,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.596852488926615
      }
    },
    {
      "id": "b01b2e34a73048a89f5125c5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1159.2599591974908,
      "unit": "Arena rating",
      "confidenceInterval": [
        1148.089804677987,
        1170.4301137169946
      ],
      "voteCount": 3602,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 32.48046063059043
      }
    },
    {
      "id": "b03bbbd220b724dc0bab9c6b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1249.0976452654377,
      "unit": "Arena rating",
      "confidenceInterval": [
        1242.2768879969258,
        1255.9184025339498
      ],
      "voteCount": 12503,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.110693329663837
      }
    },
    {
      "id": "878bee663f0e64072711d842",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1098.0969666561496,
      "unit": "Arena rating",
      "confidenceInterval": [
        1089.7742110805123,
        1106.419722231787
      ],
      "voteCount": 15321,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.03175918446697
      }
    },
    {
      "id": "3607e8e9a7745f287a5583fa",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1217.1137879961307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1198.5480266010104,
        1235.679549391251
      ],
      "voteCount": 1049,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 89.72828091340975
      }
    },
    {
      "id": "7169566dc5d4f8be49cc9d39",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1210.3711455045202,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.8066131830549,
        1242.9356778259853
      ],
      "voteCount": 399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 276.0536595116064
      }
    },
    {
      "id": "1931fbfefabb2c642163cef3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1154.654319136624,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.975144652321,
        1175.3334936209267
      ],
      "voteCount": 871,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 111.31923503867509
      }
    },
    {
      "id": "7de6ccaaeccbed80c60cab60",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1240.4666352241875,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.3494720375793,
        1250.5837984107957
      ],
      "voteCount": 3931,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.645343793107543
      }
    },
    {
      "id": "f9b48bd3bc50143c64919fb1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1224.5436968867211,
      "unit": "Arena rating",
      "confidenceInterval": [
        1216.195149573634,
        1232.8922441998086
      ],
      "voteCount": 6679,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 18.143691105939077
      }
    },
    {
      "id": "18e3f3a81c15c3d6382a3a16",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1196.000607534645,
      "unit": "Arena rating",
      "confidenceInterval": [
        1183.7224844215204,
        1208.2787306477694
      ],
      "voteCount": 2763,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 39.24350467299893
      }
    },
    {
      "id": "85835ad16e31211dc27f65b9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1152.1580588951542,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.4538603430196,
        1162.8622574472888
      ],
      "voteCount": 3893,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.8271755579611
      }
    },
    {
      "id": "2d6a746eaaf507b7899921e5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1251.938396129924,
      "unit": "Arena rating",
      "confidenceInterval": [
        1235.414254699441,
        1268.4625375604073
      ],
      "voteCount": 1510,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 71.07905167268493
      }
    },
    {
      "id": "9b00b35fa1219693649f6439",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1230.039845696557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1219.2626921553426,
        1240.8169992377716
      ],
      "voteCount": 4292,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.235138230617206
      }
    },
    {
      "id": "5032ef5a9a8fdb39a939e7ef",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1222.0886525427663,
      "unit": "Arena rating",
      "confidenceInterval": [
        1210.5040902994258,
        1233.673214786107
      ],
      "voteCount": 2568,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 34.93518703021905
      }
    },
    {
      "id": "b341c82bbe7c0e59f8a7c558",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1225.5094642209206,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.9343810022976,
        1243.0845474395433
      ],
      "voteCount": 1330,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.40787746507846
      }
    },
    {
      "id": "52add20f74c520df6ab6f6c4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1237.976803451746,
      "unit": "Arena rating",
      "confidenceInterval": [
        1229.2583603867288,
        1246.6952465167633
      ],
      "voteCount": 6462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 19.787079082683977
      }
    },
    {
      "id": "748ff7674d779b3ffedba248",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1174.5318977685222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.6295262257054,
        1183.434269311339
      ],
      "voteCount": 6540,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.63076106905544
      }
    },
    {
      "id": "2e3c0890a2973e5348fa2eb7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1186.6309165013906,
      "unit": "Arena rating",
      "confidenceInterval": [
        1178.9256690243817,
        1194.3361639783996
      ],
      "voteCount": 8996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.455284425312211
      }
    },
    {
      "id": "9409b05e41d5f332252ae37c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1076.2851494995482,
      "unit": "Arena rating",
      "confidenceInterval": [
        1048.6970764325192,
        1103.873222566577
      ],
      "voteCount": 506,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 198.12831819298228
      }
    },
    {
      "id": "282f5fc7348065a83d8a8202",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1078.116713362613,
      "unit": "Arena rating",
      "confidenceInterval": [
        1053.2400438784841,
        1102.993382846742
      ],
      "voteCount": 804,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 161.09731055525603
      }
    },
    {
      "id": "fb0a42b8ff5e3e66f38aeae3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1202.4289895611162,
      "unit": "Arena rating",
      "confidenceInterval": [
        1189.0134691498104,
        1215.8445099724217
      ],
      "voteCount": 2098,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.85100018165474
      }
    },
    {
      "id": "65adf622da7798f317768a32",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1212.78127365524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.7490137016994,
        1223.8135336087807
      ],
      "voteCount": 2985,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.683473743577245
      }
    },
    {
      "id": "0182b68300e2f30f4acdbee4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1188.4719933550102,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.1924415132694,
        1199.751545196751
      ],
      "voteCount": 3391,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.119784875769696
      }
    },
    {
      "id": "2bb7b7b5590a29cbe9aa24a7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1212.5409781673116,
      "unit": "Arena rating",
      "confidenceInterval": [
        1207.5034041194617,
        1217.5785522151616
      ],
      "voteCount": 24146,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.606123733739947
      }
    },
    {
      "id": "4c27144dcd265ec02b7913b0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1137.1815133550954,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.1755154583013,
        1149.1875112518892
      ],
      "voteCount": 3231,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.52324109822793
      }
    },
    {
      "id": "0d989d0001e1b075a148bcec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-1.5-34b-chat",
      "license": "Apache-2.0",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1164.9380953305608,
      "unit": "Arena rating",
      "confidenceInterval": [
        1134.025767810731,
        1195.850422850391
      ],
      "voteCount": 458,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 248.75237176708228
      }
    },
    {
      "id": "65c63c84afa58c2e8eaaa852",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1249.433469983066,
      "unit": "Arena rating",
      "confidenceInterval": [
        1231.1865480435076,
        1267.680391922625
      ],
      "voteCount": 1219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.67284378390993
      }
    },
    {
      "id": "e7334d0b56e9570678208b8d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1204.3044609061878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1191.2883184157622,
        1217.3206033966135
      ],
      "voteCount": 2345,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 44.10302784410749
      }
    },
    {
      "id": "433a3de4ca807a6e7f2d3091",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1153.5348396242505,
      "unit": "Arena rating",
      "confidenceInterval": [
        1139.7877515958535,
        1167.2819276526477
      ],
      "voteCount": 2379,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 49.195484861751694
      }
    },
    {
      "id": "f3f3806905be0664b4eaaf3d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1209.2921981366094,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.3604379151902,
        1217.223958358028
      ],
      "voteCount": 10572,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.377325163859364
      }
    },
    {
      "id": "f10cfc73b001d83ddd2ee3a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1052.2973898704558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1042.1491397691332,
        1062.4456399717785
      ],
      "voteCount": 10427,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.809341171171276
      }
    },
    {
      "id": "17f6ae43bc5b1498c3fe54d7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1151.335431961755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1126.2568382011614,
        1176.4140257223485
      ],
      "voteCount": 559,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 163.7231828754151
      }
    },
    {
      "id": "e26a4c081efdbf2df0758b0f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1157.4899257292334,
      "unit": "Arena rating",
      "confidenceInterval": [
        1116.362202018464,
        1198.6176494400029
      ],
      "voteCount": 234,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 440.3248184042101
      }
    },
    {
      "id": "ca1f4a801c29be8bb3f61b13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1102.2486032510956,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.4822971141466,
        1134.0149093880445
      ],
      "voteCount": 381,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 262.6861962310523
      }
    },
    {
      "id": "10e428e92fc6940051eaeb10",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1196.5481750813756,
      "unit": "Arena rating",
      "confidenceInterval": [
        1184.497352392641,
        1208.5989977701106
      ],
      "voteCount": 2844,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 37.80395267886414
      }
    },
    {
      "id": "dff58b29a3db4654ba6db68c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1182.7331041493558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1172.137342770548,
        1193.3288655281635
      ],
      "voteCount": 3838,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.225917662277624
      }
    },
    {
      "id": "ecc381bcecadf6f6bbbab642",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1170.5785780381152,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.9434577431684,
        1187.2136983330618
      ],
      "voteCount": 1433,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.03701514034219
      }
    },
    {
      "id": "faa29026dccb9a3f4eea397b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1158.7516847741106,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.3955830791028,
        1172.1077864691183
      ],
      "voteCount": 2338,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 46.436903482191276
      }
    },
    {
      "id": "528f33967a3c8b9a1c050c07",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1221.5737082523337,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.7716832201415,
        1243.3757332845257
      ],
      "voteCount": 857,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 123.73640267694927
      }
    },
    {
      "id": "80e55ee3511eb6c34bbfee88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1213.0630291849295,
      "unit": "Arena rating",
      "confidenceInterval": [
        1199.8531178821024,
        1226.2729404877564
      ],
      "voteCount": 2658,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.425908430543984
      }
    },
    {
      "id": "489d1359088662ece66e99a5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1158.9262588021788,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.7818418110749,
        1173.0706757932826
      ],
      "voteCount": 1719,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.0803531565845
      }
    },
    {
      "id": "81eed292d3ea42337db4055a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1199.569009681798,
      "unit": "Arena rating",
      "confidenceInterval": [
        1177.6490837814333,
        1221.4889355821624
      ],
      "voteCount": 824,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 125.07830329693684
      }
    },
    {
      "id": "23a469d4cee697ebe67394cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1204.4745353810713,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.7258442963532,
        1215.2232264657896
      ],
      "voteCount": 4134,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.07564715058552
      }
    },
    {
      "id": "5a47b432370fd177b43016ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1163.0630657177926,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.663920631554,
        1174.4622108040317
      ],
      "voteCount": 3702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 33.8258236681145
      }
    },
    {
      "id": "083646a43911b756d9c80d14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1150.2797073036757,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.5342933362367,
        1160.0251212711146
      ],
      "voteCount": 5099,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.72318403756662
      }
    },
    {
      "id": "56ce9d31c7c8d3cc4e0295f8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1050.578073863792,
      "unit": "Arena rating",
      "confidenceInterval": [
        1006.7868565388242,
        1094.36929118876
      ],
      "voteCount": 197,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 499.2037671917721
      }
    },
    {
      "id": "32d828a95337c5756ce48c13",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1039.7933232850028,
      "unit": "Arena rating",
      "confidenceInterval": [
        998.1491370683423,
        1081.4375095016633
      ],
      "voteCount": 227,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 451.4530355773882
      }
    },
    {
      "id": "4e274358c6e77e0d4a401563",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1169.3444760936109,
      "unit": "Arena rating",
      "confidenceInterval": [
        1151.2991845670267,
        1187.3897676201948
      ],
      "voteCount": 1106,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.76793881668243
      }
    },
    {
      "id": "ba753ba2b4139cb3019d5e91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1150.5173234782644,
      "unit": "Arena rating",
      "confidenceInterval": [
        1137.3067952706838,
        1163.727851685845
      ],
      "voteCount": 2043,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.43015132249879
      }
    },
    {
      "id": "313cbd92b9244dddb974f3ce",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1160.2654538489035,
      "unit": "Arena rating",
      "confidenceInterval": [
        1145.4922264960123,
        1175.0386812017946
      ],
      "voteCount": 1947,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 56.813897169610954
      }
    },
    {
      "id": "526b08ff97bf4fa36cc6c9ea",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1182.98232329307,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.1549446518864,
        1189.8097019342536
      ],
      "voteCount": 15483,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.134218088967422
      }
    },
    {
      "id": "b0b8458dc74b8d61e84d7c81",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1110.0236949174164,
      "unit": "Arena rating",
      "confidenceInterval": [
        1088.8578952698908,
        1131.189494564942
      ],
      "voteCount": 789,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 116.62003827968731
      }
    },
    {
      "id": "e4c346b0d807108b7f19f4fc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-34b-chat",
      "license": "Yi License",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1127.2733330299507,
      "unit": "Arena rating",
      "confidenceInterval": [
        1085.028787149913,
        1169.5178789099887
      ],
      "voteCount": 218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 464.5635264907425
      }
    },
    {
      "id": "77ad85532376002ea36c0e05",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1362.3021897781932,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.078488028682,
        1374.525891527704
      ],
      "voteCount": 2736,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 38.89639104188051
      }
    },
    {
      "id": "24eb314f44a19b0207296c29",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1369.0601555549,
      "unit": "Arena rating",
      "confidenceInterval": [
        1359.3912201994708,
        1378.7290909103292
      ],
      "voteCount": 4316,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.33666876860535
      }
    },
    {
      "id": "553d3a79d7498fc9b38df72e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1297.5056211501246,
      "unit": "Arena rating",
      "confidenceInterval": [
        1287.0668504309647,
        1307.9443918692841
      ],
      "voteCount": 3781,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.36628979078735
      }
    },
    {
      "id": "b9e9fa270139e9bcc98bb2f4",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1354.3552100270495,
      "unit": "Arena rating",
      "confidenceInterval": [
        1347.8147155148029,
        1360.8957045392963
      ],
      "voteCount": 13650,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 11.13589145724561
      }
    },
    {
      "id": "4abbad4503a67aba3e0a8446",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1280.8437328895172,
      "unit": "Arena rating",
      "confidenceInterval": [
        1273.1621194677386,
        1288.525346311296
      ],
      "voteCount": 17462,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 15.360618847136136
      }
    },
    {
      "id": "bb01fb39202f199a59d92b0b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1330.2629284928485,
      "unit": "Arena rating",
      "confidenceInterval": [
        1315.646192643541,
        1344.8796643421556
      ],
      "voteCount": 1533,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 55.616622970806624
      }
    },
    {
      "id": "cbb6e6a0e6ee4314ccec570b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1342.7316760655315,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.709103301153,
        1379.75424882991
      ],
      "voteCount": 270,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 356.8099927844708
      }
    },
    {
      "id": "861090820ee24cdf16fb3f1e",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1292.0466854071215,
      "unit": "Arena rating",
      "confidenceInterval": [
        1270.5973309641095,
        1313.496039850134
      ],
      "voteCount": 700,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 119.76564828536576
      }
    },
    {
      "id": "0cfe1adffae25caa0482a72b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1360.7384051706272,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.9276455614377,
        1370.5491647798171
      ],
      "voteCount": 3939,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.055846906596706
      }
    },
    {
      "id": "242a3d710ab9296f3ad0d4ab",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1341.0717090060098,
      "unit": "Arena rating",
      "confidenceInterval": [
        1333.0866306581042,
        1349.0567873539153
      ],
      "voteCount": 6961,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 16.59824540580864
      }
    },
    {
      "id": "19332d90d7702511104cdc54",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1318.988895869208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1307.9147917441846,
        1330.0629999942312
      ],
      "voteCount": 3420,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 31.924273536713024
      }
    },
    {
      "id": "f332505c0e08e2456b73f1f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1294.7208803669023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1284.5601828232302,
        1304.8815779105744
      ],
      "voteCount": 3980,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.875148060374446
      }
    },
    {
      "id": "118ea2a23181fa56b21c12e3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1365.694936671388,
      "unit": "Arena rating",
      "confidenceInterval": [
        1350.7327869029232,
        1380.6570864398523
      ],
      "voteCount": 1697,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 58.27627891986945
      }
    },
    {
      "id": "97be55c4e0b7238e6557e20c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1353.7010050503927,
      "unit": "Arena rating",
      "confidenceInterval": [
        1344.074677518787,
        1363.3273325819982
      ],
      "voteCount": 4822,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.122653937236873
      }
    },
    {
      "id": "fd62388dbb9a1839f3e6389f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1316.9102002985437,
      "unit": "Arena rating",
      "confidenceInterval": [
        1306.4888053787915,
        1327.3315952182961
      ],
      "voteCount": 3206,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 28.271934476656252
      }
    },
    {
      "id": "047d25e6041e32e756beb453",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1355.1641579154823,
      "unit": "Arena rating",
      "confidenceInterval": [
        1338.9756695164303,
        1371.3526463145342
      ],
      "voteCount": 1451,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 68.22073823477443
      }
    },
    {
