{
  "api_version": "1",
  "updated": "2026-10-28",
  "latest_event": "2026-10-27",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "longcat-flash-thinking",
    "name": "LongCat-Flash-Thinking",
    "lab": "meituan",
    "date": "2025-09-22",
    "source": "https://tech.meituan.com/2025/09/22/LongCat-Flash-Thinking.html",
    "source_title": "LongCat-Flash-Thinking 正式发布，更强、更专业，保持极速！",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
    "releases": [],
    "variant_of": null,
    "made_by": "Meituan",
    "url": "https://frontierlog.ai/model/longcat-flash-thinking",
    "results": [
      {
        "id": "longcat-flash-thinking:livecodebench:default:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "livecodebench",
        "benchmark_name": "LiveCodeBench",
        "setting": "default",
        "setting_name": "",
        "score": 79.4,
        "unit": "%",
        "printed": "79.4",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://tech.meituan.com/2025/09/22/LongCat-Flash-Thinking.html",
        "source_title": "LongCat-Flash-Thinking 正式发布，更强、更专业，保持极速！",
        "source_date": "2025-09-22",
        "where": "capability list, coding item (sentence on LiveCodeBench); 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",
            "name": "LongCat-Flash-Thinking card",
            "title": "LongCat-Flash-Thinking model card (Hugging Face)",
            "lab": "meituan",
            "date": "2025-09-22",
            "printed": "79.4",
            "where": "Evaluation table, LiveCodeBench (Mean@4) row, LongCat-Flash-Thinking column"
          }
        ]
      },
      {
        "id": "longcat-flash-thinking:aime-2024:no-tools:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "aime-2024",
        "benchmark_name": "AIME 2024",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 93.3,
        "unit": "%",
        "printed": "93.3",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://tech.meituan.com/2025/09/22/LongCat-Flash-Thinking.html",
        "source_title": "LongCat-Flash-Thinking 正式发布，更强、更专业，保持极速！",
        "source_date": "2025-09-22",
        "where": "benchmark bar chart image, panel 'AIME-24 (Mean@32)', value label on the LongCat-Flash-Thinking bar",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 32 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",
            "name": "LongCat-Flash-Thinking card",
            "title": "LongCat-Flash-Thinking model card (Hugging Face)",
            "lab": "meituan",
            "date": "2025-09-22",
            "printed": "93.3",
            "where": "Evaluation table, AIME24 (Mean@32) row, LongCat-Flash-Thinking column"
          }
        ],
        "source_image": "https://frontierlog.ai/sources/d06bec885c54b691.png",
        "source_image_original": "https://p0.meituan.net/meituantechblog/b3cc3f8aba974e16c322cd5d29cf8138333495.png"
      },
      {
        "id": "longcat-flash-thinking:mmlu-pro:default:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "mmlu-pro",
        "benchmark_name": "MMLU-Pro",
        "setting": "default",
        "setting_name": "",
        "score": 82.6,
        "unit": "%",
        "printed": "82.6",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking",
        "source_title": "LongCat-Flash-Thinking model card (Hugging Face)",
        "source_date": "2025-09-22",
        "where": "model card, benchmark table, row 'MMLU-Pro (acc)', column 'LongCat-Flash-Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "double_entry",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      },
      {
        "id": "longcat-flash-thinking:aime-2025:no-tools:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "aime-2025",
        "benchmark_name": "AIME 2025",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 90.6,
        "unit": "%",
        "printed": "90.6",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking",
        "source_title": "LongCat-Flash-Thinking model card (Hugging Face)",
        "source_date": "2025-09-22",
        "where": "model card, benchmark table, row 'AIME25 (Mean@32)', column 'LongCat-Flash-Thinking'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "average of 32 runs",
        "caveat": "",
        "human_verified": false,
        "human_verified_on": null,
        "check": "double_entry",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": []
      },
      {
        "id": "longcat-flash-thinking:tau2-bench:retail:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "tau2-bench",
        "benchmark_name": "τ²-bench",
        "setting": "retail",
        "setting_name": "Retail",
        "score": 71.5,
        "unit": "%",
        "printed": "71.5",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking",
        "source_title": "LongCat-Flash-Thinking model card (Hugging Face)",
        "source_date": "2025-09-22",
        "where": "model card, benchmark table, row 'τ²-Bench-Retail (Mean@4)', column 'LongCat-Flash-Thinking'",
        "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:tau2-bench:airline:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "tau2-bench",
        "benchmark_name": "τ²-bench",
        "setting": "airline",
        "setting_name": "Airline",
        "score": 67.5,
        "unit": "%",
        "printed": "67.5",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking",
        "source_title": "LongCat-Flash-Thinking model card (Hugging Face)",
        "source_date": "2025-09-22",
        "where": "model card, benchmark table, row 'τ²-Bench-Airline (Mean@4)', column 'LongCat-Flash-Thinking'",
        "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:tau2-bench:telecom:1",
        "model": "longcat-flash-thinking",
        "model_name": "LongCat-Flash-Thinking",
        "model_date": "2025-09-22",
        "event": "https://frontierlog.ai/event/2025-09-22-longcat-flash-thinking",
        "benchmark": "tau2-bench",
        "benchmark_name": "τ²-bench",
        "setting": "telecom",
        "setting_name": "Telecom",
        "score": 83.1,
        "unit": "%",
        "printed": "83.1",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-Flash-Thinking",
        "source": "https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking",
        "source_title": "LongCat-Flash-Thinking model card (Hugging Face)",
        "source_date": "2025-09-22",
        "where": "model card, benchmark table, row 'τ²-Bench-Telecom (Mean@4)', column 'LongCat-Flash-Thinking'",
        "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": []
      }
    ]
  }
}