{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "qwen3-7-max",
    "name": "Qwen3.7-Max",
    "lab": "alibaba",
    "date": "2026-05-20",
    "source": "https://qwen.ai/blog?id=qwen3.7",
    "source_title": "Qwen3.7: The Agent Frontier",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
    "releases": [],
    "variant_of": null,
    "made_by": "Alibaba",
    "url": "https://frontierlog.ai/model/qwen3-7-max",
    "results": [
      {
        "id": "qwen3-7-max:terminal-bench-2-0:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "terminal-bench-2-0",
        "benchmark_name": "Terminal-Bench 2.0",
        "setting": "default",
        "setting_name": "",
        "score": 69.7,
        "unit": "%",
        "printed": "69.7",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'Terminal Bench 2.0-Terminus', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Terminus 2 harness on Harbor; 5h timeout; 256K context; average of 5 runs",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:swe-bench-verified:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 80.4,
        "unit": "%",
        "printed": "80.4",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'SWE-Verified', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "internal harness with bash and file-edit tools; 200K context",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:swe-bench-pro:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "swe-bench-pro",
        "benchmark_name": "SWE-bench Pro",
        "setting": "default",
        "setting_name": "",
        "score": 60.6,
        "unit": "%",
        "printed": "60.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'SWE-Pro', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "internal harness with bash and file-edit tools; 200K context",
        "caveat": "Run on the lab's own corrected version of the public set",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://z.ai/blog/glm-5.2",
            "name": "GLM-5.2",
            "title": "GLM-5.2: Built for Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-06-16",
            "printed": "60.6",
            "where": "Full Benchmark Table, row 'SWE-bench Pro', column 'Qwen3.7-Max'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:mcp-atlas:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "default",
        "setting_name": "",
        "score": 76.4,
        "unit": "%",
        "printed": "76.4",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'MCP-Atlas', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "public set; Gemini 2.5 Pro judge",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://z.ai/blog/glm-5.2",
            "name": "GLM-5.2",
            "title": "GLM-5.2: Built for Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-06-16",
            "printed": "76.4",
            "where": "Full Benchmark Table, row 'MCP-Atlas Public Set', column 'Qwen3.7-Max'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:hle:with-tools:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 53.5,
        "unit": "%",
        "printed": "53.5",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'HLE w/ tools', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://z.ai/blog/glm-5.2",
            "name": "GLM-5.2",
            "title": "GLM-5.2: Built for Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-06-16",
            "printed": "53.5",
            "where": "Full Benchmark Table, row 'HLE w/ Tools (* = full set for Opus 4.8, GPT-5.5, Gemini 3.1 Pro)', column 'Qwen3.7-Max'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:gpqa-diamond:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 92.4,
        "unit": "%",
        "printed": "92.4",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'GPQA Diamond', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "xhigh reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:hle:no-tools:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 41.4,
        "unit": "%",
        "printed": "41.4",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'HLE', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "xhigh reasoning effort",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:livecodebench:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "livecodebench",
        "benchmark_name": "LiveCodeBench",
        "setting": "default",
        "setting_name": "",
        "score": 91.6,
        "unit": "%",
        "printed": "91.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'LiveCodeBench', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "problem window not stated",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:mmlu-pro:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "mmlu-pro",
        "benchmark_name": "MMLU-Pro",
        "setting": "default",
        "setting_name": "",
        "score": 89.6,
        "unit": "%",
        "printed": "89.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "'Performance' table, row 'MMLU-Pro', column 'Qwen3.7-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9d2174c2d8ef254a.png"
      },
      {
        "id": "qwen3-7-max:terminal-bench-2-1:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 74.5,
        "unit": "%",
        "printed": "74.5",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.8",
        "source_title": "Qwen3.8-Max: A New Bar for Coding and Cowork",
        "source_date": "2026-08-03",
        "where": "Qwen3.8 post, 'Full Benchmark Table', row 'Terminal Bench 2.1', column 'Qwen3.7-Max'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "harness not stated",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-7-max:deepswe-1-1:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 21.6,
        "unit": "%",
        "printed": "21.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.8",
        "source_title": "Qwen3.8-Max: A New Bar for Coding and Cowork",
        "source_date": "2026-08-03",
        "where": "Qwen3.8 post, 'Full Benchmark Table', row 'DeepSWE 1.1', column 'Qwen3.7-Max'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "the higher of the Claude Code and mini-SWE-agent harnesses",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-7-max:automationbench:default:1",
        "model": "qwen3-7-max",
        "model_name": "Qwen3.7-Max",
        "model_date": "2026-05-20",
        "event": "https://frontierlog.ai/event/2026-05-20-qwen3-7-max",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 14.2,
        "unit": "%",
        "printed": "14.2",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.7-Max",
        "source": "https://qwen.ai/blog?id=qwen3.8",
        "source_title": "Qwen3.8-Max: A New Bar for Coding and Cowork",
        "source_date": "2026-08-03",
        "where": "Qwen3.8 post, 'Full Benchmark Table', row 'Automation-Bench (Pass@1)', column 'Qwen3.7-Max'",
        "own": false,
        "primary": true,
        "parallel": false,
        "notes": "600-task public subset; pass@1",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      }
    ]
  }
}