      "id": "09f785f68bdbe1b46be79e46",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1360.0427734882135,
      "unit": "Arena rating",
      "confidenceInterval": [
        1351.8045869443422,
        1368.2809600320847
      ],
      "voteCount": 7070,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.66717299324337
      }
    },
    {
      "id": "e5765b2dd822d48b9d71362c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1302.6689562285014,
      "unit": "Arena rating",
      "confidenceInterval": [
        1294.4276240225904,
        1310.9102884344125
      ],
      "voteCount": 7632,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 17.680667605311758
      }
    },
    {
      "id": "d29c99dd52eb5e491fd8db88",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1308.4546771913951,
      "unit": "Arena rating",
      "confidenceInterval": [
        1301.5304683581949,
        1315.3788860245954
      ],
      "voteCount": 10932,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 12.480849126245113
      }
    },
    {
      "id": "ee6eaf313233e9d917e56d28",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "japanese",
      "score": 1254.3541857394011,
      "unit": "Arena rating",
      "confidenceInterval": [
        1230.1785004427225,
        1278.52987103608
      ],
      "voteCount": 565,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 152.14630348645622
      }
    },
    {
      "id": "240fcf864c498899e2fe91ca",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "korean",
      "score": 1224.4991764999818,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.5058944357183,
        1255.492458564245
      ],
      "voteCount": 425,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 250.0569648020899
      }
    },
    {
      "id": "6dea95774bce5ef8b0e9461a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1325.1664804458242,
      "unit": "Arena rating",
      "confidenceInterval": [
        1314.5436328022151,
        1335.7893280894332
      ],
      "voteCount": 3634,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 29.375530840374783
      }
    },
    {
      "id": "331c37ebae4949c533a77dc2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1305.7272510899445,
      "unit": "Arena rating",
      "confidenceInterval": [
        1295.9512945000597,
        1315.5032076798293
      ],
      "voteCount": 3921,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.878394304912433
      }
    },
    {
      "id": "9ba074b4d52b69eeacbae7ec",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1330.4925402844235,
      "unit": "Arena rating",
      "confidenceInterval": [
        1320.6583098251733,
        1340.326770743674
      ],
      "voteCount": 4748,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 25.175875426453228
      }
    },
    {
      "id": "14ada6ee1730d7ee8725f155",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1328.3024760204353,
      "unit": "Arena rating",
      "confidenceInterval": [
        1323.3732239427025,
        1333.2317280981679
      ],
      "voteCount": 27332,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 6.3250778363001645
      }
    },
    {
      "id": "18cfff205894ab714d0e6ec8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1285.4922842551023,
      "unit": "Arena rating",
      "confidenceInterval": [
        1275.4851195533001,
        1295.4994489569042
      ],
      "voteCount": 4189,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 26.069092509729483
      }
    },
    {
      "id": "a21fc4f6df9a54fb36336b8c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "yi-lightning",
      "license": "Proprietary",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1337.4656158222583,
      "unit": "Arena rating",
      "confidenceInterval": [
        1305.317064528232,
        1369.614167116285
      ],
      "voteCount": 341,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 269.04605738241395
      }
    },
    {
      "id": "9cc1f92efffb8d9eab671c57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1165.1655093496222,
      "unit": "Arena rating",
      "confidenceInterval": [
        1125.5788237670668,
        1204.7521949321779
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 407.9454573273159
      }
    },
    {
      "id": "2188fed3349eb0fe78e3161f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1100.539471786861,
      "unit": "Arena rating",
      "confidenceInterval": [
        1070.8005349543002,
        1130.2784086194215
      ],
      "voteCount": 399,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 230.22617323572655
      }
    },
    {
      "id": "2a8f3903f0a3da17558613cb",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1157.6883964951878,
      "unit": "Arena rating",
      "confidenceInterval": [
        1140.3807575971603,
        1174.9960353932154
      ],
      "voteCount": 1415,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 77.97932457607074
      }
    },
    {
      "id": "0635f57c7d042893ef4253b7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 970.6742606400485,
      "unit": "Arena rating",
      "confidenceInterval": [
        948.1644338619154,
        993.1840874181817
      ],
      "voteCount": 1218,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 131.90101084827035
      }
    },
    {
      "id": "308e43c1f6ac9b908d74f491",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1135.9939759975346,
      "unit": "Arena rating",
      "confidenceInterval": [
        1103.1295274173947,
        1168.8584245776747
      ],
      "voteCount": 278,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 281.1619311544531
      }
    },
    {
      "id": "acfc776708820f1ecf1c7bfe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1121.1750158405976,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.7839723314487,
        1150.5660593497466
      ],
      "voteCount": 333,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 224.8711957819712
      }
    },
    {
      "id": "f201161141e8d4ef07c85a33",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1098.8817561025635,
      "unit": "Arena rating",
      "confidenceInterval": [
        1067.1559107599044,
        1130.6076014452226
      ],
      "voteCount": 329,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 262.01745474508436
      }
    },
    {
      "id": "8b8750b2ee1522ded5215585",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1141.5885847735137,
      "unit": "Arena rating",
      "confidenceInterval": [
        1107.9367798296498,
        1175.2403897173776
      ],
      "voteCount": 294,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 294.7952923195035
      }
    },
    {
      "id": "03724f7ad158a688bb517a4c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1157.869104831929,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.300450425239,
        1186.437759238619
      ],
      "voteCount": 406,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 212.4630388362225
      }
    },
    {
      "id": "22ae969d05c1a371dcdc4e78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1122.131235730118,
      "unit": "Arena rating",
      "confidenceInterval": [
        1096.8446919352732,
        1147.4177795249632
      ],
      "voteCount": 569,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 166.449603375697
      }
    },
    {
      "id": "94e67cf0c0a6c4ce0eb05669",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1097.0100130002802,
      "unit": "Arena rating",
      "confidenceInterval": [
        1072.6618352537325,
        1121.358190746828
      ],
      "voteCount": 534,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 154.32516323847148
      }
    },
    {
      "id": "f46ccce0af4a3cff96242922",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1073.5239334323776,
      "unit": "Arena rating",
      "confidenceInterval": [
        1039.3603548022502,
        1107.6875120625052
      ],
      "voteCount": 283,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 303.8299144401631
      }
    },
    {
      "id": "cda4fc3f52c13927545fb97d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-alpha",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1125.8937597730314,
      "unit": "Arena rating",
      "confidenceInterval": [
        1110.267888517731,
        1141.5196310283316
      ],
      "voteCount": 1785,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.56123126242427
      }
    },
    {
      "id": "53d873538eeaa4d0080a5fa9",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1045.6036082287005,
      "unit": "Arena rating",
      "confidenceInterval": [
        1014.1562410707681,
        1077.050975386633
      ],
      "voteCount": 373,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 257.4378503911972
      }
    },
    {
      "id": "ba4da0c3120e0ab3fe1ac71b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1151.043360401271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1132.8080164310982,
        1169.2787043714436
      ],
      "voteCount": 1250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.56288801513927
      }
    },
    {
      "id": "2eea2554c0afd4e460be7e43",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1135.6888851787362,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.6473383096304,
        1151.7304320478424
      ],
      "voteCount": 1993,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 66.98789131031884
      }
    },
    {
      "id": "3ce08e980dbafbec12ccd1e8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1166.5037262955516,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.8475857932438,
        1176.1598667978592
      ],
      "voteCount": 8764,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 24.272302204052092
      }
    },
    {
      "id": "3b8a8663b55029173c27693d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 973.1694209774942,
      "unit": "Arena rating",
      "confidenceInterval": [
        960.5307992868504,
        985.808042668138
      ],
      "voteCount": 7522,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 41.58179631621017
      }
    },
    {
      "id": "c7dfda0b246d93927c07da94",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1108.1627310704853,
      "unit": "Arena rating",
      "confidenceInterval": [
        1069.810672047748,
        1146.5147900932227
      ],
      "voteCount": 201,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 382.8963162014958
      }
    },
    {
      "id": "632b1b3921d98f9cb8eb6d2d",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "french",
      "score": 1103.0148001762304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1052.7722847220598,
        1153.2573156304006
      ],
      "voteCount": 153,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 657.1228475921627
      }
    },
    {
      "id": "3e6f3966004bc7d07d595a14",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "german",
      "score": 1055.5592578427386,
      "unit": "Arena rating",
      "confidenceInterval": [
        1008.3402271395212,
        1102.7782885459558
      ],
      "voteCount": 152,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 580.4140990761678
      }
    },
    {
      "id": "dfbb65ec69e1321501f49cf0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1134.5500934447755,
      "unit": "Arena rating",
      "confidenceInterval": [
        1119.014543882172,
        1150.0856430073788
      ],
      "voteCount": 1847,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 62.82855328604039
      }
    },
    {
      "id": "994819773ba123dbdf8a2b30",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1115.1465820089682,
      "unit": "Arena rating",
      "confidenceInterval": [
        1100.7592017823001,
        1129.533962235636
      ],
      "voteCount": 2220,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 53.884922225800345
      }
    },
    {
      "id": "ae9a3dfd7747c0d6c264f9f1",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1095.0428201613308,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.5061258527583,
        1115.5795144699036
      ],
      "voteCount": 997,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 109.79053344311382
      }
    },
    {
      "id": "ec27e74b4e2766c428d9233b",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1114.7795846894824,
      "unit": "Arena rating",
      "confidenceInterval": [
        1098.891781905277,
        1130.667387473688
      ],
      "voteCount": 1869,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.7100047383028
      }
    },
    {
      "id": "3bb9284dcba6e26358d52ee8",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1187.061870572952,
      "unit": "Arena rating",
      "confidenceInterval": [
        1161.040890566639,
        1213.0828505792651
      ],
      "voteCount": 621,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 176.2589245630893
      }
    },
    {
      "id": "22409d46c23411f8aebd4866",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1157.663935727327,
      "unit": "Arena rating",
      "confidenceInterval": [
        1141.806699751533,
        1173.5211717031211
      ],
      "voteCount": 1996,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.4574068157213
      }
    },
    {
      "id": "cd83fdc8b025ea0822793da7",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1094.0148922740557,
      "unit": "Arena rating",
      "confidenceInterval": [
        1075.8017869623598,
        1112.2279975857518
      ],
      "voteCount": 1113,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 86.35188364065097
      }
    },
    {
      "id": "b61b372996863c3429cdf04f",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1148.2653551069375,
      "unit": "Arena rating",
      "confidenceInterval": [
        1122.0730292664898,
        1174.4576809473851
      ],
      "voteCount": 580,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 178.58786595250342
      }
    },
    {
      "id": "24ed4551c1393510e0cb4dc3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1143.6482752139493,
      "unit": "Arena rating",
      "confidenceInterval": [
        1129.4183725891708,
        1157.8781778387279
      ],
      "voteCount": 2598,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 52.71177908242962
      }
    },
    {
      "id": "560eae067f075150e2d1dd78",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1120.2787239435524,
      "unit": "Arena rating",
      "confidenceInterval": [
        1106.3029873273322,
        1134.2544605597725
      ],
      "voteCount": 2691,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 50.84558317109878
      }
    },
    {
      "id": "8f15a409af7adb1abbfb764c",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1087.2451557548918,
      "unit": "Arena rating",
      "confidenceInterval": [
        1074.4406080005983,
        1100.049703509185
      ],
      "voteCount": 3094,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 42.68077593562522
      }
    },
    {
      "id": "2e664d230c0d7be2d28bdaf3",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1103.742533140508,
      "unit": "Arena rating",
      "confidenceInterval": [
        1076.0006627231946,
        1131.4844035578212
      ],
      "voteCount": 461,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 200.34351796381802
      }
    },
    {
      "id": "643305be5e14b22a8cb39aed",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1082.1494857347748,
      "unit": "Arena rating",
      "confidenceInterval": [
        1065.1362274873677,
        1099.162743982182
      ],
      "voteCount": 1250,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 75.34922791146002
      }
    },
    {
      "id": "d79b41dabb17d0a9149d97d0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1088.6204859743975,
      "unit": "Arena rating",
      "confidenceInterval": [
        1071.0178082789173,
        1106.2231636698775
      ],
      "voteCount": 1574,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 80.66057102623488
      }
    },
    {
      "id": "48aca491284b9b8d64b2dd02",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1129.9675850811848,
      "unit": "Arena rating",
      "confidenceInterval": [
        1121.1324089193517,
        1138.8027612430178
      ],
      "voteCount": 11118,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 20.320493191312988
      }
    },
    {
      "id": "a1ed5b839b80f6a3f571e7f5",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1130.2125672649227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1091.7958104775166,
        1168.6293240523291
      ],
      "voteCount": 202,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 384.18925490291923
      }
    },
    {
      "id": "13216c99096f9ff076efcb99",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-7b-beta",
      "license": "MIT",
      "benchmark": "LMArena Arena rating",
      "category": "spanish",
      "score": 1135.9717133109248,
      "unit": "Arena rating",
      "confidenceInterval": [
        1080.362494162771,
        1191.5809324590787
      ],
      "voteCount": 127,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 805.0028384030983
      }
    },
    {
      "id": "09f1c9d588f9b740ae758866",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "chinese",
      "score": 1185.2508610990208,
      "unit": "Arena rating",
      "confidenceInterval": [
        1162.198079062724,
        1208.303643135318
      ],
      "voteCount": 657,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 138.3408711165073
      }
    },
    {
      "id": "6551692e33bc5c2240e7805a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "coding",
      "score": 1243.5371534871333,
      "unit": "Arena rating",
      "confidenceInterval": [
        1222.9034760701727,
        1264.1708309040941
      ],
      "voteCount": 831,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.82993821348951
      }
    },
    {
      "id": "e2b4e1ceb526a99160439ffe",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "creative_writing",
      "score": 1168.1617909644765,
      "unit": "Arena rating",
      "confidenceInterval": [
        1144.7126599012713,
        1191.6109220276815
      ],
      "voteCount": 635,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 143.13878484320426
      }
    },
    {
      "id": "1aadfe5ac44766a5a2b1f528",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "english",
      "score": 1238.9315175148786,
      "unit": "Arena rating",
      "confidenceInterval": [
        1225.6658092463845,
        1252.1972257833725
      ],
      "voteCount": 2702,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 45.81046526303512
      }
    },
    {
      "id": "e46881555b20ff69b7a89fe0",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "exclude_ties",
      "score": 1097.360721119081,
      "unit": "Arena rating",
      "confidenceInterval": [
        1081.5368410696788,
        1113.1846011684834
      ],
      "voteCount": 3178,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 65.18231523633168
      }
    },
    {
      "id": "b99192d8d52e2a9b56fbfe75",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "expert",
      "score": 1167.1612305431893,
      "unit": "Arena rating",
      "confidenceInterval": [
        1127.2465490187788,
        1207.0759120675998
      ],
      "voteCount": 219,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 414.7335362838104
      }
    },
    {
      "id": "dca9f9473f7d792334e8f686",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts_english",
      "score": 1228.6472552355572,
      "unit": "Arena rating",
      "confidenceInterval": [
        1208.064058157334,
        1249.23045231378
      ],
      "voteCount": 820,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 110.28831018014489
      }
    },
    {
      "id": "4d13080145edc18fad951941",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "hard_prompts",
      "score": 1214.1128863662889,
      "unit": "Arena rating",
      "confidenceInterval": [
        1197.1586318540662,
        1231.0671408785115
      ],
      "voteCount": 1240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 74.8274963971318
      }
    },
    {
      "id": "b18310b45a1a034b6cac534a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_business_and_management_and_financial_operations",
      "score": 1184.1376828295831,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.2971711638247,
        1211.9781944953415
      ],
      "voteCount": 441,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 201.7707662609208
      }
    },
    {
      "id": "04d52c5b4f9cf94b029b8a18",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_entertainment_and_sports_and_media",
      "score": 1188.8241081660808,
      "unit": "Arena rating",
      "confidenceInterval": [
        1165.595457890851,
        1212.0527584413103
      ],
      "voteCount": 617,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 140.4597104366277
      }
    },
    {
      "id": "1a86cbf9990c6084e9c2fd91",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_legal_and_government",
      "score": 1224.9725273503955,
      "unit": "Arena rating",
      "confidenceInterval": [
        1186.914914096224,
        1263.0301406045671
      ],
      "voteCount": 240,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 377.0395555984069
      }
    },
    {
      "id": "20090731de81a28c2d358758",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_life_and_physical_and_social_science",
      "score": 1239.3170220382212,
      "unit": "Arena rating",
      "confidenceInterval": [
        1218.347357957451,
        1260.2866861189914
      ],
      "voteCount": 827,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 114.46870373606811
      }
    },
    {
      "id": "08eab102dfcddac4a2e274fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_mathematical",
      "score": 1200.6185441784153,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.7840324480526,
        1224.453055908778
      ],
      "voteCount": 526,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 147.88234781133133
      }
    },
    {
      "id": "6e780da92e38f0fdcde08a2a",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_medicine_and_healthcare",
      "score": 1228.9807727858092,
      "unit": "Arena rating",
      "confidenceInterval": [
        1193.3174626536304,
        1264.6440829179883
      ],
      "voteCount": 284,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 331.09080402797423
      }
    },
    {
      "id": "576a6b8791ba21305b57aa66",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_software_and_it_services",
      "score": 1234.3633513837558,
      "unit": "Arena rating",
      "confidenceInterval": [
        1217.6198631422494,
        1251.1068396252622
      ],
      "voteCount": 1344,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 72.97862910393101
      }
    },
    {
      "id": "ddb2977e3caffa95efe30154",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "industry_writing_and_literature_and_language",
      "score": 1194.3933078846271,
      "unit": "Arena rating",
      "confidenceInterval": [
        1176.4005675967524,
        1212.3860481725021
      ],
      "voteCount": 1129,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 84.27493777179554
