{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "kimi-k3-1-pro",
    "name": "Kimi K3.1 Pro",
    "lab": "moonshot",
    "date": "2026-10-24",
    "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
    "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
    "releases": [],
    "variant_of": null,
    "made_by": "Moonshot AI",
    "url": "https://frontierlog.ai/model/kimi-k3-1-pro",
    "results": [
      {
        "id": "kimi-k3-1-pro:terminal-bench-4-0:default:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "terminal-bench-4-0",
        "benchmark_name": "Terminal-Bench 4.0",
        "setting": "default",
        "setting_name": "",
        "score": 65.7,
        "unit": "%",
        "printed": "65.7",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Coding', row 'Terminal-Bench 4.0', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness; max reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      },
      {
        "id": "kimi-k3-1-pro:terminal-bench-science-0-1:default:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "terminal-bench-science-0-1",
        "benchmark_name": "Terminal-Bench Science 0.1",
        "setting": "default",
        "setting_name": "",
        "score": 38.1,
        "unit": "%",
        "printed": "38.1",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Coding', row 'Terminal-Bench Science 0.1', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness; max reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      },
      {
        "id": "kimi-k3-1-pro:deepswe-1-1:default:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 75.5,
        "unit": "%",
        "printed": "75.5",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Coding', row 'DeepSWE v1.1', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness; max reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      },
      {
        "id": "kimi-k3-1-pro:hle:with-tools:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 70.0,
        "unit": "%",
        "printed": "70.0",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Agentic', row 'HLE-Full w/ tools', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "full set; max reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      },
      {
        "id": "kimi-k3-1-pro:browsecomp:default:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "browsecomp",
        "benchmark_name": "BrowseComp",
        "setting": "default",
        "setting_name": "",
        "score": 92.1,
        "unit": "%",
        "printed": "92.1",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Agentic', row 'BrowseComp', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "max reasoning effort; context compaction at 200K tokens; 500-step limit",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      },
      {
        "id": "kimi-k3-1-pro:hle:no-tools:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 51.1,
        "unit": "%",
        "printed": "51.1",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Reasoning & Knowledge & Multimodal', row 'HLE-Full', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "full set; max reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      },
      {
        "id": "kimi-k3-1-pro:gpqa-diamond:default:1",
        "model": "kimi-k3-1-pro",
        "model_name": "Kimi K3.1 Pro",
        "model_date": "2026-10-24",
        "event": "https://frontierlog.ai/event/2026-10-24-kimi-k3-1-pro",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 94.2,
        "unit": "%",
        "printed": "94.2",
        "reported_by": "moonshot",
        "run_by": null,
        "label": "Kimi K3.1 Pro (max)",
        "source": "https://www.kimi.ai/blog/kimi-k3-1-pro",
        "source_title": "Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence",
        "source_date": "2026-10-24",
        "where": "'Benchmarks' table (rendered by the page's script), section 'Reasoning & Knowledge & Multimodal', row 'GPQA-Diamond', column 'Kimi K3.1 Pro (max)'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "max reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-24",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/6013c23ab67bdd5d.png"
      }
    ]
  }
}