{
  "schema": "builderwars.eval-source-extract.v1",
  "id": "livecodebench",
  "sourceUrl": "https://livecodebench.github.io/performances_generation.json",
  "sourceSha256": "17f9a1d69e3f6290fc8b967a4dd13fbb46e34dd05716fdee793780a1cfadd0c1",
  "capturedAt": "2026-10-07T07:01:28Z",
  "extraction": "Retained reported score columns; not complete source page or execution evidence",
  "rows": [
    {
      "name": "O4-Mini (High)",
      "score": 80.2,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 1,
      "sourceRowId": "8"
    },
    {
      "name": "O3 (High)",
      "score": 75.8,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 2,
      "sourceRowId": "11"
    },
    {
      "name": "O4-Mini (Medium)",
      "score": 74.2,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 3,
      "sourceRowId": "9"
    },
    {
      "name": "Gemini-2.5-Pro-06-05",
      "score": 73.6,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 4,
      "sourceRowId": "18"
    },
    {
      "name": "DeepSeek-R1-0528",
      "score": 73.1,
      "detail": "454 problems · source eligibility date 2024-06-30 (unverified release date)",
      "date": null,
      "rank": 5,
      "sourceRowId": "23"
    },
    {
      "name": "Gemini-2.5-Pro-05-06",
      "score": 71.8,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 6,
      "sourceRowId": "19"
    },
    {
      "name": "EXAONE-4.0-32B",
      "score": 70.0,
      "detail": "454 problems · source eligibility date 2024-04-01 (unverified release date)",
      "date": null,
      "rank": 7,
      "sourceRowId": "28"
    },
    {
      "name": "OpenReasoning-Nemotron-32B",
      "score": 69.8,
      "detail": "454 problems · source eligibility date 2024-04-01 (unverified release date)",
      "date": null,
      "rank": 8,
      "sourceRowId": "26"
    },
    {
      "name": "O3-Mini-2025-01-31 (High)",
      "score": 67.4,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 9,
      "sourceRowId": "7"
    },
    {
      "name": "OpenCodeReasoning-Nemotron-1.1-32B",
      "score": 66.8,
      "detail": "454 problems · source eligibility date 2024-04-01 (unverified release date)",
      "date": null,
      "rank": 10,
      "sourceRowId": "25"
    },
    {
      "name": "Grok-3-Mini (High)",
      "score": 66.7,
      "detail": "454 problems · source eligibility date 2024-03-01 (unverified release date)",
      "date": null,
      "rank": 11,
      "sourceRowId": "24"
    },
    {
      "name": "O4-Mini (Low)",
      "score": 65.9,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 12,
      "sourceRowId": "10"
    },
    {
      "name": "Qwen3-235B-A22B",
      "score": 65.9,
      "detail": "454 problems · source eligibility date 2024-06-30 (unverified release date)",
      "date": null,
      "rank": 12,
      "sourceRowId": "22"
    },
    {
      "name": "XBai-o4-medium",
      "score": 65.0,
      "detail": "454 problems · source eligibility date 2024-04-01 (unverified release date)",
      "date": null,
      "rank": 14,
      "sourceRowId": "27"
    },
    {
      "name": "O3-Mini-2025-01-31 (Med)",
      "score": 63.0,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 15,
      "sourceRowId": "6"
    },
    {
      "name": "Gemini-2.5-Flash-05-20",
      "score": 61.9,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 16,
      "sourceRowId": "21"
    },
    {
      "name": "Gemini-2.5-Flash-04-17",
      "score": 60.6,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 17,
      "sourceRowId": "20"
    },
    {
      "name": "O3-Mini-2025-01-31 (Low)",
      "score": 57.0,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 18,
      "sourceRowId": "5"
    },
    {
      "name": "Claude-Opus-4 (Thinking)",
      "score": 56.6,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 19,
      "sourceRowId": "15"
    },
    {
      "name": "Claude-Sonnet-4 (Thinking)",
      "score": 55.9,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 20,
      "sourceRowId": "14"
    },
    {
      "name": "Claude-Sonnet-4",
      "score": 47.1,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 21,
      "sourceRowId": "17"
    },
    {
      "name": "Claude-Opus-4",
      "score": 46.9,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 22,
      "sourceRowId": "16"
    },
    {
      "name": "Claude-3.5-Sonnet-20241022",
      "score": 36.4,
      "detail": "454 problems · source eligibility date 2024-03-31 (unverified release date)",
      "date": null,
      "rank": 23,
      "sourceRowId": "12"
    },
    {
      "name": "GPT-4O-2024-08-06",
      "score": 29.5,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 24,
      "sourceRowId": "3"
    },
    {
      "name": "GPT-4-Turbo-2024-04-09",
      "score": 28.7,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 25,
      "sourceRowId": "2"
    },
    {
      "name": "GPT-4O-mini-2024-07-18",
      "score": 27.5,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 26,
      "sourceRowId": "4"
    },
    {
      "name": "DeepSeek-V3",
      "score": 27.2,
      "detail": "454 problems · source eligibility date 2024-06-30 (unverified release date)",
      "date": null,
      "rank": 27,
      "sourceRowId": "1"
    },
    {
      "name": "Claude-3-Haiku",
      "score": 20.2,
      "detail": "454 problems · source eligibility date 2023-04-30 (unverified release date)",
      "date": null,
      "rank": 28,
      "sourceRowId": "13"
    }
  ]
}