      }
    },
    {
      "id": "c648e4d4409ce390a8332fcc",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "instruction_following",
      "score": 1190.9044619271606,
      "unit": "Arena rating",
      "confidenceInterval": [
        1175.3365585838865,
        1206.4723652704347
      ],
      "voteCount": 1593,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 63.09051478045911
      }
    },
    {
      "id": "c3ec2fd0f2b9077ad7642a57",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "longer_query",
      "score": 1181.2344036440227,
      "unit": "Arena rating",
      "confidenceInterval": [
        1153.0184831781066,
        1209.4503241099387
      ],
      "voteCount": 448,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 207.24891373299545
      }
    },
    {
      "id": "a94f706b3df0faac1e3cfce2",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "math",
      "score": 1195.7533621199987,
      "unit": "Arena rating",
      "confidenceInterval": [
        1173.5659110274205,
        1217.9408132125768
      ],
      "voteCount": 589,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 128.15000992164778
      }
    },
    {
      "id": "d9b181b34054014d4e87c3b6",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "multi_turn",
      "score": 1157.5371942883387,
      "unit": "Arena rating",
      "confidenceInterval": [
        1133.5002678150588,
        1181.5741207616184
      ],
      "voteCount": 683,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 150.40479704464465
      }
    },
    {
      "id": "3e5b7a7debaa242cd5b692fd",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "overall",
      "score": 1211.8927929621304,
      "unit": "Arena rating",
      "confidenceInterval": [
        1201.0970018803523,
        1222.688584043909
      ],
      "voteCount": 4652,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 30.33980331991355
      }
    },
    {
      "id": "27034e4501dc1821624fb613",
      "sourceId": "lmarena-text-style-control-latest",
      "model": "zephyr-orpo-141b-A35b-v0.1",
      "license": "Apache 2.0",
      "benchmark": "LMArena Arena rating",
      "category": "russian",
      "score": 1184.0199142040724,
      "unit": "Arena rating",
      "confidenceInterval": [
        1156.558354742816,
        1211.4814736653286
      ],
      "voteCount": 407,
      "asOf": "2026-05-27",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "variance": 196.31532791176664
      }
    },
    {
      "id": "1a056434259328c4d619aa46",
      "sourceId": "openevals-leaderboard-data",
      "model": "allenai/olmOCR-2-7B-1025-FP8",
      "organization": "allenai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "allenai-olmocr-2-7b-1025-fp8",
        "modelType": "open",
        "parametersBillions": 8.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ddc570465b37145436c6af14",
      "sourceId": "openevals-leaderboard-data",
      "model": "allenai/olmOCR-2-7B-1025-FP8",
      "organization": "allenai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "allenai-olmocr-2-7b-1025-fp8",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "78a6e21f170e725f71982b14",
      "sourceId": "openevals-leaderboard-data",
      "model": "allenai/olmOCR-2-7B-1025-FP8",
      "organization": "allenai",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "allenai-olmocr-2-7b-1025-fp8",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "042d99a6d99bc72520b2a2b5",
      "sourceId": "openevals-leaderboard-data",
      "model": "arcee-ai/Trinity-Large-Preview",
      "organization": "arcee-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "arcee-ai-trinity-large-preview",
        "modelType": "open",
        "parametersBillions": 398.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e0b28d7db420bfe8d3790260",
      "sourceId": "openevals-leaderboard-data",
      "model": "arcee-ai/Trinity-Large-Preview",
      "organization": "arcee-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "arcee-ai-trinity-large-preview",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "c75cc24eae3038c0283b2aa6",
      "sourceId": "openevals-leaderboard-data",
      "model": "arcee-ai/Trinity-Large-Preview",
      "organization": "arcee-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "arcee-ai-trinity-large-preview",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ab4dc8b4611ef25858b941f6",
      "sourceId": "openevals-leaderboard-data",
      "model": "Ares-Realm-Studios/Trinity-Large-Preview-ARSTEST",
      "organization": "Ares-Realm-Studios",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "ares-realm-studios-trinity-large-preview-arstest",
        "modelType": "open",
        "parametersBillions": 398.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "4c07b5e05cc8344b084fe4d0",
      "sourceId": "openevals-leaderboard-data",
      "model": "Ares-Realm-Studios/Trinity-Large-Preview-ARSTEST",
      "organization": "Ares-Realm-Studios",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "ares-realm-studios-trinity-large-preview-arstest",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e8853b0c51a11edb071b65be",
      "sourceId": "openevals-leaderboard-data",
      "model": "Ares-Realm-Studios/Trinity-Large-Preview-ARSTEST",
      "organization": "Ares-Realm-Studios",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "ares-realm-studios-trinity-large-preview-arstest",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2437bc665a873f3a3550cade",
      "sourceId": "openevals-leaderboard-data",
      "model": "baidu/Qianfan-OCR",
      "organization": "baidu",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 79.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "baidu-qianfan-ocr",
        "modelType": "open",
        "parametersBillions": 4.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "f6e42da864db0eaca15aac72",
      "sourceId": "openevals-leaderboard-data",
      "model": "baidu/Qianfan-OCR",
      "organization": "baidu",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 79.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "baidu-qianfan-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e3f056a5d64623d8d68a49c0",
      "sourceId": "openevals-leaderboard-data",
      "model": "baidu/Qianfan-OCR",
      "organization": "baidu",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 79.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "baidu-qianfan-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "8338436b6679c3601235c2b3",
      "sourceId": "openevals-leaderboard-data",
      "model": "datalab-to/chandra-ocr-2",
      "organization": "datalab-to",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 85.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "datalab-to-chandra-ocr-2",
        "modelType": "open",
        "parametersBillions": 5.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "1caa41a1361296c93a6f11b9",
      "sourceId": "openevals-leaderboard-data",
      "model": "datalab-to/chandra-ocr-2",
      "organization": "datalab-to",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 85.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "datalab-to-chandra-ocr-2",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ff949ce6a5057865fd2d60e0",
      "sourceId": "openevals-leaderboard-data",
      "model": "datalab-to/chandra-ocr-2",
      "organization": "datalab-to",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 85.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "datalab-to-chandra-ocr-2",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ecb055b18cb3369998ff3ed8",
      "sourceId": "openevals-leaderboard-data",
      "model": "datalab-to/chandra",
      "organization": "datalab-to",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "datalab-to-chandra",
        "modelType": "open",
        "parametersBillions": 8.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3cbbfa4bd969b92798038f03",
      "sourceId": "openevals-leaderboard-data",
      "model": "datalab-to/chandra",
      "organization": "datalab-to",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "datalab-to-chandra",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "1e330c272fa409f28b42479e",
      "sourceId": "openevals-leaderboard-data",
      "model": "datalab-to/chandra",
      "organization": "datalab-to",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "datalab-to-chandra",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "b8ee597abe6939aeebd0312b",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-OCR-2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 76.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-ocr-2",
        "modelType": "open",
        "parametersBillions": 3.4,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "15efb3c355e62ef7369e6dc0",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-OCR-2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 76.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-ocr-2",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "f0217c2e41bd111fed406425",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-OCR-2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 76.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-ocr-2",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2816a984e1384710c8bae966",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-OCR",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 75.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-ocr",
        "modelType": "open",
        "parametersBillions": 3.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "32253d14339c94e3ed6f5aa3",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-OCR",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 75.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "09d54c7a347fc09e3173c371",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-OCR",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 75.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "9253718892b96d632cf75a94",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1-0528",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1-0528",
        "modelType": "open",
        "parametersBillions": 684.5,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "4d36bb9783b3ff8af860f929",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1-0528",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1-0528",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "b62d9278e0eb591cea63af36",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1-0528",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1-0528",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "954b0a7c7467c2e2acc6382e",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 77.75,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1",
        "modelType": "open",
        "parametersBillions": 684.5,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "b67b5166a40d9a5c2f626f03",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 77.75,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1cb6be54bc158e9ddcd1f096",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 71.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1cfb4b89bcd2516f167935c0",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-R1",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 84,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-r1",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "2ed628494d0bdfe611cfa00a",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 79.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v2",
        "modelType": "open",
        "parametersBillions": 235.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2771e435b3a16cda677abd5a",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 79.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v2",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "01fa2ed83b8a7e70b953eda9",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 79.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v2",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2e8a8e76c76fdadf4f30fba4",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3-0324",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 81.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3-0324",
        "modelType": "open",
        "parametersBillions": 684.5,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "fe16eec81d2c1f330651d080",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3-0324",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 81.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3-0324",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "c9460f074b78186cde367b7f",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3-0324",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 81.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3-0324",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2b86aa15813f95cee2f6a54b",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 64.28,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "modelType": "open",
        "parametersBillions": 685.4,
        "contextWindow": null,
        "coveragePercent": 81.8
      }
    },
    {
      "id": "78b341c46f9ab588322b19fd",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 64.28,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "8c8a539b4719e6c6cbc16d7d",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 94.17,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "8afe4da1a1b38387530b180f",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals evasionBench",
      "category": "evasionBench",
      "score": 66.88,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "03610cbcad0f16ecabb9d604",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "921702c8c2f8d5d228157388",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 40.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "3b90eb7c4b6b44dcd1002970",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 84.09,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "b3766d749677afc7fe134270",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "20226bdcaf6f2f46bcfe4b55",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 15.56,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "e36a2bee46f4d2d6c1a06ddd",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 70,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "ad097bddb63750f9b0011294",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3.2",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 39.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3.2",
        "coveragePercent": 81.8
      }
    },
    {
      "id": "9e33bb5a491ac7c1002e1a07",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 76.85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3",
        "modelType": "open",
        "parametersBillions": 684.5,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "3c5529f2e4972d3e0eecd653",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 76.85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "09cdf2f27c5518239774678e",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 89.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "c820455200f77f578883898b",
      "sourceId": "openevals-leaderboard-data",
      "model": "deepseek-ai/DeepSeek-V3",
      "organization": "deepseek-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 64.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "deepseek-ai-deepseek-v3",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "6425a994f1d18eea2afa70c6",
      "sourceId": "openevals-leaderboard-data",
      "model": "facebook/cwm",
      "organization": "facebook",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 53.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "facebook-cwm",
        "modelType": "open",
        "parametersBillions": 32.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5fb04776695519954ec8d62f",
      "sourceId": "openevals-leaderboard-data",
      "model": "facebook/cwm",
      "organization": "facebook",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 53.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "facebook-cwm",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a6d453d68027d4b797ace101",
      "sourceId": "openevals-leaderboard-data",
      "model": "facebook/cwm",
      "organization": "facebook",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 53.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "facebook-cwm",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2c93d6de855fd46f5d579942",
      "sourceId": "openevals-leaderboard-data",
      "model": "FireRedTeam/FireRed-OCR",
      "organization": "FireRedTeam",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 70.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "fireredteam-firered-ocr",
        "modelType": "open",
        "parametersBillions": 2.1,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "b8168896662fc49dccea0d2e",
      "sourceId": "openevals-leaderboard-data",
      "model": "FireRedTeam/FireRed-OCR",
      "organization": "FireRedTeam",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 70.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "fireredteam-firered-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e08d15fffb0a1b62f48fde4d",
      "sourceId": "openevals-leaderboard-data",
      "model": "FireRedTeam/FireRed-OCR",
      "organization": "FireRedTeam",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 70.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "fireredteam-firered-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "28b675f87e340e3f7deb8d9f",
      "sourceId": "openevals-leaderboard-data",
      "model": "GAIR/OpenSWE-32B",
      "organization": "GAIR",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 62.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "gair-openswe-32b",
        "modelType": "open",
        "parametersBillions": 32.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0913d47c8a0dbdb5edfcd511",
      "sourceId": "openevals-leaderboard-data",
      "model": "GAIR/OpenSWE-32B",
      "organization": "GAIR",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 62.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "gair-openswe-32b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "38960624f47ef51bb5ee204c",
      "sourceId": "openevals-leaderboard-data",
      "model": "GAIR/OpenSWE-32B",
      "organization": "GAIR",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 62.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "gair-openswe-32b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "1af0c5cccd90affecf8b8b7a",
      "sourceId": "openevals-leaderboard-data",
      "model": "GAIR/OpenSWE-72B",
      "organization": "GAIR",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 66,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "gair-openswe-72b",
        "modelType": "open",
        "parametersBillions": 72.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3816f027180fbde3b277d76b",
      "sourceId": "openevals-leaderboard-data",
      "model": "GAIR/OpenSWE-72B",
      "organization": "GAIR",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 66,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "gair-openswe-72b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "24f59884c671401592e67635",
      "sourceId": "openevals-leaderboard-data",
      "model": "GAIR/OpenSWE-72B",
      "organization": "GAIR",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 66,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "gair-openswe-72b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "bd41b3bb9dc2884109cec041",
      "sourceId": "openevals-leaderboard-data",
      "model": "google/gemma-3-27b-it",
      "organization": "google",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 11.38,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "google-gemma-3-27b-it",
        "modelType": "open",
        "parametersBillions": 27.4,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3cd5c847be1e4a59eb6d4c46",
      "sourceId": "openevals-leaderboard-data",
      "model": "google/gemma-3-27b-it",
      "organization": "google",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 11.38,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "google-gemma-3-27b-it",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "10526dc078f6ad70d6c8825e",
      "sourceId": "openevals-leaderboard-data",
      "model": "google/gemma-3-27b-it",
      "organization": "google",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 11.38,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "google-gemma-3-27b-it",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "136dd533d9c3f49f7ca19036",
      "sourceId": "openevals-leaderboard-data",
      "model": "HelpingAI/Dhanishtha-2.0-0126",
      "organization": "HelpingAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 9.92,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "helpingai-dhanishtha-2.0-0126",
        "modelType": "open",
        "parametersBillions": 14.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "33de0379c6af9292a7580bb2",
      "sourceId": "openevals-leaderboard-data",
      "model": "HelpingAI/Dhanishtha-2.0-0126",
      "organization": "HelpingAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 9.92,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "helpingai-dhanishtha-2.0-0126",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "03db8e1228d64e843b08e42e",
      "sourceId": "openevals-leaderboard-data",
      "model": "HelpingAI/Dhanishtha-2.0-0126",
      "organization": "HelpingAI",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 9.92,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "helpingai-dhanishtha-2.0-0126",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "02a4c5620408e403b9b1eb8c",
      "sourceId": "openevals-leaderboard-data",
      "model": "infly/Infinity-Parser-7B",
      "organization": "infly",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 82.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "infly-infinity-parser-7b",
        "modelType": "open",
        "parametersBillions": 8.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e5d93eef4947a2d89cf8c5be",
      "sourceId": "openevals-leaderboard-data",
      "model": "infly/Infinity-Parser-7B",
      "organization": "infly",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 82.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "infly-infinity-parser-7b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5f6f5fad745187dfbdfd8d5a",
      "sourceId": "openevals-leaderboard-data",
      "model": "infly/Infinity-Parser-7B",
      "organization": "infly",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 82.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "infly-infinity-parser-7b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ce89dc208f68e01492982d99",
      "sourceId": "openevals-leaderboard-data",
      "model": "internlm/internlm2_5-7b-chat",
      "organization": "internlm",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 86,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "internlm-internlm2_5-7b-chat",
        "modelType": "open",
        "parametersBillions": 7.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "579934bd4680fbaeea2f473b",
      "sourceId": "openevals-leaderboard-data",
