{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "claude-opus-4-1",
    "name": "Claude Opus 4.1",
    "lab": "anthropic",
    "date": "2025-08-05",
    "source": "https://www.anthropic.com/news/claude-opus-4-1",
    "source_title": "Claude Opus 4.1",
    "flagship": true,
    "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
    "releases": [],
    "variant_of": null,
    "made_by": "Anthropic",
    "url": "https://frontierlog.ai/model/claude-opus-4-1",
    "results": [
      {
        "id": "claude-opus-4-1:swe-bench-verified:default:1",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 74.5,
        "unit": "%",
        "printed": "74.5%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Claude Opus 4.1",
        "source": "https://www.anthropic.com/news/claude-opus-4-1",
        "source_title": "Claude Opus 4.1",
        "source_date": "2025-08-05",
        "where": "benchmark table (image), row 'Agentic coding, SWE-bench Verified', column 'Claude Opus 4.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "bash and editor tools; averaged over 10 trials; no test-time compute",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://www.anthropic.com/claude-opus-4-5-system-card",
            "name": "Claude Opus 4.5 card",
            "title": "Claude Opus 4.5 System Card",
            "lab": "anthropic",
            "date": "2025-11-24",
            "printed": "74.5%",
            "where": "Table 2.3.A (p.19), row SWE-bench Verified, column Claude Opus 4.1"
          },
          {
            "url": "https://www.anthropic.com/news/claude-opus-4-5",
            "name": "Claude Opus 4.5",
            "title": "Introducing Claude Opus 4.5",
            "lab": "anthropic",
            "date": "2025-11-24",
            "printed": "74.5%",
            "where": "Benchmark table image, row 'Agentic coding SWE-bench Verified', column 'Opus 4.1'"
          },
          {
            "url": "https://www.anthropic.com/news/claude-sonnet-4-5",
            "name": "Claude Agent SDK",
            "title": "Introducing Claude Sonnet 4.5",
            "lab": "anthropic",
            "date": "2025-09-29",
            "printed": "74.5%",
            "where": "Benchmark table image, row 'Agentic coding SWE-bench Verified', column 'Claude Opus 4.1', upper value"
          },
          {
            "url": "https://www.minimax.io/news/minimax-m25",
            "name": "MiniMax M2.5",
            "title": "MiniMax M2.5: Built for Real-World Productivity.",
            "lab": "minimax",
            "date": "2026-02-12",
            "printed": "74.5%",
            "where": "'SWE-bench Verified Score Evolution' line chart image; point label 'Opus 4.1 74.5%'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/cebed70e8721d155.png",
        "source_image_original": "https://www-cdn.anthropic.com/images/4zrzovbb/website/bde326699c667506c87f74b09a6355961d29eb26-2600x2084.png"
      },
      {
        "id": "claude-opus-4-1:gpqa-diamond:default:1",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 80.9,
        "unit": "%",
        "printed": "80.9%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Claude Opus 4.1",
        "source": "https://www.anthropic.com/news/claude-opus-4-1",
        "source_title": "Claude Opus 4.1",
        "source_date": "2025-08-05",
        "where": "benchmark table (image), row 'Graduate-level reasoning, GPQA Diamond', column 'Claude Opus 4.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "extended thinking up to 64K tokens",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/cebed70e8721d155.png",
        "source_image_original": "https://www-cdn.anthropic.com/images/4zrzovbb/website/bde326699c667506c87f74b09a6355961d29eb26-2600x2084.png"
      },
      {
        "id": "claude-opus-4-1:hle:no-tools:1",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 14.2,
        "unit": "%",
        "printed": "14.2%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Opus 4.1",
        "source": "https://www.anthropic.com/claude-opus-4-5-system-card",
        "source_title": "Claude Opus 4.5 System Card",
        "source_date": "2025-11-24",
        "where": "Figure 2.16.A 'Humanity's Last Exam (HLE)', panel 'Without Search', bar 'Opus 4.1' (page 32)",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "reasoning only; decontamination improved with Opus 4.5, which may affect this score",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/119c3ba76f816d86.png"
      },
      {
