{
  "api_version": "1",
  "updated": "2026-10-18",
  "latest_event": "2026-10-17",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "aime-2025",
    "name": "AIME 2025",
    "family": "aime",
    "unit": "%",
    "higher_is_better": true,
    "status": "superseded",
    "benchmark_url": "https://maa.org/amc/aime",
    "introduced": "2025-02-12",
    "creator": "Mathematical Association of America",
    "introduced_source": "https://maa.org/news/aime-thresholds-are-available/",
    "settings": [
      {
        "setting": "no-tools",
        "name": "No tools",
        "url": "https://frontierlog.ai/benchmark/aime-2025",
        "results": 11
      },
      {
        "setting": "with-tools",
        "name": "With tools",
        "url": "https://frontierlog.ai/benchmark/aime-2025/with-tools",
        "results": 4
      }
    ]
  },
  "total": 4,
  "results": [
    {
      "id": "openai-o3:aime-2025:with-tools:1",
      "model": "openai-o3",
      "model_name": "OpenAI o3",
      "model_date": "2025-04-16",
      "event": "https://frontierlog.ai/event/2025-04-16-o3-and-o4-mini",
      "benchmark": "aime-2025",
      "benchmark_name": "AIME 2025",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 98.4,
      "unit": "%",
      "printed": "98.4%",
      "reported_by": "openai",
      "label": "o3",
      "source": "https://openai.com/index/introducing-o3-and-o4-mini",
      "source_title": "Introducing OpenAI o3 and o4-mini",
      "source_date": "2025-04-16",
      "where": "'What's changed' section, paragraph on o4-mini, last sentence (o3 with tool use)",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "Sentence in the text; tool is a Python interpreter (the sentence compares to o4-mini 'when given access to a Python interpreter'). pass@1. The post says these with-tools results should not be compared to models without tool access.",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-18"
    },
    {
      "id": "openai-o3:aime-2025:with-tools:2",
      "model": "openai-o3",
      "model_name": "OpenAI o3",
      "model_date": "2025-04-16",
      "event": "https://frontierlog.ai/event/2025-04-16-o3-and-o4-mini",
      "benchmark": "aime-2025",
      "benchmark_name": "AIME 2025",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 100.0,
      "unit": "%",
      "printed": "100%",
      "reported_by": "openai",
      "label": "o3",
      "source": "https://openai.com/index/introducing-o3-and-o4-mini",
      "source_title": "Introducing OpenAI o3 and o4-mini",
      "source_date": "2025-04-16",
      "where": "'What's changed' section, paragraph on o4-mini, last sentence (o3 with tool use), second figure in the parenthesis",
      "own": true,
      "primary": false,
      "parallel": true,
      "notes": "consensus@8 (majority voting over 8 samples), with a Python interpreter.",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-18"
    },
    {
      "id": "gpt-5:aime-2025:with-tools:1",
      "model": "gpt-5",
      "model_name": "GPT-5",
      "model_date": "2025-08-07",
      "event": "https://frontierlog.ai/event/2025-08-07-gpt-5",
      "benchmark": "aime-2025",
      "benchmark_name": "AIME 2025",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 99.6,
      "unit": "%",
      "printed": "99.6%",
      "reported_by": "openai",
      "label": "GPT-5 (python), With thinking",
      "source": "https://openai.com/index/introducing-gpt-5",
      "source_title": "Introducing GPT-5",
      "source_date": "2025-08-07",
      "where": "'Evaluations' section, bar chart 'AIME 2025 / Competition math', 3rd bar 'GPT-5 (python)', top (dark) segment",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "Read from the full-page screenshot (shots.jsonl part 3, image 97; the bar's x-axis label is at the top of part 4, kb:/api/images/98, sha256 f036431e418305f0b45d54e5179176b075413da4a646a81867a80b28bd140ddb). Chart y-axis 'Accuracy, pass@1'; legend: dark = With thinking, light = Without thinking; stacked bar, value label on each segment. Footnote under the chart: '*AIME results with tools should not be compared directly to the performance of models without tool access; they are an example of how effectively GPT-5 leverages available tools.' Tool: Python. Read from a full-page screenshot of the post (para-kb image /api/images/97), as openai.com is bot-walled.",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-18"
    },
    {
      "id": "gpt-5:aime-2025:with-tools:2",
      "model": "gpt-5",
      "model_name": "GPT-5",
      "model_date": "2025-08-07",
      "event": "https://frontierlog.ai/event/2025-08-07-gpt-5",
      "benchmark": "aime-2025",
      "benchmark_name": "AIME 2025",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 71.0,
      "unit": "%",
      "printed": "71.0%",
      "reported_by": "openai",
      "label": "GPT-5 (python), Without thinking",
      "source": "https://openai.com/index/introducing-gpt-5",
      "source_title": "Introducing GPT-5",
      "source_date": "2025-08-07",
      "where": "'Evaluations' section, bar chart 'AIME 2025 / Competition math', 3rd bar 'GPT-5 (python)', lower (light) segment",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "Read from the full-page screenshot (shots.jsonl part 3, image 97; the bar's x-axis label is at the top of part 4, kb:/api/images/98, sha256 f036431e418305f0b45d54e5179176b075413da4a646a81867a80b28bd140ddb). Chart y-axis 'Accuracy, pass@1'; legend: dark = With thinking, light = Without thinking; stacked bar, value label on each segment. Footnote under the chart: '*AIME results with tools should not be compared directly to the performance of models without tool access; they are an example of how effectively GPT-5 leverages available tools.' Tool: Python. Without-thinking value. Read from a full-page screenshot of the post (para-kb image /api/images/97), as openai.com is bot-walled.",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-18"
    }
  ]
}