      "model": "internlm/internlm2_5-7b-chat",
      "organization": "internlm",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 86,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "internlm-internlm2_5-7b-chat",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "37939e33f39b94687bd6f35b",
      "sourceId": "openevals-leaderboard-data",
      "model": "internlm/internlm2_5-7b-chat",
      "organization": "internlm",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 86,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "internlm-internlm2_5-7b-chat",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "8d667ea934b10a37ee086aff",
      "sourceId": "openevals-leaderboard-data",
      "model": "internlm/internlm2-chat-20b",
      "organization": "internlm",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 79.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "internlm-internlm2-chat-20b",
        "modelType": "open",
        "parametersBillions": 19.9,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "4fb13f246886bc7a70d86d15",
      "sourceId": "openevals-leaderboard-data",
      "model": "internlm/internlm2-chat-20b",
      "organization": "internlm",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 79.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "internlm-internlm2-chat-20b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "b924104cd193705907347141",
      "sourceId": "openevals-leaderboard-data",
      "model": "internlm/internlm2-chat-20b",
      "organization": "internlm",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 79.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "internlm-internlm2-chat-20b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "814a0b4f2075000abc36b2ff",
      "sourceId": "openevals-leaderboard-data",
      "model": "jdopensource/JoyAI-LLM-Flash",
      "organization": "jdopensource",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 77.72,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "jdopensource-joyai-llm-flash",
        "modelType": "open",
        "parametersBillions": 49.3,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "609f74c31fd19d4f3fbb4370",
      "sourceId": "openevals-leaderboard-data",
      "model": "jdopensource/JoyAI-LLM-Flash",
      "organization": "jdopensource",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 77.72,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "jdopensource-joyai-llm-flash",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1384f539188d3db364dd78ba",
      "sourceId": "openevals-leaderboard-data",
      "model": "jdopensource/JoyAI-LLM-Flash",
      "organization": "jdopensource",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 74.43,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "jdopensource-joyai-llm-flash",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "814bdea5014aedaf00b028f7",
      "sourceId": "openevals-leaderboard-data",
      "model": "jdopensource/JoyAI-LLM-Flash",
      "organization": "jdopensource",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 81.02,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "jdopensource-joyai-llm-flash",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "d9b5f9855ea6a879ab3c0f0a",
      "sourceId": "openevals-leaderboard-data",
      "model": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "organization": "LGAI-EXAONE",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 58.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lgai-exaone-k-exaone-236b-a23b",
        "modelType": "open",
        "parametersBillions": 237.1,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "32d3216b2696c63c68204924",
      "sourceId": "openevals-leaderboard-data",
      "model": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "organization": "LGAI-EXAONE",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 58.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lgai-exaone-k-exaone-236b-a23b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "ded6e7f125afe4ac1b2cb825",
      "sourceId": "openevals-leaderboard-data",
      "model": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "organization": "LGAI-EXAONE",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 79.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lgai-exaone-k-exaone-236b-a23b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "f5489286e3e38fcea9a8471d",
      "sourceId": "openevals-leaderboard-data",
      "model": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "organization": "LGAI-EXAONE",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 13.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lgai-exaone-k-exaone-236b-a23b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "f3c39431c25b37313baef765",
      "sourceId": "openevals-leaderboard-data",
      "model": "LGAI-EXAONE/K-EXAONE-236B-A23B",
      "organization": "LGAI-EXAONE",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 83.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lgai-exaone-k-exaone-236b-a23b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "fb3695ad3dfcac36230c77ef",
      "sourceId": "openevals-leaderboard-data",
      "model": "lightonai/LightOnOCR-1B-1025",
      "organization": "lightonai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 76.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lightonai-lightonocr-1b-1025",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ebbcf3e2c0e74517939b44f2",
      "sourceId": "openevals-leaderboard-data",
      "model": "lightonai/LightOnOCR-1B-1025",
      "organization": "lightonai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 76.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lightonai-lightonocr-1b-1025",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "47a0be623afb72d8e1dbdb34",
      "sourceId": "openevals-leaderboard-data",
      "model": "lightonai/LightOnOCR-1B-1025",
      "organization": "lightonai",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 76.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lightonai-lightonocr-1b-1025",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "4565ac7aba6b461914aae6f6",
      "sourceId": "openevals-leaderboard-data",
      "model": "lightonai/LightOnOCR-2-1B",
      "organization": "lightonai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lightonai-lightonocr-2-1b",
        "modelType": "open",
        "parametersBillions": 1,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "7936ef42c1772bd9e9765925",
      "sourceId": "openevals-leaderboard-data",
      "model": "lightonai/LightOnOCR-2-1B",
      "organization": "lightonai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lightonai-lightonocr-2-1b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "27bd41374913f7ac7e8b4b08",
      "sourceId": "openevals-leaderboard-data",
      "model": "lightonai/LightOnOCR-2-1B",
      "organization": "lightonai",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lightonai-lightonocr-2-1b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "6d8241417544a3403ec961b9",
      "sourceId": "openevals-leaderboard-data",
      "model": "LiquidAI/LFM2.5-1.2B-Instruct",
      "organization": "LiquidAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 38.89,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "liquidai-lfm2.5-1.2b-instruct",
        "modelType": "open",
        "parametersBillions": 1.2,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ff2e240749167b2548cebb30",
      "sourceId": "openevals-leaderboard-data",
      "model": "LiquidAI/LFM2.5-1.2B-Instruct",
      "organization": "LiquidAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 38.89,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "liquidai-lfm2.5-1.2b-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "86142ded568fc64a809d231b",
      "sourceId": "openevals-leaderboard-data",
      "model": "LiquidAI/LFM2.5-1.2B-Instruct",
      "organization": "LiquidAI",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 38.89,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "liquidai-lfm2.5-1.2b-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3eb1052e786172ed75ba863b",
      "sourceId": "openevals-leaderboard-data",
      "model": "lm-provers/QED-Nano",
      "organization": "lm-provers",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 72.69,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lm-provers-qed-nano",
        "modelType": "open",
        "parametersBillions": 4,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1c0a9463e726c1454271ed1c",
      "sourceId": "openevals-leaderboard-data",
      "model": "lm-provers/QED-Nano",
      "organization": "lm-provers",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 72.69,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lm-provers-qed-nano",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "4d43254d67f881aa63f67c88",
      "sourceId": "openevals-leaderboard-data",
      "model": "lm-provers/QED-Nano",
      "organization": "lm-provers",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 82.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lm-provers-qed-nano",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "3df3eff6a9f0ce9a4c042c7c",
      "sourceId": "openevals-leaderboard-data",
      "model": "lm-provers/QED-Nano",
      "organization": "lm-provers",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 62.88,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "lm-provers-qed-nano",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "13732de0daa71aa28beb3edf",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Lite",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 78.29,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-lite",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "091afa9df7c3bd3ee7f70560",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Lite",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 78.29,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-lite",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5434565ca5820492359fdd49",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Lite",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 78.29,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-lite",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "710867e4020eb8a2dd240ad8",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Thinking-2601",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 52.85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-thinking-2601",
        "modelType": "open",
        "parametersBillions": 561.9,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "661c9a0baa4183ce0dd353c1",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Thinking-2601",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 52.85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-thinking-2601",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "a0d93d7dee8bb325e440273e",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Thinking-2601",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 80.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-thinking-2601",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "7f32f1eb094872207e300d05",
      "sourceId": "openevals-leaderboard-data",
      "model": "meituan-longcat/LongCat-Flash-Thinking-2601",
      "organization": "meituan-longcat",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 25.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meituan-longcat-longcat-flash-thinking-2601",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "f8ed667e28915a5db912f6f6",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-405B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 11.18,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-405b-instruct",
        "modelType": "open",
        "parametersBillions": 405.9,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3c9e81a457eb816b133fd981",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-405B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 11.18,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-405b-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5823afe6550cf8ed0e113f34",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-405B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 11.18,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-405b-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "1342a0e3b2abf3e7df52a890",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-405B",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 96.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-405b",
        "modelType": "open",
        "parametersBillions": 405.9,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "10445651bb050b5b6e00ded2",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-405B",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 96.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-405b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "9e18f0321e176249c23a3f81",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-405B",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 96.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-405b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "143cdfb448ac57c840a0c169",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-8B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 54.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-8b-instruct",
        "modelType": "open",
        "parametersBillions": 8,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "14a1c1953050e0db20885f1d",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-8B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 54.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-8b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "891267066b0f8af3b81e3e59",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-8B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 30.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-8b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "fcafcbe6883a6a7215ecd9f3",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-8B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 84.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-8b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "21ef5c372ebaa33b049fb819",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-3.1-8B-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 48.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-3.1-8b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "36ab68765d507e34a5995002",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 5.24,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-4-maverick-17b-128e-instruct",
        "modelType": "open",
        "parametersBillions": 401.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0908cecfc0e3157c0418296a",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 5.24,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-4-maverick-17b-128e-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d01fad70d2c0fac4864d19b6",
      "sourceId": "openevals-leaderboard-data",
      "model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
      "organization": "meta-llama",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 5.24,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "meta-llama-llama-4-maverick-17b-128e-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a5b29faf13b1bc8091a5aec7",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 91,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3-medium-4k-instruct",
        "modelType": "open",
        "parametersBillions": 14,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "96306f26c61c5353f1012f45",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 91,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3-medium-4k-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3f7bbf2161bebf2e4de82f96",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3-medium-4k-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 91,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3-medium-4k-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "801ba37c6951b750359ee1f1",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 85.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3-mini-4k-instruct",
        "modelType": "open",
        "parametersBillions": 3.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3a2ad6b50bc990fefd97ede4",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 85.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3-mini-4k-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a46e1264fb9d7d50f5715723",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3-mini-4k-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 85.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3-mini-4k-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d6996d96da5fd98edae9d443",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3.5-mini-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 86.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3.5-mini-instruct",
        "modelType": "open",
        "parametersBillions": 3.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "cd213c520fa015301c90d062",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3.5-mini-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 86.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3.5-mini-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d27bfbc92c9a54b66fecffda",
      "sourceId": "openevals-leaderboard-data",
      "model": "microsoft/Phi-3.5-mini-instruct",
      "organization": "microsoft",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 86.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "microsoft-phi-3.5-mini-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2bb15a2c9774978686408068",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 53.59,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "modelType": "open",
        "parametersBillions": 228.7,
        "contextWindow": null,
        "coveragePercent": 54.5
      }
    },
    {
      "id": "5be6798ae679957084c99a90",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 53.59,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "18764c5b2fe77ddec2884787",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals evasionBench",
      "category": "evasionBench",
      "score": 71.31,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "52c697f4e5ed730672d0b796",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 22.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "10e7036b21c6b5e8f348bc4e",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 88,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "8d53f24662524571a285cf4e",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 36.81,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "ae629102638d88cd09cb5ad3",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 74,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "4c222ac25fe0422a1c640f43",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.1",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 29.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.1",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "03909791e54d11008734c112",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.5",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 58.95,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.5",
        "modelType": "open",
        "parametersBillions": 228.7,
        "contextWindow": null,
        "coveragePercent": 36.4
      }
    },
    {
      "id": "da37ef16503e288df741c408",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.5",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 58.95,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.5",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "bae4ca78c4a1d46a7b712f1a",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.5",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 85.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.5",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "3e79cadc0d8fdf404b072d57",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.5",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 19.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.5",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "bbcb94c20c81ba95c7520f33",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.5",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 55.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.5",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "aabd14e5dea3011e65307018",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2.5",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 75.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2.5",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "451bafd4ced1da00271b5199",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 48.48,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2",
        "modelType": "open",
        "parametersBillions": 228.7,
        "contextWindow": null,
        "coveragePercent": 36.4
      }
    },
    {
      "id": "29858a400af1d516253c08db",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 48.48,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "429a6f2c4d28999294b1ba3d",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 12.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "aa6ed61593a88044e2836095",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 82,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "d3faa95c07b112bec6c5ae12",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 69.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "c814590a5ef15f20d6252d1a",
      "sourceId": "openevals-leaderboard-data",
      "model": "MiniMaxAI/MiniMax-M2",
      "organization": "MiniMaxAI",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 30,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "minimaxai-minimax-m2",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "06e36058ebbb57ec449fd6de",
      "sourceId": "openevals-leaderboard-data",
      "model": "miromind-ai/MiroThinker-v1.5-235B",
      "organization": "miromind-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 39.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "miromind-ai-mirothinker-v1.5-235b",
        "modelType": "open",
        "parametersBillions": 235.1,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2a057a41656a2b95054bea11",
      "sourceId": "openevals-leaderboard-data",
      "model": "miromind-ai/MiroThinker-v1.5-235B",
      "organization": "miromind-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 39.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "miromind-ai-mirothinker-v1.5-235b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "1a64e3589e17bce4ff78b3d7",
      "sourceId": "openevals-leaderboard-data",
      "model": "miromind-ai/MiroThinker-v1.5-235B",
      "organization": "miromind-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 39.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "miromind-ai-mirothinker-v1.5-235b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "f6da240cd1483b843ea2383e",
      "sourceId": "openevals-leaderboard-data",
      "model": "miromind-ai/MiroThinker-v1.5-30B",
