{
  "api_version": "1",
  "updated": "2026-11-05",
  "latest_event": "2026-11-04",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "longcat-2-5",
    "name": "LongCat-2.5",
    "lab": "meituan",
    "date": "2026-11-01",
    "source": "https://longcat.chat/blog/longcat-2.5/",
    "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
    "releases": [],
    "variant_of": null,
    "made_by": "Meituan",
    "url": "https://frontierlog.ai/model/longcat-2-5",
    "results": [
      {
        "id": "longcat-2-5:terminal-bench-2-1:default:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 88.4,
        "unit": "%",
        "printed": "88.4",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'Terminal Bench v2.1' under 'Code Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness; 512K context; average of 3 runs",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:terminal-bench-4-0:default:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "terminal-bench-4-0",
        "benchmark_name": "Terminal-Bench 4.0",
        "setting": "default",
        "setting_name": "",
        "score": 38.5,
        "unit": "%",
        "printed": "38.5",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'Terminal Bench v4.0' under 'Code Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness; 512K context",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:deepswe-1-1:default:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 64.6,
        "unit": "%",
        "printed": "64.6",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'DeepSWE v1.1' under 'Code Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "mini-swe-agent harness; 1M context; average of 3 runs",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:browsecomp:default:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "browsecomp",
        "benchmark_name": "BrowseComp",
        "setting": "default",
        "setting_name": "",
        "score": 91.9,
        "unit": "%",
        "printed": "91.9",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'BrowseComp' under 'General Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "custom harness with context discarding at 256K; search and browse tools only; up to 1,024 rounds",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:automationbench:default:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 51.8,
        "unit": "%",
        "printed": "51.8",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'AutomationBench v1.0.6' under 'General Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "public v1.0.6 set, all 600 tasks; official evaluation code",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:hle:with-tools:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 63.1,
        "unit": "%",
        "printed": "63.1",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'HLE w/tools' under 'General Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "text-only subset; Claude Code harness; 256K output budget",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:agents-last-exam-1-1:unstated:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "agents-last-exam-1-1",
        "benchmark_name": "Agents' Last Exam v1.1",
        "setting": "unstated",
        "setting_name": "Measure not stated",
        "score": 38.5,
        "unit": "%",
        "printed": "38.5",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'ALE v1.1' under 'General Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "thinking on; harness and task count not stated",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      },
      {
        "id": "longcat-2-5:mcp-atlas:default:1",
        "model": "longcat-2-5",
        "model_name": "LongCat-2.5",
        "model_date": "2026-11-01",
        "event": "https://frontierlog.ai/event/2026-11-01-longcat-2-5",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "default",
        "setting_name": "",
        "score": 83.1,
        "unit": "%",
        "printed": "83.1",
        "reported_by": "meituan",
        "run_by": null,
        "label": "LongCat-2.5",
        "source": "https://longcat.chat/blog/longcat-2.5/",
        "source_title": "LongCat-2.5: Native Multimodality for Agentic Tasks",
        "source_date": "2026-11-01",
        "where": "'Evaluations' section table at the end of the post (rendered by the page's script; load https://longcat.ai/blog/longcat-2.5 in a browser and scroll to the end), row 'MCP Atlas' under 'General Agent', column 'LongCat-2.5'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "max reasoning effort; 256K context",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-11-02",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/2b178d4c19a6dbe7.png"
      }
    ],
    "price": [
      {
        "from": "2026-11-02",
        "listed": true,
        "currency": "CNY",
        "input_per_1m": 2.0,
        "cached_input_per_1m": 0.04,
        "cached_input_derived": false,
        "output_per_1m": 8.0,
        "cache": {
          "kind": "price"
        },
        "tiers": [],
        "printed": {
          "input": "¥2",
          "cached_input": "¥0.04",
          "output": "¥8"
        },
        "printed_unit": "1M tokens",
        "notes": "Limited-time discounted launch price",
        "sources": [
          "https://longcat.chat/platform/docs/pricing/longcat-2.5",
          "https://longcat.chat/platform/docs/api-pay-as-you-go"
        ],
        "check": "corroborated"
      }
    ],
    "context": {
      "from": "2026-11-04",
      "listed": true,
      "window_tokens": 1000000,
      "input_tokens": null,
      "output_tokens": 256000,
      "tiers": [],
      "printed": {
        "window": "1M",
        "input": null,
        "output": "256K"
      },
      "notes": "",
      "sources": [
        "https://longcat.chat/platform/docs/",
        "https://longcat.chat/platform/docs/faq",
        "https://longcat.chat/platform/docs/api/model",
        "https://longcat.chat/platform/docs/api/model-params"
      ],
      "check": "corroborated"
    },
    "prices": [
      {
        "from": "2026-11-02",
        "listed": true,
        "currency": "CNY",
        "input_per_1m": 2.0,
        "cached_input_per_1m": 0.04,
        "cached_input_derived": false,
        "output_per_1m": 8.0,
        "cache": {
          "kind": "price"
        },
        "tiers": [],
        "printed": {
          "input": "¥2",
          "cached_input": "¥0.04",
          "output": "¥8"
        },
        "printed_unit": "1M tokens",
        "notes": "Limited-time discounted launch price",
        "sources": [
          "https://longcat.chat/platform/docs/pricing/longcat-2.5",
          "https://longcat.chat/platform/docs/api-pay-as-you-go"
        ],
        "check": "corroborated"
      }
    ],
    "context_history": [
      {
        "from": "2026-11-04",
        "listed": true,
        "window_tokens": 1000000,
        "input_tokens": null,
        "output_tokens": 256000,
        "tiers": [],
        "printed": {
          "window": "1M",
          "input": null,
          "output": "256K"
        },
        "notes": "",
        "sources": [
          "https://longcat.chat/platform/docs/",
          "https://longcat.chat/platform/docs/faq",
          "https://longcat.chat/platform/docs/api/model",
          "https://longcat.chat/platform/docs/api/model-params"
        ],
        "check": "corroborated"
      }
    ],
    "stories": []
  }
}