        "id": "claude-opus-4-1:hle:with-tools:1",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 22.7,
        "unit": "%",
        "printed": "22.7%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Opus 4.1",
        "source": "https://www.anthropic.com/claude-opus-4-5-system-card",
        "source_title": "Claude Opus 4.5 System Card",
        "source_date": "2025-11-24",
        "where": "Figure 2.16.A 'Humanity's Last Exam (HLE)', panel 'With Search', bar 'Opus 4.1' (page 32)",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "with search",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/119c3ba76f816d86.png"
      },
      {
        "id": "claude-opus-4-1:terminal-bench-1-0:default:1",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "terminal-bench-1-0",
        "benchmark_name": "Terminal-Bench 1.0",
        "setting": "default",
        "setting_name": "",
        "score": 43.3,
        "unit": "%",
        "printed": "43.3%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Claude Opus 4.1",
        "source": "https://www.anthropic.com/news/claude-opus-4-1",
        "source_title": "Claude Opus 4.1",
        "source_date": "2025-08-05",
        "where": "benchmark table image, row 'Agentic terminal coding / Terminal-Bench', column 'Claude Opus 4.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "no extended thinking; Terminus 1 agent; averaged over 5 trials",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-18",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/cebed70e8721d155.png",
        "source_image_original": "https://www-cdn.anthropic.com/images/4zrzovbb/website/bde326699c667506c87f74b09a6355961d29eb26-2600x2084.png"
      },
      {
        "id": "claude-opus-4-1:aime-2025:no-tools:1",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "aime-2025",
        "benchmark_name": "AIME 2025",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 78.0,
        "unit": "%",
        "printed": "78.0%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Claude Opus 4.1",
        "source": "https://www.anthropic.com/news/claude-opus-4-1",
        "source_title": "Claude Opus 4.1",
        "source_date": "2025-08-05",
        "where": "benchmark table image, row 'High school math competition / AIME 2025', column 'Claude Opus 4.1'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "extended thinking up to 64K tokens",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-18",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_image": "https://frontierlog.ai/sources/cebed70e8721d155.png",
        "source_image_original": "https://www-cdn.anthropic.com/images/4zrzovbb/website/bde326699c667506c87f74b09a6355961d29eb26-2600x2084.png"
      },
      {
        "id": "claude-opus-4-1:gpqa-diamond:default:2",
        "model": "claude-opus-4-1",
        "model_name": "Claude Opus 4.1",
        "model_date": "2025-08-05",
        "event": "https://frontierlog.ai/event/2025-08-05-claude-opus-4-1",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 81.0,
        "unit": "%",
        "printed": "81.0%",
        "reported_by": "anthropic",
        "run_by": null,
        "label": "Opus 4.1",
        "source": "https://www.anthropic.com/news/claude-opus-4-5",
        "source_title": "Introducing Claude Opus 4.5",
        "source_date": "2025-11-24",
        "where": "benchmark table (image), row 'Graduate-level reasoning, GPQA Diamond', column 'Opus 4.1'",
        "own": false,
        "primary": false,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-20",
        "corroborated_by": [
          {
            "url": "https://www.anthropic.com/news/claude-sonnet-4-5",
            "name": "Claude Agent SDK",
            "title": "Introducing Claude Sonnet 4.5",
            "lab": "anthropic",
            "date": "2025-09-29",
            "printed": "81.0%",
            "where": "main benchmark table image, row 'Graduate-level reasoning / GPQA Diamond', column 'Claude Opus 4.1'"
          },
          {
            "url": "https://www.anthropic.com/claude-opus-4-5-system-card",
            "name": "Claude Opus 4.5 card",
            "title": "Claude Opus 4.5 System Card",
            "lab": "anthropic",
            "date": "2025-11-24",
            "printed": "81.0%",
            "where": "Table 2.3.A, row 'GPQA Diamond', column 'Claude Opus 4.1'"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/790b0c5480216588.png",
        "source_image_original": "https://cdn.sanity.io/images/4zrzovbb/website/52303b11db76017fd0c2f73c7fafa5c752515979-2600x2236.png"
      }
    ]
  }
}