      "organization": "miromind-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 31,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "miromind-ai-mirothinker-v1.5-30b",
        "modelType": "open",
        "parametersBillions": 30.5,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "722f0df0e293ec312a890ad1",
      "sourceId": "openevals-leaderboard-data",
      "model": "miromind-ai/MiroThinker-v1.5-30B",
      "organization": "miromind-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 31,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "miromind-ai-mirothinker-v1.5-30b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "06ea19676410676b18157386",
      "sourceId": "openevals-leaderboard-data",
      "model": "miromind-ai/MiroThinker-v1.5-30B",
      "organization": "miromind-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 31,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "miromind-ai-mirothinker-v1.5-30b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "191d46716fde5808f0045c6c",
      "sourceId": "openevals-leaderboard-data",
      "model": "mistralai/Mistral-Small-4-119B-2603",
      "organization": "mistralai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 71.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mistralai-mistral-small-4-119b-2603",
        "modelType": "open",
        "parametersBillions": 119.4,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "449ee857c933ab3bc571c954",
      "sourceId": "openevals-leaderboard-data",
      "model": "mistralai/Mistral-Small-4-119B-2603",
      "organization": "mistralai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 71.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mistralai-mistral-small-4-119b-2603",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a9c2aa1f31b0c766ee650008",
      "sourceId": "openevals-leaderboard-data",
      "model": "mistralai/Mistral-Small-4-119B-2603",
      "organization": "mistralai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 71.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mistralai-mistral-small-4-119b-2603",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "67f745b88329054207e72686",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-4bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-4bit",
        "modelType": "open",
        "parametersBillions": 1.5,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "8d5321e5fac38c0e2a58168c",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-4bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-4bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d4543a664fe00e30532b3592",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-4bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-4bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "830feb74e91aa16df1e6e375",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-5bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-5bit",
        "modelType": "open",
        "parametersBillions": 1.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "7c68ff183eb181736101f8e6",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-5bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-5bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "1f2ef6631e30e839a1137df5",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-5bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-5bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "f40d2ab2465a1a32d55c564f",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-6bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-6bit",
        "modelType": "open",
        "parametersBillions": 1.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a7db33fc12ad0a8cbbf832d6",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-6bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-6bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d932831b81a90668e24ce73e",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-6bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-6bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "86cd8ce6df30dd15a9f84ab4",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-8bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-8bit",
        "modelType": "open",
        "parametersBillions": 1.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "b33eeae04b8eb33c620645ca",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-8bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-8bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "06a8a8af4cf63e662c3c889c",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-8bit",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-8bit",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "450f51e7cbb8b5c35e7e9102",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-bf16",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-bf16",
        "modelType": "open",
        "parametersBillions": 3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "046b070895ebdd22116772ae",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-bf16",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-bf16",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "14990bcb0df71f9604005821",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-bf16",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-bf16",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "51527d8768089a61bd39a352",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-mxfp4",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-mxfp4",
        "modelType": "open",
        "parametersBillions": 1.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "03ba90abb330103a974cbaa4",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-mxfp4",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-mxfp4",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "7cc251aa7932d23add9d40e9",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-mxfp4",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-mxfp4",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0bb66e7dc7b17dc7592b9db1",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-mxfp8",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-mxfp8",
        "modelType": "open",
        "parametersBillions": 1.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "33eb7e666d520998f2a9e1e0",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-mxfp8",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-mxfp8",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "8cc65b187d0deb505ae41ce2",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-mxfp8",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-mxfp8",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a9319bebffd0595030aebcef",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-nvfp4",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-nvfp4",
        "modelType": "open",
        "parametersBillions": 1.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ed25cbf49c90ab0d36502f0e",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-nvfp4",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-nvfp4",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5c2e3abd531465f37e790ec5",
      "sourceId": "openevals-leaderboard-data",
      "model": "mlx-community/dots.mocr-nvfp4",
      "organization": "mlx-community",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "mlx-community-dots.mocr-nvfp4",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ecba899af435287b9cd8c7db",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct-0905",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 66.68,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct-0905",
        "modelType": "open",
        "parametersBillions": 1026.5,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "c13f877ada29117ea3a5ef5d",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct-0905",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 66.68,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct-0905",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "4cfaed6f09e1f22e9ab404df",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct-0905",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals evasionBench",
      "category": "evasionBench",
      "score": 66.68,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct-0905",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "bd8b3faa120db4534167a415",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 27.73,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct",
        "modelType": "open",
        "parametersBillions": 1026.5,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "5c113129bb0fbb832e6460c8",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 27.73,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "fb236f667299651dfa163a1a",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 27.67,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "2019e6cde4f63bf1d3803afa",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Instruct",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 27.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-instruct",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "716565feda4234818fb96bb1",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 60,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "modelType": "open",
        "parametersBillions": 1058.1,
        "contextWindow": null,
        "coveragePercent": 45.5
      }
    },
    {
      "id": "f0dc2e0b87fd95a90d61e0d7",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 60,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "25ee080c283744c17e4bd8cd",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 84.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "f372ecd629c2efd2664e8d64",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 23.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "8f0560d0ef94758d73b46873",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 84.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "333f8d3c6df4d02ebc4b0968",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 71.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "e1c87313a0b0ec2cae01354d",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2-Thinking",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 35.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2-thinking",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "9ec33a3b6a4956fe4b18e479",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 71.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "modelType": "open",
        "parametersBillions": 1058.6,
        "contextWindow": null,
        "coveragePercent": 72.7
      }
    },
    {
      "id": "da5e8d404d6c966a6f0c495b",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 71.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "1ee6e6b07bc82199c6a74b51",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 95.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "aeca8a7a6608179d6b4488aa",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 87.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "7acce5c21f6b1c88a0568cd9",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 50.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "36a03b932da0a4c356b2ce1d",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 87.12,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "4025f500a8fb2863b9425228",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 87.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "4251f2e762aed041e803a822",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 50.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "a7bfd28ca52f67065c37a958",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 70.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "6bd8f8dd3a66d92c7bc529d3",
      "sourceId": "openevals-leaderboard-data",
      "model": "moonshotai/Kimi-K2.5",
      "organization": "moonshotai",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 43.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "moonshotai-kimi-k2.5",
        "coveragePercent": 72.7
      }
    },
    {
      "id": "ac84ee95776ee66f464522fb",
      "sourceId": "openevals-leaderboard-data",
      "model": "Multilingual-Multimodal-NLP/IndustrialCoder",
      "organization": "Multilingual-Multimodal-NLP",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 74.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "multilingual-multimodal-nlp-industrialcoder",
        "modelType": "open",
        "parametersBillions": 32,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "bd0859f254059c62143e7643",
      "sourceId": "openevals-leaderboard-data",
      "model": "Multilingual-Multimodal-NLP/IndustrialCoder",
      "organization": "Multilingual-Multimodal-NLP",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 74.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "multilingual-multimodal-nlp-industrialcoder",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "cbc69a1c9ac170641d4706a8",
      "sourceId": "openevals-leaderboard-data",
      "model": "Multilingual-Multimodal-NLP/IndustrialCoder",
      "organization": "Multilingual-Multimodal-NLP",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 74.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "multilingual-multimodal-nlp-industrialcoder",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a4fe9b6868566b5e783e8450",
      "sourceId": "openevals-leaderboard-data",
      "model": "Nanbeige/Nanbeige4.1-3B",
      "organization": "Nanbeige",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 48.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanbeige-nanbeige4.1-3b",
        "modelType": "open",
        "parametersBillions": 3.9,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "e8b11d651252cb24490cacbd",
      "sourceId": "openevals-leaderboard-data",
      "model": "Nanbeige/Nanbeige4.1-3B",
      "organization": "Nanbeige",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 48.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanbeige-nanbeige4.1-3b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "169b343aaba0cecda0387a67",
      "sourceId": "openevals-leaderboard-data",
      "model": "Nanbeige/Nanbeige4.1-3B",
      "organization": "Nanbeige",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 83.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanbeige-nanbeige4.1-3b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "e85ba1f54750361b9402936d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Nanbeige/Nanbeige4.1-3B",
      "organization": "Nanbeige",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 12.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanbeige-nanbeige4.1-3b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "77e642c07af10e0aa98c4333",
      "sourceId": "openevals-leaderboard-data",
      "model": "nanonets/Nanonets-OCR2-3B",
      "organization": "nanonets",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 69.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanonets-nanonets-ocr2-3b",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "29efc4320e1f3159588dd0a8",
      "sourceId": "openevals-leaderboard-data",
      "model": "nanonets/Nanonets-OCR2-3B",
      "organization": "nanonets",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 69.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanonets-nanonets-ocr2-3b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "09dcb6e08986c278d2fc06d2",
      "sourceId": "openevals-leaderboard-data",
      "model": "nanonets/Nanonets-OCR2-3B",
      "organization": "nanonets",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 69.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nanonets-nanonets-ocr2-3b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a4ad4fa5dda3660a9d0ad9b4",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 57.87,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
        "modelType": "open",
        "parametersBillions": 31.6,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "2c25bd907c0990e39bd0fe94",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 57.87,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "3cb98cac16b535af8c03df77",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 76.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "db8f5ecab31f3e7c93ccb4a1",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 17.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "e5c3ad4e43ba92f9fd10f525",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Cascade-2-30B-A3B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 79.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-cascade-2-30b-a3b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "8c8df37143467a46d6a53b33",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Orchestrator-8B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 37.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-orchestrator-8b",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d5d99a8de1d0a0fc03adb8f3",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Orchestrator-8B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 37.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-orchestrator-8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d3525d3edd99cc68ec2e48d9",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Orchestrator-8B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 37.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-orchestrator-8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "21d380b866cea70f0c5bbf6f",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-14B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 20.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-14b",
        "modelType": "open",
        "parametersBillions": 14.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a3516c0683c37276ea3a1069",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-14B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 20.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-14b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0f4351c71e6f88f140c84584",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-14B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 20.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-14b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "822bfd0fd49a2c93df1c87b8",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-32B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 27.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-32b",
        "modelType": "open",
        "parametersBillions": 32.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "098aa10f158612729c74df9b",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-32B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 27.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-32b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5ad1fd3eedf9c335098f1e47",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-32B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 27.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-32b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "aec05480c697824a30678046",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-8B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 13,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-8b",
        "modelType": "open",
        "parametersBillions": 8.2,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3eced6863f8d243eb7770d4d",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-8B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 13,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "555425968251bd73ab0566ec",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/Nemotron-Terminal-8B",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 13,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nemotron-terminal-8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "450cc23dcfb446e369e879b3",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 46.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16",
        "modelType": "open",
        "parametersBillions": 31.6,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "812493073c22dd070ebaf95d",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 46.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "5c6fd5d6f6d622a3038548d9",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 15.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1e18738b4d8ba533e7edef74",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 78.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-bf16",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "d7e9c56f7a7a7e3c97b112fb",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 44.15,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-fp8",
        "modelType": "open",
        "parametersBillions": 31.6,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "7e128ea1f1be16cb5283a63e",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 44.15,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-fp8",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "fc57b362160a7c638ecb351c",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 10.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-fp8",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "3485a79427055cea579ffe94",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 78.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-nano-30b-a3b-fp8",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "931b8bb262d5296c731c9197",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 62.97,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "modelType": "open",
        "parametersBillions": 123.6,
        "contextWindow": null,
        "coveragePercent": 63.6
      }
    },
    {
      "id": "168ca6c8acb4b076963775f1",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 62.97,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "7708981b43f5759d3a94d3b2",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 90,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "5a07e5f41ed2c1e0badb87da",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 79.23,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "251e484357651e49d95493d5",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 18.26,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "1f88ca395ba9d5b1746145d9",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 84.85,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "dcc6f9f4a2a9986a14962821",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 83.73,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "3c96b98c56d5bf716080718f",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 53.73,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "06dca2aafb91c3efbfef02a9",
      "sourceId": "openevals-leaderboard-data",
      "model": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "nvidia",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 31,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "nvidia-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "fb957e7c96730eab4d3b55cb",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-120b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 34.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-120b",
        "modelType": "open",
        "parametersBillions": 120.4,
        "contextWindow": null,
