{
  "url": "https://www.aibattle.space/models/gpt-6-astra",
  "slug": "gpt-6-astra",
  "name": "GPT-6 Astra (max)",
  "creator": "OpenAI",
  "rebuilt": "2026-09-19",
  "placements": [
    {
      "dataset": "MMMU-Pro: Score",
      "rank": 1,
      "total": 19,
      "value": 0.86878612716763
    },
    {
      "dataset": "AA-Omniscience Index",
      "rank": 2,
      "total": 20,
      "value": 43.4
    },
    {
      "dataset": "Artificial Analysis Intelligence Index by Open Weights / Proprietary",
      "rank": 2,
      "total": 20,
      "value": 52.814069395513
    },
    {
      "dataset": "Artificial Analysis Intelligence Index by Open Weights / Proprietary",
      "rank": 2,
      "total": 20,
      "value": 52.814069395513
    },
    {
      "dataset": "Artificial Analysis Intelligence Index",
      "rank": 2,
      "total": 20,
      "value": 52.814069395513
    },
    {
      "dataset": "Artificial Analysis Finance & Accounting Index",
      "rank": 2,
      "total": 20,
      "value": 55.47977223592988
    },
    {
      "dataset": "AA-Omniscience Index",
      "rank": 2,
      "total": 20,
      "value": 43.4
    },
    {
      "dataset": "Artificial Analysis Intelligence Index",
      "rank": 2,
      "total": 20,
      "value": 52.814069395513
    },
    {
      "dataset": "Terminal-Bench v4.0: Score",
      "rank": 2,
      "total": 20,
      "value": 0.590909090909091
    },
    {
      "dataset": "Humanity's Last Exam: Output Tokens per Task",
      "rank": 3,
      "total": 20,
      "value": 275.63253012048193
    },
    {
      "dataset": "AA-LCR v1.1: Output Tokens per Task",
      "rank": 3,
      "total": 20,
      "value": 90.69
    },
    {
      "dataset": "Intelligence",
      "rank": 2,
      "total": 11,
      "value": 52.814069395513
    },
    {
      "dataset": "Intelligence",
      "rank": 2,
      "total": 11,
      "value": 52.814069395513
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 4,
      "total": 20,
      "value": 1562.01
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 4,
      "total": 20,
      "value": 1562.01
    },
    {
      "dataset": "AA-Omniscience Index: Score",
      "rank": 4,
      "total": 20,
      "value": 43.4
    },
    {
      "dataset": "MMMU-Pro: Token Usage",
      "rank": 4,
      "total": 19,
      "value": 1000367
    },
    {
      "dataset": "Output Tokens per Intelligence Index Task",
      "rank": 5,
      "total": 20,
      "value": 10514.266871765667
    },
    {
      "dataset": "Output Tokens per Intelligence Index Task",
      "rank": 5,
      "total": 20,
      "value": 10514.266871765667
    },
    {
      "dataset": "AA-Omniscience Accuracy",
      "rank": 5,
      "total": 20,
      "value": 0.626
    },
    {
      "dataset": "AA-AnalystAgent pass^5",
      "rank": 3,
      "total": 11,
      "value": 0.5125
    },
    {
      "dataset": "Context Window",
      "rank": 6,
      "total": 20,
      "value": 1000000
    },
    {
      "dataset": "Humanity's Last Exam: Score",
      "rank": 6,
      "total": 20,
      "value": 0.546802594995366
    },
    {
      "dataset": "AA-Briefcase Elo",
      "rank": 8,
      "total": 20,
      "value": 1562.01
    },
    {
      "dataset": "AA-Briefcase Output Tokens per Task",
      "rank": 8,
      "total": 20,
      "value": 37019.12087912088
    },
    {
      "dataset": "Humanity's Last Exam: Time per Task",
      "rank": 9,
      "total": 20,
      "value": 2.120330856898991
    },
    {
      "dataset": "Terminal-Bench v4.0: Output Tokens per Task",
      "rank": 9,
      "total": 20,
      "value": 23335.60606060606
    },
    {
      "dataset": "GDPval-AA v2: Output Tokens per Task",
      "rank": 9,
      "total": 20,
      "value": 18050.313636363637
    },
    {
      "dataset": "SciCode: Output Tokens per Task",
      "rank": 9,
      "total": 20,
      "value": 399.9826388888889
    },
    {
      "dataset": "GDPval-AA v2 Leaderboard",
      "rank": 11,
      "total": 20,
      "value": 1580.2
    },
    {
      "dataset": "AA-Briefcase Rubric Pass Rate by File Type (Normalized)",
      "rank": 11,
      "total": 20,
      "value": 0.7307692307692307
    },
    {
      "dataset": "Time per Task",
      "rank": 12,
      "total": 20,
      "value": 21.733867106693534
    },
    {
      "dataset": "AA-LCR v1.1: Time per Task",
      "rank": 12,
      "total": 20,
      "value": 0.3052677914563706
    },
    {
      "dataset": "Time per Intelligence Index Task",
      "rank": 13,
      "total": 20,
      "value": 7.692844744950559
    },
    {
      "dataset": "Time per Intelligence Index Task",
      "rank": 13,
      "total": 20,
      "value": 7.692844744950559
    },
    {
      "dataset": "SciCode: Score",
      "rank": 13,
      "total": 20,
      "value": 0.564814814814815
    },
    {
      "dataset": "AA-Omniscience Hallucination Rate",
      "rank": 14,
      "total": 20,
      "value": 0.5133689839572193
    },
    {
      "dataset": "Speed",
      "rank": 8,
      "total": 11,
      "value": 58.926489179096
    },
    {
      "dataset": "Speed",
      "rank": 8,
      "total": 11,
      "value": 58.926489179096
    },
    {
      "dataset": "AA-Omniscience Index: Token Usage",
      "rank": 15,
      "total": 20,
      "value": 740990
    },
    {
      "dataset": "Terminal-Bench v4.0: Time per Task",
      "rank": 16,
      "total": 20,
      "value": 21.395289600221677
    },
    {
      "dataset": "GDPval-AA v2 Leaderboard",
      "rank": 16,
      "total": 20,
      "value": 1580.2
    },
    {
      "dataset": "Cost per Task",
      "rank": 9,
      "total": 11,
      "value": 3.2575003134834164
    },
    {
      "dataset": "Cost per Task",
      "rank": 9,
      "total": 11,
      "value": 3.2575003134834164
    },
    {
      "dataset": "𝜏³-Banking: Score",
      "rank": 17,
      "total": 20,
      "value": 0.414432989690722
    },
    {
      "dataset": "MMMU-Pro: Total Cost to Run",
      "rank": 17,
      "total": 19,
      "value": 10.00367
    },
    {
      "dataset": "AA-LCR v1.1: Score",
      "rank": 18,
      "total": 20,
      "value": 0.806666666666667
    },
    {
      "dataset": "SciCode: Time per Task",
      "rank": 18,
      "total": 20,
      "value": 1.1838934253861242
    },
    {
      "dataset": "Output Speed",
      "rank": 19,
      "total": 20,
      "value": 58.926489179096
    },
    {
      "dataset": "Output Speed",
      "rank": 19,
      "total": 20,
      "value": 58.926489179096
    },
    {
      "dataset": "𝜏³-Banking: Output Tokens per Task",
      "rank": 20,
      "total": 20,
      "value": 2188.7938144329896
    }
  ]
}