{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "openai-o1-preview",
    "name": "o1-preview",
    "lab": "openai",
    "date": "2024-09-12",
    "source": "https://openai.com/index/introducing-openai-o1-preview",
    "source_title": "Introducing OpenAI o1",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2024-09-12-openai-o1",
    "releases": [],
    "variant_of": null,
    "made_by": "OpenAI",
    "url": "https://frontierlog.ai/model/openai-o1-preview",
    "results": [
      {
        "id": "openai-o1-preview:swe-bench-verified:default:1",
        "model": "openai-o1-preview",
        "model_name": "o1-preview",
        "model_date": "2024-09-12",
        "event": "https://frontierlog.ai/event/2024-09-12-openai-o1",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 41.4,
        "unit": "%",
        "printed": "41.4%",
        "reported_by": "openai",
        "run_by": null,
        "label": "o1-preview (final model)",
        "source": "https://cdn.openai.com/o1-preview-system-card-20240917.pdf",
        "source_title": "OpenAI o1 System Card (o1-preview version, Sept 12, 2024)",
        "source_date": "2024-09-12",
        "where": "section 4.5.2 'SWE-bench Verified', paragraph under the 'SWE-Bench Verified (with 5-try Agentless Scaffold)' chart, sentence on the final o1-preview model",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Agentless scaffold; 5 tries to produce a patch; 3-trial average; 477 of the 500 tasks",
        "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/6f898b9550e2ee4c.png"
      },
      {
        "id": "openai-o1-preview:swe-bench-verified:default:2",
        "model": "openai-o1-preview",
        "model_name": "o1-preview",
        "model_date": "2024-09-12",
        "event": "https://frontierlog.ai/event/2024-09-12-openai-o1",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 41.3,
        "unit": "%",
        "printed": "41.3",
        "reported_by": "openai",
        "run_by": null,
        "label": "o1-preview",
        "source": "https://openai.com/index/o1-and-new-tools-for-developers",
        "source_title": "OpenAI o1 and new tools for developers",
        "source_date": "2024-12-17",
        "where": "eval table (Category / Eval / o1-2024-12-17 / o1-preview), row 'Coding: SWE-bench Verified', column 'o1-preview'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "",
        "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/3524505a975cb735.png"
      },
      {
        "id": "openai-o1-preview:gpqa-diamond:default:1",
        "model": "openai-o1-preview",
        "model_name": "o1-preview",
        "model_date": "2024-09-12",
        "event": "https://frontierlog.ai/event/2024-09-12-openai-o1",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 73.3,
        "unit": "%",
        "printed": "73.3",
        "reported_by": "openai",
        "run_by": null,
        "label": "o1-preview",
        "source": "https://openai.com/index/o1-and-new-tools-for-developers",
        "source_title": "OpenAI o1 and new tools for developers",
        "source_date": "2024-12-17",
        "where": "eval table (Category / Eval / o1-2024-12-17 / o1-preview), row 'General: GPQA diamond', column 'o1-preview'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://openai.com/index/learning-to-reason-with-llms",
            "name": "OpenAI post",
            "title": "Learning to reason with LLMs",
            "lab": "openai",
            "date": "2024-09-12",
            "printed": "73.3",
            "where": "Table (appendix), row 'GPQA Diamond', metric 'pass@1', column 'o1-preview'"
          },
          {
            "url": "https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning",
            "name": "o1-mini",
            "title": "OpenAI o1-mini",
            "lab": "openai",
            "date": "2024-09-12",
            "printed": "73.3%",
            "where": "STEM chart, row 'GPQA Diamond, 0-shot CoT', bar 'o1-preview' (bars: o1 77.3%, o1-preview 73.3%, o1-mini 60.0%, GPT-4o 53.6%)"
          },
          {
            "url": "https://api-docs.deepseek.com/news/news1120/",
            "name": "DeepSeek-R1 card",
            "title": "DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power!",
            "lab": "deepseek",
            "date": "2025-01-20",
            "printed": "73.3",
            "where": "DeepSeek-R1-Lite-Preview launch chart image (r1_hist_en.jpeg), panel 'GPQA Diamond' (pass@1), 'o1-preview' bar. No provenance footnote."
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/3524505a975cb735.png"
      },
      {
        "id": "openai-o1-preview:aime-2024:no-tools:1",
        "model": "openai-o1-preview",
        "model_name": "o1-preview",
        "model_date": "2024-09-12",
        "event": "https://frontierlog.ai/event/2024-09-12-openai-o1",
        "benchmark": "aime-2024",
        "benchmark_name": "AIME 2024",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 42.0,
        "unit": "%",
        "printed": "42.0",
        "reported_by": "openai",
        "run_by": null,
        "label": "o1-preview",
        "source": "https://openai.com/index/o1-and-new-tools-for-developers",
        "source_title": "OpenAI o1 and new tools for developers",
        "source_date": "2024-12-17",
        "where": "eval table (Category / Eval / o1-2024-12-17 / o1-preview), row 'Math: AIME 2024 (pass @1)', column 'o1-preview'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "pass@1",
        "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/3524505a975cb735.png"
      },
      {
        "id": "openai-o1-preview:aime-2024:no-tools:2",
        "model": "openai-o1-preview",
        "model_name": "o1-preview",
        "model_date": "2024-09-12",
        "event": "https://frontierlog.ai/event/2024-09-12-openai-o1",
        "benchmark": "aime-2024",
        "benchmark_name": "AIME 2024",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 44.6,
        "unit": "%",
        "printed": "44.6%",
        "reported_by": "openai",
        "run_by": null,
        "label": "o1-preview",
        "source": "https://openai.com/index/openai-o1-mini-advancing-cost-efficient-reasoning",
        "source_title": "OpenAI o1-mini",
        "source_date": "2024-09-12",
        "where": "'Optimized for STEM Reasoning' section, the 'Mathematics:' paragraph under the 'Math Performance vs Inference Cost' chart, the figure in parentheses after 'o1-preview'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "AIME year and pass@1 not stated",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-20",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      }
    ]
  }
}