        "coveragePercent": 36.4
      }
    },
    {
      "id": "393629cc93d48a24db623f97",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-120b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 34.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-120b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "c474181ecc1c73186ffc1223",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-120b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 67.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-120b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "c3065a58f297452a5168ca36",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-120b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 5.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-120b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "bff2ce9fdac24bc9748cc6ee",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-120b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 16.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-120b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "06eb61734477e94814c0b308",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-120b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 47.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-120b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "c41f733e8676911062b6a1e1",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-20b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 32.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-20b",
        "modelType": "open",
        "parametersBillions": 21.5,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "f7396af21b00b0dd657eb2a9",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-20b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 32.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-20b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "dae4b43c18c3bcc426e1745a",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-20b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 56.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-20b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "fbdf8e17c6bb037c1b3262c6",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-20b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 4.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-20b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "535ddfb6c55e83b09c65adf7",
      "sourceId": "openevals-leaderboard-data",
      "model": "openai/gpt-oss-20b",
      "organization": "openai",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 37.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openai-gpt-oss-20b",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "1acd9a0ccab34294d03e3c98",
      "sourceId": "openevals-leaderboard-data",
      "model": "openbmb/AgentCPM-Explore",
      "organization": "openbmb",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 19.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openbmb-agentcpm-explore",
        "modelType": "open",
        "parametersBillions": 4,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "11c2262dd73df9517f1ac8b3",
      "sourceId": "openevals-leaderboard-data",
      "model": "openbmb/AgentCPM-Explore",
      "organization": "openbmb",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 19.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openbmb-agentcpm-explore",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "59ce0ff68dcc78de632ded59",
      "sourceId": "openevals-leaderboard-data",
      "model": "openbmb/AgentCPM-Explore",
      "organization": "openbmb",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 19.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "openbmb-agentcpm-explore",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e66b3e0a456754215c3b65b2",
      "sourceId": "openevals-leaderboard-data",
      "model": "opendatalab/MinerU2.5-2509-1.2B",
      "organization": "opendatalab",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "opendatalab-mineru2.5-2509-1.2b",
        "modelType": "open",
        "parametersBillions": 1.2,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "7c39d05f494a7f10a6716c9d",
      "sourceId": "openevals-leaderboard-data",
      "model": "opendatalab/MinerU2.5-2509-1.2B",
      "organization": "opendatalab",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "opendatalab-mineru2.5-2509-1.2b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d40171df6f4e49590b7ae5e0",
      "sourceId": "openevals-leaderboard-data",
      "model": "opendatalab/MinerU2.5-2509-1.2B",
      "organization": "opendatalab",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "opendatalab-mineru2.5-2509-1.2b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "faeb8f070de787c0da5fc2ac",
      "sourceId": "openevals-leaderboard-data",
      "model": "PaddlePaddle/PaddleOCR-VL",
      "organization": "PaddlePaddle",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 80,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "paddlepaddle-paddleocr-vl",
        "modelType": "open",
        "parametersBillions": 1,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2ad3580a96c29e1467474e71",
      "sourceId": "openevals-leaderboard-data",
      "model": "PaddlePaddle/PaddleOCR-VL",
      "organization": "PaddlePaddle",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 80,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "paddlepaddle-paddleocr-vl",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ff47c349f3c366aae90b58e2",
      "sourceId": "openevals-leaderboard-data",
      "model": "PaddlePaddle/PaddleOCR-VL",
      "organization": "PaddlePaddle",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 80,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "paddlepaddle-paddleocr-vl",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "71d7492c222655a0d2dba99a",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen2-72B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 89.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen2-72b",
        "modelType": "open",
        "parametersBillions": 72.7,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0c112bf3dfba1ce3f5df924d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen2-72B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 89.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen2-72b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d0dca14d56bcd399487d5898",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen2-72B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 89.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen2-72b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "3a3a0d85477607d1fff8d49e",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen2-7B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 79.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen2-7b",
        "modelType": "open",
        "parametersBillions": 7.6,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "422e32693cc5ee610209e7a4",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen2-7B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 79.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen2-7b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ad6244058aac764377717c41",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen2-7B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 79.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen2-7b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "907fea346eb83737a3b556a1",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-235B-A22B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 84.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-235b-a22b-thinking-2507",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "9983551417d3c4a798b26e57",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-235B-A22B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 84.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-235b-a22b-thinking-2507",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "72ef96a975d1bcbc45438822",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-235B-A22B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 84.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-235b-a22b-thinking-2507",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "ec8f58d82cc2efdcc2881504",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-235B-A22B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 21.41,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-235b-a22b",
        "modelType": "open",
        "parametersBillions": 235.1,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d5fb7bc2f587e46e7844f219",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-235B-A22B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 21.41,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-235b-a22b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "366cd5daa1ed3fd78336c23e",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-235B-A22B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 21.41,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-235b-a22b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "de9766d924fa70180b1644b1",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-30B-A3B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.15,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-30b-a3b-thinking-2507",
        "modelType": "open",
        "parametersBillions": 30.5,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "16fdceb0c4180d476d0c5af2",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-30B-A3B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.15,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-30b-a3b-thinking-2507",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "4db4abb37b0bff36ce5d4fb0",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-30B-A3B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 87.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-30b-a3b-thinking-2507",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1fd37e81b3f4e1dd0b12af48",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-30B-A3B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 78.79,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-30b-a3b-thinking-2507",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "b46984085908ecdd065560f9",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Instruct-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 65.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-instruct-2507",
        "modelType": "open",
        "parametersBillions": 4,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "533742c39e3575c2469ff345",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Instruct-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 65.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-instruct-2507",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "81b6eecd628db581d0ed0d7f",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Instruct-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 62,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-instruct-2507",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "6b37a143887a04fe602b0655",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Instruct-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 69.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-instruct-2507",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "a652d176acd0c5166bc03e13",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 68.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-thinking-2507",
        "modelType": "open",
        "parametersBillions": 4,
        "contextWindow": null,
        "coveragePercent": 36.4
      }
    },
    {
      "id": "fe0af43a7c0292fee5073826",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 68.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-thinking-2507",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "008b01aca1cdc47986c4aa05",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 82.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-thinking-2507",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "ab3a1ca66d4693c9f09333ea",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 65.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-thinking-2507",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "1c78ebba90d0f0413e2fc212",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 53.03,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-thinking-2507",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "aeee37817115f3d6c7109a2a",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-4B-Thinking-2507",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 74,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-4b-thinking-2507",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "ea72d2733e254fc85d6f49e7",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 46.92,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
        "modelType": "open",
        "parametersBillions": 480.2,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "fc2d53b075bb67d22b5ad49b",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 46.92,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "9911621f263d706f5e3a2809",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals evasionBench",
      "category": "evasionBench",
      "score": 78.16,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "858f87c48ac66ec297beb04d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 38.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "d58b93045f558f0e9139fa2f",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-480B-A35B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 23.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-480b-a35b-instruct",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "ebdbcd173af7932b5fe7a3ea",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-Next",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 50.37,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-next",
        "modelType": "open",
        "parametersBillions": 79.7,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "723dd8c6aad5c4f11a30c780",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-Next",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 50.37,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-next",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "575b3f7c9cb0853963548f76",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-Next",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 44.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-next",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "6ec9d34759df9ebe2ffbee21",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-Next",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 70.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-next",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "4f078e0f247342910c7c741e",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Coder-Next",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 36.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-coder-next",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "551ca0d6a099558f1c5bf1d7",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Next-80B-A3B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 80.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-next-80b-a3b-instruct",
        "modelType": "open",
        "parametersBillions": 81.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "aac6c2d4c8063693c76dae7d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Next-80B-A3B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 80.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-next-80b-a3b-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "467006ca9a9e3dbfa6cae865",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3-Next-80B-A3B-Instruct",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 80.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3-next-80b-a3b-instruct",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "84882b198d8df50704b9fb7b",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-0.8B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 20.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-0.8b",
        "modelType": "open",
        "parametersBillions": 0.9,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "a198e67b91bfba9043f1df6d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-0.8B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 20.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-0.8b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "28799377000364718b7c89aa",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-0.8B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 11.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-0.8b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "5503c6d0e7f85c4e4b28f623",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-0.8B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 29.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-0.8b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "c0d1671f993367ca195ff740",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 64,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "modelType": "open",
        "parametersBillions": 125.1,
        "contextWindow": null,
        "coveragePercent": 45.5
      }
    },
    {
      "id": "cf34ac3a9b211a6b2b548fe2",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 64,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "4dd58b0e1d083c7d22743213",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 86.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "9635ed87e1432a035af8fde9",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 25.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "fc7613d6f9be52e79df50b52",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 86.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "ec19ef4c5ad5539bd33ca399",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 72,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "57fde0292db1fb413fac679c",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-122B-A10B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 49.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-122b-a10b",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "5e0f6ecf9500aa45b601ad88",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 68.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "modelType": "open",
        "parametersBillions": 27.8,
        "contextWindow": null,
        "coveragePercent": 63.6
      }
    },
    {
      "id": "e70cb7e8c53078f6c53ac8d1",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 68.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "fc80f5bbcd6b98082bad9378",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 90.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "c6b230965469e468fa6265bd",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 85.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "2ae3e90f6f3bd247e1dff3a5",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 24.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "9df6e954d2a2aa97e6a841d0",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 81.06,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "39453cecba75713a697b083d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 86.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "3ebf29016af5ffa6a656f736",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 72.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "c70d6df7e9f4429166c3dc1d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-27B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 41.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-27b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "2795e47e6f372ee2097411bc",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-2B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 55.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-2b",
        "modelType": "open",
        "parametersBillions": 2.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "04124aeb0a76b08d1fe1dc07",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-2B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 55.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-2b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "9978dc9b235f5fbd59934071",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-2B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 55.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-2b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "82b5096ebae1e7da900e8aa7",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 68.11,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "modelType": "open",
        "parametersBillions": 36,
        "contextWindow": null,
        "coveragePercent": 63.6
      }
    },
    {
      "id": "867b3125b360d1f24b4134d9",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 68.11,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "4b419b3aef428c823bfc4458",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 93.33,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "f851712637e09fe7b44ec857",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 84.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "5ee6a999354e6bda283af81d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 22.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "d829060a2fd342f27fc8a036",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 81.82,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "123f88a0e42bf56509f29f26",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 85.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "5ba5c811c0a295cedcf9c813",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 69.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "d146393a379585a40ada845c",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-35B-A3B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 40.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-35b-a3b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "00d881b2d48e85c42b6db083",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 73.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "modelType": "open",
        "parametersBillions": 403.4,
        "contextWindow": null,
        "coveragePercent": 63.6
      }
    },
    {
      "id": "a1dbb24c62fbffb6e42a347f",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 73.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "94421360ed458578e28fe0e7",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 93.33,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "054e44e11312484876310a2c",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 88.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "ca27b3cf3b5d7de3cb0569a9",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 28.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "e559c7daecb001a8700f669d",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 87.88,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "49637817536add6a6f90ebee",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 87.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "b03ec6c8656a37dfd4d247af",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 76.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "1b7e5c568fa9ecf4d4ccb391",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-397B-A17B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 52.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-397b-a17b",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "447a104a6195cee7f5df32df",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-4B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 77.65,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-4b",
