{
  "api_version": "1",
  "updated": "2026-10-28",
  "latest_event": "2026-10-27",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "aime-2024",
    "name": "AIME 2024",
    "family": "aime",
    "unit": "%",
    "higher_is_better": true,
    "status": "superseded",
    "active": false,
    "superseded_by": "aime-2025",
    "retired": null,
    "benchmark_url": "https://maa.org/amc/aime",
    "introduced": "2024-02-07",
    "creator": "Mathematical Association of America",
    "introduced_source": "https://maa.org/sites/default/files/Programs/2024%20AIME%20TM.pdf",
    "settings": [
      {
        "setting": "no-tools",
        "name": "No tools",
        "url": "https://frontierlog.ai/benchmark/aime-2024",
        "results": 70
      },
      {
        "setting": "with-tools",
        "name": "With tools",
        "url": "https://frontierlog.ai/benchmark/aime-2024/with-tools",
        "results": 8
      }
    ]
  },
  "total": 8,
  "results": [
    {
      "id": "openai-o3:aime-2024: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-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 95.2,
      "unit": "%",
      "printed": "95.2",
      "reported_by": "openai",
      "run_by": null,
      "label": "o3",
      "source": "https://openai.com/index/introducing-gpt-oss",
      "source_title": "Introducing gpt-oss",
      "source_date": "2025-08-05",
      "where": "bar chart 'AIME 2024 (tools) / Competition math', bar 'o3' (page screenshot (job 20879 capture), part 03)",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "openai-o4-mini:aime-2024:with-tools:1",
      "model": "openai-o4-mini",
      "model_name": "o4-mini",
      "model_date": "2025-04-16",
      "event": "https://frontierlog.ai/event/2025-04-16-o3-and-o4-mini",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 98.7,
      "unit": "%",
      "printed": "98.7",
      "reported_by": "openai",
      "run_by": null,
      "label": "o4-mini",
      "source": "https://openai.com/index/introducing-gpt-oss",
      "source_title": "Introducing gpt-oss",
      "source_date": "2025-08-05",
      "where": "bar chart 'AIME 2024 (tools) / Competition math', bar 'o4-mini' (page screenshot (job 20879 capture), part 03)",
      "own": false,
      "primary": true,
      "parallel": false,
      "notes": "tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gpt-oss-120b:aime-2024:with-tools:1",
      "model": "gpt-oss-120b",
      "model_name": "gpt-oss-120b",
      "model_date": "2025-08-05",
      "event": "https://frontierlog.ai/event/2025-08-05-gpt-oss",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 96.6,
      "unit": "%",
      "printed": "96.6",
      "reported_by": "openai",
      "run_by": null,
      "label": "gpt-oss-120b",
      "source": "https://openai.com/index/introducing-gpt-oss",
      "source_title": "Introducing gpt-oss",
      "source_date": "2025-08-05",
      "where": "bar chart 'AIME 2024 (tools) / Competition math', bar 'gpt-oss-120b' (page screenshot (job 20879 capture), part 03)",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "high reasoning effort; tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gpt-oss-120b:aime-2024:with-tools:2",
      "model": "gpt-oss-120b",
      "model_name": "gpt-oss-120b",
      "model_date": "2025-08-05",
      "event": "https://frontierlog.ai/event/2025-08-05-gpt-oss",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 75.4,
      "unit": "%",
      "printed": "75.4",
      "reported_by": "openai",
      "run_by": null,
      "label": "gpt-oss-120b low",
      "source": "https://deploymentsafety.openai.com/gpt-oss",
      "source_title": "gpt-oss-120b & gpt-oss-20b Model Card",
      "source_date": "2025-08-05",
      "where": "section 2.6.1, Table 3 'Evaluations across multiple benchmarks and reasoning levels' (HTML), row 'AIME 2024 (with tools)', column 'gpt-oss-120b' / 'low'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "low reasoning effort; tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gpt-oss-120b:aime-2024:with-tools:3",
      "model": "gpt-oss-120b",
      "model_name": "gpt-oss-120b",
      "model_date": "2025-08-05",
      "event": "https://frontierlog.ai/event/2025-08-05-gpt-oss",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 87.9,
      "unit": "%",
      "printed": "87.9",
      "reported_by": "openai",
      "run_by": null,
      "label": "gpt-oss-120b medium",
      "source": "https://deploymentsafety.openai.com/gpt-oss",
      "source_title": "gpt-oss-120b & gpt-oss-20b Model Card",
      "source_date": "2025-08-05",
      "where": "section 2.6.1, Table 3 'Evaluations across multiple benchmarks and reasoning levels' (HTML), row 'AIME 2024 (with tools)', column 'gpt-oss-120b' / 'medium'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "medium reasoning effort; tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gpt-oss-20b:aime-2024:with-tools:1",
      "model": "gpt-oss-20b",
      "model_name": "gpt-oss-20b",
      "model_date": "2025-08-05",
      "event": "https://frontierlog.ai/event/2025-08-05-gpt-oss",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 96.0,
      "unit": "%",
      "printed": "96",
      "reported_by": "openai",
      "run_by": null,
      "label": "gpt-oss-20b",
      "source": "https://openai.com/index/introducing-gpt-oss",
      "source_title": "Introducing gpt-oss",
      "source_date": "2025-08-05",
      "where": "bar chart 'AIME 2024 (tools) / Competition math', bar 'gpt-oss-20b' (page screenshot (job 20879 capture), part 03)",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "high reasoning effort; tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gpt-oss-20b:aime-2024:with-tools:2",
      "model": "gpt-oss-20b",
      "model_name": "gpt-oss-20b",
      "model_date": "2025-08-05",
      "event": "https://frontierlog.ai/event/2025-08-05-gpt-oss",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 61.2,
      "unit": "%",
      "printed": "61.2",
      "reported_by": "openai",
      "run_by": null,
      "label": "gpt-oss-20b low",
      "source": "https://deploymentsafety.openai.com/gpt-oss",
      "source_title": "gpt-oss-120b & gpt-oss-20b Model Card",
      "source_date": "2025-08-05",
      "where": "section 2.6.1, Table 3 'Evaluations across multiple benchmarks and reasoning levels' (HTML), row 'AIME 2024 (with tools)', column 'gpt-oss-20b' / 'low'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "low reasoning effort; tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    },
    {
      "id": "gpt-oss-20b:aime-2024:with-tools:3",
      "model": "gpt-oss-20b",
      "model_name": "gpt-oss-20b",
      "model_date": "2025-08-05",
      "event": "https://frontierlog.ai/event/2025-08-05-gpt-oss",
      "benchmark": "aime-2024",
      "benchmark_name": "AIME 2024",
      "setting": "with-tools",
      "setting_name": "With tools",
      "score": 86.0,
      "unit": "%",
      "printed": "86.0",
      "reported_by": "openai",
      "run_by": null,
      "label": "gpt-oss-20b medium",
      "source": "https://deploymentsafety.openai.com/gpt-oss",
      "source_title": "gpt-oss-120b & gpt-oss-20b Model Card",
      "source_date": "2025-08-05",
      "where": "section 2.6.1, Table 3 'Evaluations across multiple benchmarks and reasoning levels' (HTML), row 'AIME 2024 (with tools)', column 'gpt-oss-20b' / 'medium'",
      "own": true,
      "primary": false,
      "parallel": false,
      "notes": "medium reasoning effort; tools",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "double_entry",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": []
    }
  ]
}