{
  "generated": "2026-09-08",
  "benchmark": "aime-2025",
  "results": [
    {
      "system": "DeepSeek-R1",
      "developer": "DeepSeek",
      "value": 70.0,
      "date": "2025-02-12",
      "source": {
        "url": "https://matharena.ai/",
        "kind": "independent-evaluation",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "tools": false,
        "pass_k": 1,
        "notes": "MathArena AIME 2025 table (I+II, 30 problems), 70.00% +/- 8.20. MathArena does not show a run date; date used is AIME II exam day (R1 was released 2025-01-20, before the exam)."
      }
    },
    {
      "system": "o3 (high)",
      "developer": "OpenAI",
      "value": 88.9,
      "date": "2025-08-07",
      "source": {
        "url": "https://openai.com/index/introducing-gpt-5/",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "tools": false,
        "notes": "GPT-5 launch chart 'AIME 2025 (no tools)'; MathArena independently measured o3 (high) at 89.2."
      }
    },
    {
      "system": "GPT-5 (no tools)",
      "developer": "OpenAI",
      "value": 94.6,
      "date": "2025-08-07",
      "source": {
        "url": "https://openai.com/index/introducing-gpt-5/",
        "kind": "developer-report",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "tools": false,
        "notes": "With thinking. GPT-5 with python scored 99.6 in the same chart; tool runs are not comparable."
      }
    },
    {
      "system": "GPT-5.2 (high)",
      "developer": "OpenAI",
      "value": 100.0,
      "date": "2025-12-11",
      "source": {
        "url": "https://matharena.ai/",
        "kind": "independent-evaluation",
        "accessed": "2026-09-04"
      },
      "conditions": {
        "tools": false,
        "pass_k": 1,
        "notes": "MathArena AIME 2025 table, 100.00% +/- 0.00 for both high and xhigh effort. Date is model release; MathArena marks the competition deprecated."
      }
    }
  ]
}