        "modelType": "open",
        "parametersBillions": 4.7,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "5ee54e1993563dad46950a98",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-4B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 77.65,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-4b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "a9aba023602c87b865fe41d4",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-4B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 76.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-4b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "a26834e223f5aaa8cfc61c0c",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-4B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 79.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-4b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "f595313cee811873481d377f",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-9B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 81.98,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-9b",
        "modelType": "open",
        "parametersBillions": 9.7,
        "contextWindow": null,
        "coveragePercent": 36.4
      }
    },
    {
      "id": "a3a4f7312263c4c8953106ea",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-9B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 81.98,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-9b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "ee25a0827acd3e672e7185c6",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-9B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 92.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-9b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "aed39793c875a0b6dd560d01",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-9B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 81.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-9b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "e5956e89a5ea882236f2b9bb",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-9B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 71.21,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-9b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "e9613908ce82b0737cddde52",
      "sourceId": "openevals-leaderboard-data",
      "model": "Qwen/Qwen3.5-9B",
      "organization": "Qwen",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 82.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "qwen-qwen3.5-9b",
        "coveragePercent": 36.4
      }
    },
    {
      "id": "0e7ba4510686b8635ab14c4a",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 53.19,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "modelType": "open",
        "parametersBillions": 123.6,
        "contextWindow": null,
        "coveragePercent": 45.5
      }
    },
    {
      "id": "b0e1af502c57904a5041ac9c",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 53.19,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "1d443c1110efe1c7020d05ff",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 79.23,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "d0248bc067cbacc92932be19",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 18.26,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "30e1de5c03bb46e98f5b3c3e",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 83.73,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "c874f7211bae5e93dfde4942",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 53.73,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "6d7abcad60b80fac10b4d98f",
      "sourceId": "openevals-leaderboard-data",
      "model": "RedHatAI/NVIDIA-Nemotron-3-Super-120B-A12B-BF16",
      "organization": "RedHatAI",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 31,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "redhatai-nvidia-nemotron-3-super-120b-a12b-bf16",
        "coveragePercent": 45.5
      }
    },
    {
      "id": "c947b8068a02916e777e76c3",
      "sourceId": "openevals-leaderboard-data",
      "model": "rednote-hilab/dots.mocr",
      "organization": "rednote-hilab",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "rednote-hilab-dots.mocr",
        "modelType": "open",
        "parametersBillions": 3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "550225975eb2095ed1e331d8",
      "sourceId": "openevals-leaderboard-data",
      "model": "rednote-hilab/dots.mocr",
      "organization": "rednote-hilab",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "rednote-hilab-dots.mocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "2d08f2cdd1d82e077930a5ed",
      "sourceId": "openevals-leaderboard-data",
      "model": "rednote-hilab/dots.mocr",
      "organization": "rednote-hilab",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 83.9,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "rednote-hilab-dots.mocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0ccad47b39d119c58491dbd6",
      "sourceId": "openevals-leaderboard-data",
      "model": "rednote-hilab/dots.ocr",
      "organization": "rednote-hilab",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 79.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "rednote-hilab-dots.ocr",
        "modelType": "open",
        "parametersBillions": 3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d70eac2456280b7f7b5d8c5a",
      "sourceId": "openevals-leaderboard-data",
      "model": "rednote-hilab/dots.ocr",
      "organization": "rednote-hilab",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 79.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "rednote-hilab-dots.ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "fc1f340ce2acb3da3a3737f1",
      "sourceId": "openevals-leaderboard-data",
      "model": "rednote-hilab/dots.ocr",
      "organization": "rednote-hilab",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 79.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "rednote-hilab-dots.ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "57939e6306e6a7467086e351",
      "sourceId": "openevals-leaderboard-data",
      "model": "SnurfyAI/Sn-Logicer-0.8B",
      "organization": "SnurfyAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 50.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "snurfyai-sn-logicer-0.8b",
        "modelType": "open",
        "parametersBillions": 0.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "66b6e820e8db15024e4c032e",
      "sourceId": "openevals-leaderboard-data",
      "model": "SnurfyAI/Sn-Logicer-0.8B",
      "organization": "SnurfyAI",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 50.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "snurfyai-sn-logicer-0.8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "cbc9e4146ae5b91e144cc094",
      "sourceId": "openevals-leaderboard-data",
      "model": "SnurfyAI/Sn-Logicer-0.8B",
      "organization": "SnurfyAI",
      "license": "Unknown",
      "benchmark": "OpenEvals gsm8k",
      "category": "gsm8k",
      "score": 50.57,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "snurfyai-sn-logicer-0.8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "c7e0edd0438a9fd69b9158e7",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 71.35,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "modelType": "open",
        "parametersBillions": 199.4,
        "contextWindow": null,
        "coveragePercent": 63.6
      }
    },
    {
      "id": "35a5f6d3da805ef4c07bced2",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 71.35,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "1cd4bd91ce265c5f6f2af555",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 96.67,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "6f2aa224c763ce74aced98d9",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 83.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "40c0205152c72e7db88933fd",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 23.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "c2db3718dae2534bd4ea4ee1",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 86.36,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "3e321aa4810e50b4feb575a3",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 84.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "04232009fd4d1af1ab55e698",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 74.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "4835570ff9c4cc19e1907442",
      "sourceId": "openevals-leaderboard-data",
      "model": "stepfun-ai/Step-3.5-Flash",
      "organization": "stepfun-ai",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 51,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "stepfun-ai-step-3.5-flash",
        "coveragePercent": 63.6
      }
    },
    {
      "id": "fe766ae0041c57b6555e954d",
      "sourceId": "openevals-leaderboard-data",
      "model": "SWE-Lego/SWE-Lego-Qwen3-32B",
      "organization": "SWE-Lego",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 52.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "swe-lego-swe-lego-qwen3-32b",
        "modelType": "open",
        "parametersBillions": 0,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "756d8639e534a49b367ed005",
      "sourceId": "openevals-leaderboard-data",
      "model": "SWE-Lego/SWE-Lego-Qwen3-32B",
      "organization": "SWE-Lego",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 52.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "swe-lego-swe-lego-qwen3-32b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "b46a122b66dad12f0e6d67ac",
      "sourceId": "openevals-leaderboard-data",
      "model": "SWE-Lego/SWE-Lego-Qwen3-32B",
      "organization": "SWE-Lego",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 52.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "swe-lego-swe-lego-qwen3-32b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "33b9627fea11b606623b9df4",
      "sourceId": "openevals-leaderboard-data",
      "model": "SWE-Lego/SWE-Lego-Qwen3-8B",
      "organization": "SWE-Lego",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 42.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "swe-lego-swe-lego-qwen3-8b",
        "modelType": "open",
        "parametersBillions": 0,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "a7d3cd6cca7493052659c30d",
      "sourceId": "openevals-leaderboard-data",
      "model": "SWE-Lego/SWE-Lego-Qwen3-8B",
      "organization": "SWE-Lego",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 42.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "swe-lego-swe-lego-qwen3-8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "db36bd20ed850f8dd41dea55",
      "sourceId": "openevals-leaderboard-data",
      "model": "SWE-Lego/SWE-Lego-Qwen3-8B",
      "organization": "SWE-Lego",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 42.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "swe-lego-swe-lego-qwen3-8b",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "8880b9b1db9f9d45c96e737b",
      "sourceId": "openevals-leaderboard-data",
      "model": "tiiuae/Falcon-H1R-7B",
      "organization": "tiiuae",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 41.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "tiiuae-falcon-h1r-7b",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "59d4f43da1bc99ca9a3adfb3",
      "sourceId": "openevals-leaderboard-data",
      "model": "tiiuae/Falcon-H1R-7B",
      "organization": "tiiuae",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 41.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "tiiuae-falcon-h1r-7b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "6ef2bc7a4cabddf7f3d3bfd1",
      "sourceId": "openevals-leaderboard-data",
      "model": "tiiuae/Falcon-H1R-7B",
      "organization": "tiiuae",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 11.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "tiiuae-falcon-h1r-7b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "6762a78408034d9f03a6c640",
      "sourceId": "openevals-leaderboard-data",
      "model": "tiiuae/Falcon-H1R-7B",
      "organization": "tiiuae",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 72.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "tiiuae-falcon-h1r-7b",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "0c9ba0e169b0e85c406e2589",
      "sourceId": "openevals-leaderboard-data",
      "model": "TitanML/olmOCR-2-7B-1025-FP8",
      "organization": "TitanML",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "titanml-olmocr-2-7b-1025-fp8",
        "modelType": "open",
        "parametersBillions": 8.3,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "fc09fcc7e5f96fffece47a2c",
      "sourceId": "openevals-leaderboard-data",
      "model": "TitanML/olmOCR-2-7B-1025-FP8",
      "organization": "TitanML",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "titanml-olmocr-2-7b-1025-fp8",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "0ea655d13e441549e361feab",
      "sourceId": "openevals-leaderboard-data",
      "model": "TitanML/olmOCR-2-7B-1025-FP8",
      "organization": "TitanML",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 82.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "titanml-olmocr-2-7b-1025-fp8",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "de6ef05a78fe1752e57626ee",
      "sourceId": "openevals-leaderboard-data",
      "model": "XiaomiMiMo/MiMo-V2-Flash",
      "organization": "XiaomiMiMo",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 22.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "xiaomimimo-mimo-v2-flash",
        "modelType": "open",
        "parametersBillions": 309.8,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "d8465dffb107727c8ebfc803",
      "sourceId": "openevals-leaderboard-data",
      "model": "XiaomiMiMo/MiMo-V2-Flash",
      "organization": "XiaomiMiMo",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 22.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "xiaomimimo-mimo-v2-flash",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "30ac96c5eea0416f050c95f2",
      "sourceId": "openevals-leaderboard-data",
      "model": "XiaomiMiMo/MiMo-V2-Flash",
      "organization": "XiaomiMiMo",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 22.1,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "xiaomimimo-mimo-v2-flash",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "e275e55e473f47ed3ad49151",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.6",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 17.09,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.6",
        "modelType": "open",
        "parametersBillions": 356.8,
        "contextWindow": null,
        "coveragePercent": 18.2
      }
    },
    {
      "id": "91aff0f112e5cd2e86d70660",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.6",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 17.09,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.6",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "6d00a5e073e3a71a163dc74a",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.6",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals swePro",
      "category": "swePro",
      "score": 9.67,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.6",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "1aa7e6dba1eee7274301ee78",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.6",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 24.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.6",
        "coveragePercent": 18.2
      }
    },
    {
      "id": "50719299e6f63a145c1bb908",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7-Flash",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 49.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7-flash",
        "modelType": "open",
        "parametersBillions": 31.2,
        "contextWindow": null,
        "coveragePercent": 27.3
      }
    },
    {
      "id": "ead41649ea31af8a832dd623",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7-Flash",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 49.6,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7-flash",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "e818b498d9e58f6e0083f236",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7-Flash",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7-flash",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "f9ca13016d3059eb1ae52aec",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7-Flash",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 14.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7-flash",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "cc2cdcad6bfad89ecd7efd00",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7-Flash",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 59.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7-flash",
        "coveragePercent": 27.3
      }
    },
    {
      "id": "1221e02d5f4024926c792818",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 64.15,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "modelType": "open",
        "parametersBillions": 358.3,
        "contextWindow": null,
        "coveragePercent": 54.5
      }
    },
    {
      "id": "8d5483b5178146e40ac1ab27",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 64.15,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "04878b04b79168fa9a040ef5",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals evasionBench",
      "category": "evasionBench",
      "score": 82.91,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "d35341aec0aca5f0117e948c",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 85.7,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "5e9c8530a71e57aa90f32189",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 24.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "57f2e382f7c56650600611d4",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals mmluPro",
      "category": "mmluPro",
      "score": 84.3,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "353b19d56424eac51aff3474",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 73.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "827763a25f5d1473c52fee9d",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-4.7",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 33.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-4.7",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "346c7773e03d270caab953fd",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 70.65,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "modelType": "open",
        "parametersBillions": 753.9,
        "contextWindow": null,
        "coveragePercent": 54.5
      }
    },
    {
      "id": "032924ba487364f973429bf8",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 70.65,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "5f3ac02fc31ad19f93dff88c",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aime2026",
      "category": "aime2026",
      "score": 95.83,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "e79589a43452414958a04f97",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals gpqa",
      "category": "gpqa",
      "score": 86,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "911eef5f6da38f06986b7ade",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals hle",
      "category": "hle",
      "score": 30.5,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "6485ba375cd3beaa43584d3c",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals hmmt2026",
      "category": "hmmt2026",
      "score": 86.36,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "3d52009e67d61d6dd04338cc",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals sweVerified",
      "category": "sweVerified",
      "score": 72.8,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "ad70e1e846c6eabc67e9b01b",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-5",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals terminalBench",
      "category": "terminalBench",
      "score": 52.4,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-5",
        "coveragePercent": 54.5
      }
    },
    {
      "id": "23a3b6d953a5e8a1aec2ae2a",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-OCR",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate_score",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-ocr",
        "modelType": "open",
        "parametersBillions": null,
        "contextWindow": null,
        "coveragePercent": 9.1
      }
    },
    {
      "id": "24ad04c03f12e4fa8106b722",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-OCR",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals aggregate",
      "category": "aggregate",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-ocr",
        "coveragePercent": 9.1
      }
    },
    {
      "id": "5a50bf36601d079ddfba3ed8",
      "sourceId": "openevals-leaderboard-data",
      "model": "zai-org/GLM-OCR",
      "organization": "zai-org",
      "license": "Unknown",
      "benchmark": "OpenEvals olmOcr",
      "category": "olmOcr",
      "score": 75.2,
      "unit": "score",
      "provenance": "external-dataset",
      "verification": "third-party",
      "metadata": {
        "modelId": "zai-org-glm-ocr",
        "coveragePercent": 9.1
      }
    }
  ],
  "attributedSources": [
    {
      "id": "alibayram-tr-mmlu",
      "source": "alibayram/yapay_zeka_turkce_mmlu_liderlik_tablosu",
      "sourceTitle": "Alibayram · Turkish MMLU Leaderboard",
      "sourceUrl": "https://huggingface.co/spaces/alibayram/turkish_mmlu_leaderboard",
      "datasetUrl": "https://huggingface.co/datasets/alibayram/yapay_zeka_turkce_mmlu_liderlik_tablosu",
      "license": "CC-BY-NC-4.0",
      "attribution": "Bayram, M. (2025). Yapay Zeka Türkçe MMLU Liderlik Tablosu. Hugging Face. DOI: 10.57967/hf/3127",
      "caveat": "CC-BY-NC-4.0 forbids commercial reuse. Total time field is Bayram's own measurement; GPU is not identified upstream.",
      "dimension": "tr-mmlu",
      "fullSampleCount": 6200,
      "lastFetched": "2026-06-08T09:56:55.228Z",
      "lastUpstreamModified": "2025-07-29T21:50:57.000Z",
      "rowCount": 66,
      "rows": [
        {
          "id": "4e0f59b2ae4ebfa887a7e8a7",
          "modelName": "gpt-4o",
          "format": "API-Accessed",
          "family": "GPT",
          "parameterSize": "Unknown",
          "quantization": "No Quantization",
          "correctAnswers": 5260,
          "scorePercent": 84.84,
          "totalSeconds": 5021.924,
          "modelLink": null
        },
        {
          "id": "6b4bfa985dc9df3535d1d5c5",
          "modelName": "claude-3-5-sonnet-20240620",
          "format": "API-Accessed",
          "family": "Sonnet",
          "parameterSize": "Unknown",
          "quantization": "No Quantization",
          "correctAnswers": 5233,
          "scorePercent": 84.4,
