{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "openai-o3-mini",
    "name": "o3-mini",
    "lab": "openai",
    "date": "2025-01-31",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2025-01-31-openai-o3-mini",
    "releases": [],
    "variant_of": null,
    "made_by": "OpenAI",
    "url": "https://frontierlog.ai/model/openai-o3-mini",
    "results": [
      {
        "id": "openai-o3-mini:gpqa-diamond:default:1",
        "model": "openai-o3-mini",
        "model_name": "o3-mini",
        "model_date": "2025-01-31",
        "event": "https://frontierlog.ai/event/2025-01-31-openai-o3-mini",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 79.7,
        "unit": "%",
        "printed": "79.7",
        "reported_by": "openai",
        "run_by": null,
        "label": "o3-mini (high)",
        "source": "https://openai.com/index/openai-o3-mini",
        "source_title": "OpenAI o3-mini",
        "source_date": "2025-01-31",
        "where": "image GPQA.png (bar chart, accuracy by OpenAI model), value label over the 'o3-mini (high)' bar",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "high reasoning effort",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://www.anthropic.com/news/claude-3-7-sonnet",
            "name": "Claude 3.7 Sonnet",
            "title": "Claude 3.7 Sonnet and Claude Code",
            "lab": "anthropic",
            "date": "2025-02-24",
            "printed": "79.7%",
            "where": "Benchmark table image, row \"Graduate-level reasoning GPQA Diamond\", column \"OpenAI o3-mini High\""
          },
          {
            "url": "https://blog.google/innovation-and-ai/models-and-research/google-deepmind/gemini-model-thinking-updates-march-2025/",
            "name": "Gemini 2.5 Pro",
            "title": "Gemini 2.5: Our most intelligent AI model",
            "lab": "google",
            "date": "2025-03-25",
            "printed": "79.7%",
            "where": "Benchmark table image; row 'Science GPQA diamond', single attempt (pass@1); column 'OpenAI o3-mini High'. Footnote: non-Gemini results sourced from providers' self-reported numbers; where provider numbers are not available, HLE from agi.safe.ai / Scale leaderboard. Same value fits both o3-mini (high) GPQA rows."
          }
        ],
        "source_image": "https://frontierlog.ai/sources/789a44bdbc12cbdd.png",
        "source_image_original": "https://images.ctfassets.net/kftzwdyauwt9/6RtMqSi8nzD2TawNrhiCXr/1d7eed551d8d118e6c6d219e38f5b5a7/GPQA.png"
      },
      {
        "id": "openai-o3-mini:gpqa-diamond:default:2",
        "model": "openai-o3-mini",
        "model_name": "o3-mini",
        "model_date": "2025-01-31",
        "event": "https://frontierlog.ai/event/2025-01-31-openai-o3-mini",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 77.2,
        "unit": "%",
        "printed": "77.2%",
        "reported_by": "openai",
        "run_by": null,
        "label": "OpenAI o3-mini (high)",
        "source": "https://openai.com/index/gpt-4-1",
        "source_title": "Introducing GPT-4.1 in the API",
        "source_date": "2025-04-14",
        "where": "academic eval table (columns GPT-4.1 ... GPT-4.5), row 'GPQA Diamond1', column 'OpenAI o3-mini(high)'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "high reasoning effort; answers parsed by a model, not regex",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/b347e2620091fc48.png"
      },
      {
        "id": "openai-o3-mini:gpqa-diamond:default:3",
        "model": "openai-o3-mini",
        "model_name": "o3-mini",
        "model_date": "2025-01-31",
        "event": "https://frontierlog.ai/event/2025-01-31-openai-o3-mini",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 77.0,
        "unit": "%",
        "printed": "77.0",
        "reported_by": "openai",
        "run_by": null,
        "label": "o3-mini",
        "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, bar chart 'GPQA Diamond / PhD-Level Science Questions', 2nd bar 'o3-mini' (page screenshot (job 20879 capture), part 02)",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "high reasoning effort; no tools",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://openai.com/index/introducing-gpt-oss",
            "name": "gpt-oss-120b and gpt-oss-20b",
            "title": "Introducing gpt-oss",
            "lab": "openai",
            "date": "2025-08-05",
            "printed": "77",
            "where": "GPQA Diamond (without tools) chart, bar 'o3-mini' (effort not stated)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/392f30ae76e5713f.png"
      },
      {
        "id": "openai-o3-mini:hle:no-tools:1",
        "model": "openai-o3-mini",
        "model_name": "o3-mini",
        "model_date": "2025-01-31",
        "event": "https://frontierlog.ai/event/2025-01-31-openai-o3-mini",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 13.0,
        "unit": "%",
        "printed": "13.0",
        "reported_by": "openai",
        "run_by": null,
        "label": "OpenAI o3-mini (high)",
        "source": "https://openai.com/index/introducing-deep-research",
        "source_title": "Introducing deep research",
        "source_date": "2025-02-02",
        "where": "Humanity's Last Exam table (Model / Accuracy (%)), row 'OpenAI o3-mini (high)*'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "high reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9676fd3a951a3d1c.png"
      },
      {
        "id": "openai-o3-mini:hle:no-tools:2",
        "model": "openai-o3-mini",
        "model_name": "o3-mini",
        "model_date": "2025-01-31",
        "event": "https://frontierlog.ai/event/2025-01-31-openai-o3-mini",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 13.4,
        "unit": "%",
        "printed": "13.40",
        "reported_by": "openai",
        "run_by": null,
        "label": "o3-mini",
        "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, bar chart 'Humanity's Last Exam', 2nd bar 'o3-mini' (page screenshot (job 20879 capture), part 02)",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "high reasoning effort",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://openai.com/index/introducing-gpt-oss",
            "name": "gpt-oss-120b and gpt-oss-20b",
            "title": "Introducing gpt-oss",
            "lab": "openai",
            "date": "2025-08-05",
            "printed": "13.4",
            "where": "Humanity's Last Exam chart, bar 'o3-mini (without tools)' (effort not stated)"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/392f30ae76e5713f.png"
      }
    ]
  }
}