{
  "url": "https://www.aibattle.space/rankings/eval-gdpval-gdpval-aa-v2-leaderboard",
  "dataset": "GDPval-AA v2 Leaderboard",
  "family": "tab::eval-gdpval",
  "familyLabel": "eval gdpval",
  "sourceRowCount": 20,
  "window": 20,
  "metricKeys": [
    "gdpvalAaElo_lower",
    "gdpvalAaElo_mid",
    "gdpvalAaElo_upper"
  ],
  "rebuilt": "2026-09-19",
  "stats": {
    "median": 1646.365,
    "mean": 1634.548,
    "min": 1476.96,
    "max": 1763.64,
    "spread": 286.68000000000006,
    "gapFirstToSecond": 18.350000000000136,
    "gapFirstToSecondPercent": 1.05,
    "creators": 8
  },
  "entries": [
    {
      "rank": 1,
      "name": "Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)",
      "creator": "Anthropic",
      "slug": "claude-fable-5-1",
      "detailsUrl": "/models/claude-fable-5-1",
      "value": 1763.64
    },
    {
      "rank": 2,
      "name": "Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)",
      "creator": "Anthropic",
      "slug": "claude-fable-5-1-xhigh",
      "detailsUrl": "/models/claude-fable-5-1-xhigh",
      "value": 1745.29
    },
    {
      "rank": 3,
      "name": "Claude Opus 5 (Adaptive Reasoning, Max Effort)",
      "creator": "Anthropic",
      "slug": "claude-opus-5",
      "detailsUrl": "/models/claude-opus-5",
      "value": 1735.09
    },
    {
      "rank": 4,
      "name": "Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)",
      "creator": "Anthropic",
      "slug": "claude-opus-5-xhigh",
      "detailsUrl": "/models/claude-opus-5-xhigh",
      "value": 1708.14
    },
    {
      "rank": 5,
      "name": "Muse Spark 1.3 (max)",
      "creator": "Meta",
      "slug": "muse-spark-1-3",
      "detailsUrl": "/models/muse-spark-1-3",
      "value": 1703.34
    },
    {
      "rank": 6,
      "name": "Grok 4.6 (xhigh)",
      "creator": "SpaceXAI",
      "slug": "grok-4-6-xhigh",
      "detailsUrl": "/models/grok-4-6-xhigh",
      "value": 1663.07
    },
    {
      "rank": 7,
      "name": "Muse Spark 1.3 (xhigh)",
      "creator": "Meta",
      "slug": "muse-spark-1-3-xhigh",
      "detailsUrl": "/models/muse-spark-1-3-xhigh",
      "value": 1662.34
    },
    {
      "rank": 8,
      "name": "GLM-5.3 (max)",
      "creator": "Z AI",
      "slug": "glm-5-3",
      "detailsUrl": "/models/glm-5-3",
      "value": 1655.16
    },
    {
      "rank": 9,
      "name": "GLM-5.3-Flash",
      "creator": "Z AI",
      "slug": "glm-5-3-flash",
      "detailsUrl": "/models/glm-5-3-flash",
      "value": 1654.95
    },
    {
      "rank": 10,
      "name": "Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)",
      "creator": "Anthropic",
      "slug": "claude-fable-5-1-high",
      "detailsUrl": "/models/claude-fable-5-1-high",
      "value": 1649.77
    },
    {
      "rank": 11,
      "name": "Grok 4.6 (high)",
      "creator": "SpaceXAI",
      "slug": "grok-4-6",
      "detailsUrl": "/models/grok-4-6",
      "value": 1642.96
    },
    {
      "rank": 12,
      "name": "DeepSeek V4.1 Flash (Reasoning, Max Effort)",
      "creator": "DeepSeek",
      "slug": "deepseek-v4-1-flash",
      "detailsUrl": "/models/deepseek-v4-1-flash",
      "value": 1632.06
    },
    {
      "rank": 13,
      "name": "Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)",
      "creator": "Anthropic",
      "slug": "claude-fable-5",
      "detailsUrl": "/models/claude-fable-5",
      "value": 1631.46
    },
    {
      "rank": 14,
      "name": "Qwen3.8 2.4T A95B",
      "creator": "Alibaba",
      "slug": "qwen3-8-2-4t-a95b",
      "detailsUrl": "/models/qwen3-8-2-4t-a95b",
      "value": 1627.82
    },
    {
      "rank": 15,
      "name": "GPT-5.6 Sol (max)",
      "creator": "OpenAI",
      "slug": "gpt-5-6-sol",
      "detailsUrl": "/models/gpt-5-6-sol",
      "value": 1624.11
    },
    {
      "rank": 16,
      "name": "GPT-6 Astra (max)",
      "creator": "OpenAI",
      "slug": "gpt-6-astra",
      "detailsUrl": "/models/gpt-6-astra",
      "value": 1580.2
    },
    {
      "rank": 17,
      "name": "Kimi K3 (max)",
      "creator": "Kimi",
      "slug": "kimi-k3",
      "detailsUrl": "/models/kimi-k3",
      "value": 1551.96
    },
    {
      "rank": 18,
      "name": "DeepSeek V4 Pro 0813 (Reasoning, Max Effort)",
      "creator": "DeepSeek",
      "slug": "deepseek-v4-pro",
      "detailsUrl": "/models/deepseek-v4-pro",
      "value": 1493.31
    },
    {
      "rank": 19,
      "name": "GPT-5.6 Luna (max)",
      "creator": "OpenAI",
      "slug": "gpt-5-6-luna",
      "detailsUrl": "/models/gpt-5-6-luna",
      "value": 1489.33
    },
    {
      "rank": 20,
      "name": "GPT-5.6 Terra (max)",
      "creator": "OpenAI",
      "slug": "gpt-5-6-terra",
      "detailsUrl": "/models/gpt-5-6-terra",
      "value": 1476.96
    }
  ]
}