          "totalSeconds": 7379.819,
          "modelLink": null
        },
        {
          "id": "ecb850cd720665cd9478990d",
          "modelName": "llama3.3:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "70.6B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4924,
          "scorePercent": 79.42,
          "totalSeconds": 13355.846,
          "modelLink": "https://ollama.com/llama3.3"
        },
        {
          "id": "3d423894133f3933d9a4accf",
          "modelName": "gemini-1.5-pro",
          "format": "API-Accessed",
          "family": "Gemini",
          "parameterSize": "Unknown",
          "quantization": "No Quantization",
          "correctAnswers": 4758,
          "scorePercent": 76.74,
          "totalSeconds": 4985.786,
          "modelLink": null
        },
        {
          "id": "c2a6315150be2d897dd0c6c4",
          "modelName": "qwen3:32b",
          "format": "gguf",
          "family": "qwen3",
          "parameterSize": "32.8B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4711,
          "scorePercent": 75.98,
          "totalSeconds": 3591.989,
          "modelLink": "https://ollama.com/qwen3"
        },
        {
          "id": "41d1083fe9ae084cd0d79991",
          "modelName": "gemma3:27b",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "27.4B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4654,
          "scorePercent": 75.06,
          "totalSeconds": 5783.192,
          "modelLink": "https://ollama.com/gemma3"
        },
        {
          "id": "39827bee6b5c3685586926a3",
          "modelName": "qwen3:30b",
          "format": "gguf",
          "family": "qwen3moe",
          "parameterSize": "30.5B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4604,
          "scorePercent": 74.26,
          "totalSeconds": 4445.075,
          "modelLink": "https://ollama.com/qwen3"
        },
        {
          "id": "09d6890ad13b9500d9c89783",
          "modelName": "alibayram/medgemma:27b",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "27.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4599,
          "scorePercent": 74.18,
          "totalSeconds": 14597.442,
          "modelLink": "https://ollama.com/alibayram/medgemma"
        },
        {
          "id": "887a293a48499ec2f443572c",
          "modelName": "alibayram/emre-gemma3-27b-tr-reasoning:latest",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "27.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4539,
          "scorePercent": 73.21,
          "totalSeconds": 11743.768,
          "modelLink": "https://ollama.com/alibayram/emre-gemma3-27b-tr-reasoning"
        },
        {
          "id": "3e75fd46997c70e5ecadab50",
          "modelName": "gemma2:27b",
          "format": "gguf",
          "family": "gemma2",
          "parameterSize": "27.2B",
          "quantization": "Q4_0",
          "correctAnswers": 4470,
          "scorePercent": 72.1,
          "totalSeconds": 5506.779,
          "modelLink": "https://ollama.com/gemma2"
        },
        {
          "id": "1b371f70359b70dbbf6b0986",
          "modelName": "qwen3:14b",
          "format": "gguf",
          "family": "qwen3",
          "parameterSize": "14.8B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4442,
          "scorePercent": 71.65,
          "totalSeconds": 8465.075,
          "modelLink": "https://ollama.com/qwen3"
        },
        {
          "id": "97956c0fed5e834baef4d686",
          "modelName": "alibayram/doktor-gemma3:12b",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "11.8B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4407,
          "scorePercent": 71.08,
          "totalSeconds": 6372.745,
          "modelLink": "https://ollama.com/alibayram/doktor-gemma3"
        },
        {
          "id": "314708e149c2f736be9bb5f6",
          "modelName": "gemma3:12b",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "12.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4386,
          "scorePercent": 70.74000000000001,
          "totalSeconds": 2656.275,
          "modelLink": "https://ollama.com/gemma3"
        },
        {
          "id": "bec4d54f540b1c1280624366",
          "modelName": "aya-expanse:32b",
          "format": "gguf",
          "family": "command-r",
          "parameterSize": "32.3B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4381,
          "scorePercent": 70.66,
          "totalSeconds": 14526.999,
          "modelLink": "https://ollama.com/aya-expanse"
        },
        {
          "id": "472a36bf4b1e15025260e079",
          "modelName": "llama3.1:70b",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "70.6B",
          "quantization": "Q4_0",
          "correctAnswers": 4366,
          "scorePercent": 70.42,
          "totalSeconds": 11349.817,
          "modelLink": "https://ollama.com/llama3.1"
        },
        {
          "id": "ad98fffc726822a868864c04",
          "modelName": "alibayram/turkish-gemma-9b-v0.1:latest",
          "format": "gguf",
          "family": "gemma2",
          "parameterSize": "9.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4361,
          "scorePercent": 70.34,
          "totalSeconds": 2137.875,
          "modelLink": "https://ollama.com/alibayram/turkish-gemma-9b-v0.1"
        },
        {
          "id": "a614aff586d04805f536242b",
          "modelName": "gemma2:latest",
          "format": "gguf",
          "family": "gemma2",
          "parameterSize": "9.2B",
          "quantization": "Q4_0",
          "correctAnswers": 4294,
          "scorePercent": 69.26,
          "totalSeconds": 2276.631,
          "modelLink": "https://ollama.com/gemma2"
        },
        {
          "id": "e1ea2ad229596741c9b21820",
          "modelName": "alibayram/metin-gemma2-9b-it-tr-dpo-v1:latest",
          "format": "gguf",
          "family": "gemma2",
          "parameterSize": "9.2B",
          "quantization": "Q4_0",
          "correctAnswers": 4288,
          "scorePercent": 69.16,
          "totalSeconds": 2214.452,
          "modelLink": "https://ollama.com/alibayram/metin-gemma2-9b-it-tr-dpo-v1"
        },
        {
          "id": "a0bf33d597926a812a425185",
          "modelName": "mistral-small3.2:24b",
          "format": "gguf",
          "family": "mistral3",
          "parameterSize": "24.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4239,
          "scorePercent": 68.37,
          "totalSeconds": 12448.755,
          "modelLink": "https://ollama.com/mistral-small3.2"
        },
        {
          "id": "264873993e212025765de3b6",
          "modelName": "qwen3:latest",
          "format": "gguf",
          "family": "qwen3",
          "parameterSize": "8.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4189,
          "scorePercent": 67.56,
          "totalSeconds": 1920.942,
          "modelLink": "https://ollama.com/qwen3"
        },
        {
          "id": "618834d4a9fd60c68d386173",
          "modelName": "mistral-small:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "23.6B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4152,
          "scorePercent": 66.97,
          "totalSeconds": 7347.536,
          "modelLink": "https://ollama.com/mistral-small"
        },
        {
          "id": "06e1ecfb83b80926445c3a7c",
          "modelName": "phi4:latest",
          "format": "gguf",
          "family": "phi3",
          "parameterSize": "14.7B",
          "quantization": "Q4_K_M",
          "correctAnswers": 4062,
          "scorePercent": 65.52,
          "totalSeconds": 4067.885,
          "modelLink": "https://ollama.com/phi4"
        },
        {
          "id": "3b46237bb8c32a173e91f10f",
          "modelName": "gemma3n:e4b",
          "format": "gguf",
          "family": "gemma3n",
          "parameterSize": "6.9B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3948,
          "scorePercent": 63.68,
          "totalSeconds": 4304.718,
          "modelLink": "https://ollama.com/gemma3n"
        },
        {
          "id": "e9976c6d07dc93bdb4fe8593",
          "modelName": "alibayram/gemma3n:latest",
          "format": "gguf",
          "family": "gemma3n",
          "parameterSize": "6.9B",
          "quantization": "Q8_0",
          "correctAnswers": 3933,
          "scorePercent": 63.44,
          "totalSeconds": 3811.102,
          "modelLink": "https://ollama.com/alibayram/gemma3n"
        },
        {
          "id": "ddd2de73e6d7390d0518aa94",
          "modelName": "vanilj/Phi-4:latest",
          "format": "gguf",
          "family": "phi3",
          "parameterSize": "14.7B",
          "quantization": "unknown",
          "correctAnswers": 3881,
          "scorePercent": 62.6,
          "totalSeconds": 4857.518,
          "modelLink": "https://ollama.com/vanilj/Phi-4"
        },
        {
          "id": "0983ab9cfcd6d95b34dfe7e0",
          "modelName": "aya-expanse:latest",
          "format": "gguf",
          "family": "command-r",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3848,
          "scorePercent": 62.06,
          "totalSeconds": 1725.916,
          "modelLink": "https://ollama.com/aya-expanse"
        },
        {
          "id": "7f162e8fd371210b044a5058",
          "modelName": "qwen2.5:latest",
          "format": "gguf",
          "family": "qwen2",
          "parameterSize": "7.6B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3824,
          "scorePercent": 61.68,
          "totalSeconds": 1808.736,
          "modelLink": "https://ollama.com/qwen2.5"
        },
        {
          "id": "31efaf36ea8010ebc3958514",
          "modelName": "alibayram/medgemma:latest",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "3.9B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3794,
          "scorePercent": 61.19,
          "totalSeconds": 2544.002,
          "modelLink": "https://ollama.com/alibayram/medgemma"
        },
        {
          "id": "64beb1c75deeb119a1430d5d",
          "modelName": "alibayram/Qwen3-30B-A3B-Instruct-2507:latest",
          "format": "gguf",
          "family": "qwen3moe",
          "parameterSize": "30.5B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3772,
          "scorePercent": 60.84,
          "totalSeconds": 5867.153,
          "modelLink": "https://ollama.com/alibayram/Qwen3-30B-A3B-Instruct-2507"
        },
        {
          "id": "79c3fc49988348de16fabe79",
          "modelName": "gemma3n:e2b",
          "format": "gguf",
          "family": "gemma3n",
          "parameterSize": "4.5B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3717,
          "scorePercent": 59.95,
          "totalSeconds": 3025.43,
          "modelLink": "https://ollama.com/gemma3n"
        },
        {
          "id": "808f51227155b8c5845fb9a9",
          "modelName": "aya:35b",
          "format": "gguf",
          "family": "command-r",
          "parameterSize": "35.0B",
          "quantization": "F16",
          "correctAnswers": 3716,
          "scorePercent": 59.94,
          "totalSeconds": 5376.47,
          "modelLink": "https://ollama.com/aya"
        },
        {
          "id": "981ff795e736b4e1de2edece",
          "modelName": "Defne-llama3.1-8B:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3549,
          "scorePercent": 57.24,
          "totalSeconds": 1778.209,
          "modelLink": "https://ollama.com/Defne-llama3.1-8B"
        },
        {
          "id": "da19e126211478a688f9f3cc",
          "modelName": "qwen2:latest",
          "format": "gguf",
          "family": "qwen2",
          "parameterSize": "7.6B",
          "quantization": "Q4_0",
          "correctAnswers": 3461,
          "scorePercent": 55.82,
          "totalSeconds": 1868.449,
          "modelLink": "https://ollama.com/qwen2"
        },
        {
          "id": "a3e25e467cedc64650b47545",
          "modelName": "ytu-ce-cosmos-Turkish-Llama-8b-DPO-v0-1:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3406,
          "scorePercent": 54.94,
          "totalSeconds": 1857.952,
          "modelLink": "https://ollama.com/ytu-ce-cosmos-Turkish-Llama-8b-DPO-v0-1"
        },
        {
          "id": "2f1fc0aa8b2e7293ad421c06",
          "modelName": "deepseek-r1:8b",
          "format": "gguf",
          "family": "qwen3",
          "parameterSize": "8.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3402,
          "scorePercent": 54.87,
          "totalSeconds": 2169.334,
          "modelLink": "https://ollama.com/deepseek-r1"
        },
        {
          "id": "7d093f295b0b4be7303d67b8",
          "modelName": "alibayram/doktorllama3-cosmos:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_0",
          "correctAnswers": 3295,
          "scorePercent": 53.15,
          "totalSeconds": 1709.051,
          "modelLink": "https://ollama.com/alibayram/doktorllama3-cosmos"
        },
        {
          "id": "89b1b0394d8aebf00e801a24",
          "modelName": "alibayram/doktorllama3:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_0",
          "correctAnswers": 3290,
          "scorePercent": 53.059999999999995,
          "totalSeconds": 1602.997,
          "modelLink": "https://ollama.com/alibayram/doktorllama3"
        },
        {
          "id": "3455a74004a109af176fdef0",
          "modelName": "Metin-LLaMA-3-8B-Instruct-TR-DPO:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3248,
          "scorePercent": 52.39,
          "totalSeconds": 1770.83,
          "modelLink": "https://ollama.com/Metin-LLaMA-3-8B-Instruct-TR-DPO"
        },
        {
          "id": "d8f639c84f0faf1aa4a808b6",
          "modelName": "llama3:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_0",
          "correctAnswers": 3238,
          "scorePercent": 52.23,
          "totalSeconds": 1665.703,
          "modelLink": "https://ollama.com/llama3"
        },
        {
          "id": "c2b199cb0a4aca36ee475786",
          "modelName": "alibayram/erurollm-9b-instruct:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "9.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3180,
          "scorePercent": 51.29,
          "totalSeconds": 2114.299,
          "modelLink": "https://ollama.com/alibayram/erurollm-9b-instruct"
        },
        {
          "id": "916917520b534c0a3860fae9",
          "modelName": "deepseek-r1:14b",
          "format": "gguf",
          "family": "qwen2",
          "parameterSize": "14.8B",
          "quantization": "Q4_K_M",
          "correctAnswers": 3068,
          "scorePercent": 49.48,
          "totalSeconds": 10822.833,
          "modelLink": "https://ollama.com/deepseek-r1"
        },
        {
          "id": "54ea27aa52aee0b7a4aefa72",
          "modelName": "gemma2:2b",
          "format": "gguf",
          "family": "gemma2",
          "parameterSize": "2.6B",
          "quantization": "Q4_0",
          "correctAnswers": 2999,
          "scorePercent": 48.37,
          "totalSeconds": 1103.659,
          "modelLink": "https://ollama.com/gemma2"
        },
        {
          "id": "fef2cf0915f2547717969f13",
          "modelName": "mistral-nemo:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "12.2B",
          "quantization": "Q4_0",
          "correctAnswers": 2907,
          "scorePercent": 46.89,
          "totalSeconds": 2421.859,
          "modelLink": "https://ollama.com/mistral-nemo"
        },
        {
          "id": "5791a7af2f1ae7b4b2f0d406",
          "modelName": "llama3.2:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "3.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 2787,
          "scorePercent": 44.95,
          "totalSeconds": 1008.758,
          "modelLink": "https://ollama.com/llama3.2"
        },
        {
          "id": "bb3b3bf9ac600588c1e944b2",
          "modelName": "gemma3:1b",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "999.89M",
          "quantization": "Q4_K_M",
          "correctAnswers": 2650,
          "scorePercent": 42.74,
          "totalSeconds": 1121.473,
          "modelLink": "https://ollama.com/gemma3"
        },
        {
          "id": "4d4e062e884e1e66ee149f7f",
          "modelName": "gemma3:4b",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "4.3B",
          "quantization": "Q4_K_M",
          "correctAnswers": 2650,
          "scorePercent": 42.74,
          "totalSeconds": 1128.676,
          "modelLink": "https://ollama.com/gemma3"
        },
        {
          "id": "00819f038723080b65a202e3",
          "modelName": "nemotron-mini:latest",
          "format": "gguf",
          "family": "nemotron",
          "parameterSize": "4.2B",
          "quantization": "Q4_K_M",
          "correctAnswers": 2320,
          "scorePercent": 37.42,
          "totalSeconds": 1399.608,
          "modelLink": "https://ollama.com/nemotron-mini"
        },
        {
          "id": "1c8277be9ecb86d7d2201c6b",
          "modelName": "llama3.1:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_0",
          "correctAnswers": 2177,
          "scorePercent": 35.11,
          "totalSeconds": 2354.278,
          "modelLink": "https://ollama.com/llama3.1"
        },
        {
          "id": "47bd2d3515a84f3ddb05a42a",
          "modelName": "openchat:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "7B",
          "quantization": "Q4_0",
          "correctAnswers": 2102,
          "scorePercent": 33.9,
          "totalSeconds": 2856.109,
          "modelLink": "https://ollama.com/openchat"
        },
        {
          "id": "511fcaf24291f5f671bc11a7",
          "modelName": "mistral:7b",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "7.2B",
          "quantization": "Q4_0",
          "correctAnswers": 2029,
          "scorePercent": 32.73,
          "totalSeconds": 8602.043,
          "modelLink": "https://ollama.com/mistral"
        },
        {
          "id": "16dae350ae0bc2ee8b1cbcda",
          "modelName": "phi3.5:latest",
          "format": "gguf",
          "family": "phi3",
          "parameterSize": "3.8B",
          "quantization": "Q4_0",
          "correctAnswers": 1821,
          "scorePercent": 29.37,
          "totalSeconds": 3244.336,
          "modelLink": "https://ollama.com/phi3.5"
        },
        {
          "id": "4778ade0e46eed104c60305e",
          "modelName": "cere-llama-3-8b-tr:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1710,
          "scorePercent": 27.58,
          "totalSeconds": 4299.565,
          "modelLink": "https://ollama.com/cere-llama-3-8b-tr"
        },
        {
          "id": "da7bb44e36bd5b42aa8bdae6",
          "modelName": "Trendyol-LLM-8b-chat-v2.0:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1710,
          "scorePercent": 27.58,
          "totalSeconds": 4457.242,
          "modelLink": "https://ollama.com/Trendyol-LLM-8b-chat-v2.0"
        },
        {
          "id": "0250f3cc6a7f1dc1fdccd2a9",
          "modelName": "Kocdigital-LLM-8B:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1703,
          "scorePercent": 27.47,
          "totalSeconds": 2867.119,
          "modelLink": "https://ollama.com/Kocdigital-LLM-8B"
        },
        {
          "id": "153e35b763451fb99571e344",
          "modelName": "zephyr:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "7B",
          "quantization": "Q4_0",
          "correctAnswers": 1693,
          "scorePercent": 27.31,
          "totalSeconds": 6041.852,
          "modelLink": "https://ollama.com/zephyr"
        },
        {
          "id": "cb9e3886cfa9f2ee4389f681",
          "modelName": "ahmets/gemma3-4b-finetuned:latest",
          "format": "gguf",
          "family": "gemma3",
          "parameterSize": "3.9B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1498,
          "scorePercent": 24.16,
          "totalSeconds": 3856.736,
          "modelLink": "https://ollama.com/ahmets/gemma3-4b-finetuned"
        },
        {
          "id": "58795afbfa6065b7da343575",
          "modelName": "CBDDO-LLM-8B-Instruct-v1:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1476,
          "scorePercent": 23.81,
          "totalSeconds": 2653.279,
          "modelLink": "https://ollama.com/CBDDO-LLM-8B-Instruct-v1"
        },
        {
          "id": "cf1e606378c9f5df86b782f0",
          "modelName": "phi3:latest",
          "format": "gguf",
          "family": "phi3",
          "parameterSize": "3.8B",
          "quantization": "Q4_0",
          "correctAnswers": 1419,
          "scorePercent": 22.89,
          "totalSeconds": 3847.113,
          "modelLink": "https://ollama.com/phi3"
        },
        {
          "id": "65765c540b7b591792f6b1af",
          "modelName": "qwen3:0.6b",
          "format": "gguf",
          "family": "qwen3",
          "parameterSize": "751.63M",
          "quantization": "Q4_K_M",
          "correctAnswers": 1342,
          "scorePercent": 21.65,
          "totalSeconds": 1610.571,
          "modelLink": "https://ollama.com/qwen3"
        },
        {
          "id": "753c23871b20b6b2186f0d75",
          "modelName": "qwen2.5:0.5b",
          "format": "gguf",
          "family": "qwen2",
          "parameterSize": "494.03M",
          "quantization": "Q4_K_M",
          "correctAnswers": 1316,
          "scorePercent": 21.23,
          "totalSeconds": 2446.218,
          "modelLink": "https://ollama.com/qwen2.5"
        },
        {
          "id": "0f7290403b8a4cfd3db2eb6d",
          "modelName": "Turkcell-LLM-7b-v1:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "7.4B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1209,
          "scorePercent": 19.5,
          "totalSeconds": 3175.645,
          "modelLink": "https://ollama.com/Turkcell-LLM-7b-v1"
        },
        {
          "id": "3c6db78dcb33dc1188ea05c5",
          "modelName": "tinyllama:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "1B",
          "quantization": "Q4_0",
          "correctAnswers": 1205,
          "scorePercent": 19.44,
          "totalSeconds": 2058.766,
          "modelLink": "https://ollama.com/tinyllama"
        },
        {
          "id": "be72b41d22b2b6e3ea0abfbd",
          "modelName": "Doktor-Llama-3-8b:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "6.8B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1192,
          "scorePercent": 19.23,
          "totalSeconds": 6325.277,
          "modelLink": "https://ollama.com/Doktor-Llama-3-8b"
        },
        {
          "id": "0b7bc900b58a9755aae9395a",
          "modelName": "llama-3.1-openhermes-tr:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1166,
          "scorePercent": 18.81,
          "totalSeconds": 5749.821,
          "modelLink": "https://ollama.com/llama-3.1-openhermes-tr"
        },
        {
          "id": "bf5804bbce90527d27cba24f",
          "modelName": "Morfoz-LLM-8b-v1.0:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1166,
          "scorePercent": 18.81,
          "totalSeconds": 5750.086,
          "modelLink": "https://ollama.com/Morfoz-LLM-8b-v1.0"
        },
        {
          "id": "c7a56cadeaa47609a2a2a458",
          "modelName": "NVIDIA-Llama3-ChatQA-1.5-8B:latest",
          "format": "gguf",
          "family": "llama",
          "parameterSize": "8.0B",
          "quantization": "Q4_K_M",
          "correctAnswers": 1166,
          "scorePercent": 18.81,
          "totalSeconds": 5822.83,
          "modelLink": "https://ollama.com/NVIDIA-Llama3-ChatQA-1.5-8B"
        }
      ],
      "contentHash": "f12fcb4d358d317ef6393bf938d06901856e0db5f90f9a2f8c663174c2371fb5"
    }
  ]
}
