{
  "api_version": "1",
  "updated": "2026-10-28",
  "latest_event": "2026-10-27",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "longcat-flash-thinking-2601",
    "name": "LongCat-Flash-Thinking-2601",
    "lab": "meituan",
    "date": "2026-01-20",
    "source": "https://tech.meituan.com/2026/01/20/LongCat-Flash-Thinking-2601.html",
    "source_title": "美团 LongCat-Flash-Thinking-2601 发布，工具调用能力登顶开源 SOTA！",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
    "releases": [],
    "variant_of": null,
    "made_by": "Meituan",
    "url": "https://frontierlog.ai/model/longcat-flash-thinking-2601",
    "results": [
      {
        "id": "longcat-flash-thinking-2601:livecodebench:default:1",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "livecodebench",
        "benchmark_name": "LiveCodeBench",
        "setting": "default",
        "setting_name": "",
        "score": 82.8,
        "unit": "%",
        "printed": "82.8",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://tech.meituan.com/2026/01/20/LongCat-Flash-Thinking-2601.html",
        "source_title": "美团 LongCat-Flash-Thinking-2601 发布，工具调用能力登顶开源 SOTA！",
        "source_date": "2026-01-20",
        "where": "capability list, coding item (sentence on LCB); the chart labels the window 24.08-25.05",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 4 runs; problems from Aug 2024 to May 2025",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-28",
        "corroborated_by": [
          {
            "url": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
            "name": "LongCat-Flash-Thinking-2601 card",
            "title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
            "lab": "meituan",
            "date": "2026-01-20",
            "printed": "82.8",
            "where": "HF model card, LCB (24.08–25.05) (Avg@4) row, LongCat-Flash-Thinking-2601 column"
          }
        ]
      },
      {
        "id": "longcat-flash-thinking-2601:aime-2025:with-tools:1",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "aime-2025",
        "benchmark_name": "AIME 2025",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 99.6,
        "unit": "%",
        "printed": "99.6",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://tech.meituan.com/2026/01/20/LongCat-Flash-Thinking-2601.html",
        "source_title": "美团 LongCat-Flash-Thinking-2601 发布，工具调用能力登顶开源 SOTA！",
        "source_date": "2026-01-20",
        "where": "benchmark chart image, 'Math w/ Python' group, panel 'AIME-25 (Avg@16)', lower value label on the LongCat-Flash-Thinking-2601 bar",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "with python; average of 16 runs",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-28",
        "corroborated_by": [
          {
            "url": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
            "name": "LongCat-Flash-Thinking-2601 card",
            "title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
            "lab": "meituan",
            "date": "2026-01-20",
            "printed": "99.6",
            "where": "HF model card, Mathematical Reasoning w/ Tools, AIME-25 (Avg@16), first value row, LongCat-Flash-Thinking-2601 column"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/18f46816ed786198.png",
        "source_image_original": "https://p0.meituan.net/meituantechblog/ae4b642f27c902ddcf062b41c078f7e9600346.png"
      },
      {
        "id": "longcat-flash-thinking-2601:aime-2025:with-tools:2",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "aime-2025",
        "benchmark_name": "AIME 2025",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 100.0,
        "unit": "%",
        "printed": "100.0",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://tech.meituan.com/2026/01/20/LongCat-Flash-Thinking-2601.html",
        "source_title": "美团 LongCat-Flash-Thinking-2601 发布，工具调用能力登顶开源 SOTA！",
        "source_date": "2026-01-20",
        "where": "capability list, math item (sentence on AIME-25 with heavy thinking mode)",
        "own": true,
        "primary": false,
        "parallel": true,
        "notes": "heavy thinking mode; with python; average of 16 runs",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "corroborated",
        "corroborated": true,
        "corroborated_on": "2026-10-28",
        "corroborated_by": [
          {
            "url": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
            "name": "LongCat-Flash-Thinking-2601 card",
            "title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
            "lab": "meituan",
            "date": "2026-01-20",
            "printed": "100.0",
            "where": "HF model card, Mathematical Reasoning w/ Tools, AIME-25 (Avg@16), value marked ‡ (Heavy Thinking mode: parallel reasoning then heavy thinking) row, LongCat-Flash-Thinking-2601 column"
          }
        ]
      },
      {
        "id": "longcat-flash-thinking-2601:tau2-bench:retail:1",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "tau2-bench",
        "benchmark_name": "τ²-bench",
        "setting": "retail",
        "setting_name": "Retail",
        "score": 88.6,
        "unit": "%",
        "printed": "88.6",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
        "source_title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
        "source_date": "2026-01-20",
        "where": "model card, Evaluation Results table, row 'τ²-Retail (Avg@4)', column 'LongCat-Flash-Thinking-2601'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 4 runs",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "double_entry",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      },
      {
        "id": "longcat-flash-thinking-2601:tau2-bench:airline:1",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "tau2-bench",
        "benchmark_name": "τ²-bench",
        "setting": "airline",
        "setting_name": "Airline",
        "score": 76.5,
        "unit": "%",
        "printed": "76.5",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
        "source_title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
        "source_date": "2026-01-20",
        "where": "model card, Evaluation Results table, row 'τ²-Airline (Avg@4)', column 'LongCat-Flash-Thinking-2601'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 4 runs; airline environment fixes from the Claude Opus 4.5 report",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "double_entry",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      },
      {
        "id": "longcat-flash-thinking-2601:tau2-bench:telecom:1",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "tau2-bench",
        "benchmark_name": "τ²-bench",
        "setting": "telecom",
        "setting_name": "Telecom",
        "score": 99.3,
        "unit": "%",
        "printed": "99.3",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
        "source_title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
        "source_date": "2026-01-20",
        "where": "model card, Evaluation Results table, row 'τ²-Telecom (Avg@4)', column 'LongCat-Flash-Thinking-2601'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 4 runs",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "double_entry",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      },
      {
        "id": "longcat-flash-thinking-2601:swe-bench-verified:default:1",
        "model": "longcat-flash-thinking-2601",
        "model_name": "LongCat-Flash-Thinking-2601",
        "model_date": "2026-01-20",
        "event": "https://frontierlog.ai/event/2026-01-20-longcat-flash-thinking-2601",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 70.0,
        "unit": "%",
        "printed": "70.0",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking-2601",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601",
        "source_title": "LongCat-Flash-Thinking-2601 model card (Hugging Face)",
        "source_date": "2026-01-20",
        "where": "model card, Evaluation Results table, row 'SWE-bench Verified (Avg@5)', column 'LongCat-Flash-Thinking-2601'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 5 runs",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "double_entry",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      }
    ]
  }
}