{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "qwen3-8-max",
    "name": "Qwen3.8-Max",
    "lab": "alibaba",
    "date": "2026-08-03",
    "source": "https://qwen.ai/blog?id=qwen3.8",
    "source_title": "Qwen3.8-Max: A New Bar for Coding and Cowork",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
    "releases": [],
    "variant_of": null,
    "made_by": "Alibaba",
    "url": "https://frontierlog.ai/model/qwen3-8-max",
    "results": [
      {
        "id": "qwen3-8-max:gpqa-diamond:default:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 92.6,
        "unit": "%",
        "printed": "92.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table', row 'GPQA Diamond', column 'Qwen3.8-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-8-max:hle:no-tools:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 43.6,
        "unit": "%",
        "printed": "43.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (first table), row 'HLE' under 'General Capabilities', column 'Qwen3.8-Max' (read via the qwen.ai article API, article 65dfab20-97fb-4932-97cd-4f7da4ab51f5)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "full or text-only set not stated",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-8-max:swe-bench-pro:default:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "swe-bench-pro",
        "benchmark_name": "SWE-bench Pro",
        "setting": "default",
        "setting_name": "",
        "score": 67.7,
        "unit": "%",
        "printed": "67.7",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (first table), row 'SWE-bench Pro' under 'Coding Agent', column 'Qwen3.8-Max' (read via the qwen.ai article API, qwen.ai/api/v2/article/?language=en-US&path=qwen3.8&type=qwen_ai, article 65dfab20-97fb-4932-97cd-4f7da4ab51f5)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness",
        "caveat": "Run on the lab's own corrected version of the public set",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-8-max:deepswe-1-1:default:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "deepswe-1-1",
        "benchmark_name": "DeepSWE v1.1",
        "setting": "default",
        "setting_name": "",
        "score": 56.6,
        "unit": "%",
        "printed": "56.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (first table), row 'DeepSWE 1.1' under 'Coding Agent', column 'Qwen3.8-Max' (read via the qwen.ai article API, article 65dfab20-97fb-4932-97cd-4f7da4ab51f5)",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness, the higher of it and mini-SWE-agent",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-17",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://z.ai/blog/glm-5.3",
            "name": "GLM-5.3",
            "title": "GLM-5.3: Frontier Coding with Emergent Cyber Capabilities",
            "lab": "zai",
            "date": "2026-08-14",
            "printed": "56.6",
            "where": "'Performance across comparison models' table, row 'DeepSWE v1.1', column 'Qwen3.8-Max'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-8-max:terminal-bench-2-1:default:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "terminal-bench-2-1",
        "benchmark_name": "Terminal-Bench 2.1",
        "setting": "default",
        "setting_name": "",
        "score": 86.6,
        "unit": "%",
        "printed": "86.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (first, language/agent HTML table), section 'Coding Agent', row 'Terminal Bench 2.1', column 'Qwen3.8-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Claude Code harness; average of 10 runs; 5h timeout",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-18",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://z.ai/blog/glm-5.3",
            "name": "GLM-5.3",
            "title": "GLM-5.3: Frontier Coding with Emergent Cyber Capabilities",
            "lab": "zai",
            "date": "2026-08-14",
            "printed": "86.6",
            "where": "'Performance across comparison models' table, row 'Terminal Bench 2.1 (Claude Code harness per footnote)', column 'Qwen3.8-Max'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      },
      {
        "id": "qwen3-8-max:osworld-verified:default:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "osworld-verified",
        "benchmark_name": "OSWorld-Verified",
        "setting": "default",
        "setting_name": "",
        "score": 86.1,
        "unit": "%",
        "printed": "86.1",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (second, multimodal HTML table), section 'Visual Agent & Coding', row 'OSWorld-Verified', column 'Qwen3.8-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-18",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9da0b23ee1bc9d3f.png"
      },
      {
        "id": "qwen3-8-max:osworld-2-0:offline-partial:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "osworld-2-0",
        "benchmark_name": "OSWorld 2.0",
        "setting": "offline-partial",
        "setting_name": "Offline set, partial score",
        "score": 46.7,
        "unit": "%",
        "printed": "46.7",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (second, multimodal HTML table), section 'Visual Agent & Coding', row 'OSWorld 2.0', column 'Qwen3.8-Max', second value of the cell",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "partial score (19.4 binary)",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-18",
        "check": "human",
        "corroborated": false,
        "corroborated_on": null,
        "corroborated_by": [],
        "source_capture": "https://frontierlog.ai/captures/9da0b23ee1bc9d3f.png"
      },
      {
        "id": "qwen3-8-max:automationbench:default:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "automationbench",
        "benchmark_name": "AutomationBench",
        "setting": "default",
        "setting_name": "",
        "score": 27.3,
        "unit": "%",
        "printed": "27.3",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (first, language/agent HTML table), General Agent section, row 'Automation-Bench (Pass@1)', column 'Qwen3.8-Max'",
        "own": true,
        "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"
      },
      {
        "id": "qwen3-8-max:hle:with-tools:1",
        "model": "qwen3-8-max",
        "model_name": "Qwen3.8-Max",
        "model_date": "2026-08-03",
        "event": "https://frontierlog.ai/event/2026-08-03-qwen3-8-max",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 56.2,
        "unit": "%",
        "printed": "56.2",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.8-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": "'Full Benchmark Table' (first, language/agent HTML table), General Agent section, row 'HLE w/ tools', column 'Qwen3.8-Max'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "tools not stated",
        "caveat": "",
        "human_verified": true,
        "human_verified_on": "2026-10-19",
        "check": "human",
        "corroborated": true,
        "corroborated_on": "2026-10-19",
        "corroborated_by": [
          {
            "url": "https://huggingface.co/zai-org/GLM-5.3",
            "name": "GLM-5.3 card",
            "title": "zai-org/GLM-5.3 model card",
            "lab": "zai",
            "date": "2026-08-14",
            "printed": "56.2",
            "where": "README Benchmark table, row 'HLE w/ Tools', column 'Qwen3.8-Max'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/10d02db2e5d51286.png"
      }
    ]
  }
}