{
  "api_version": "1",
  "updated": "2026-10-26",
  "latest_event": "2026-10-24",
  "rights": "© Frontier Log, all rights reserved.",
  "model": {
    "slug": "qwen3-6-plus",
    "name": "Qwen3.6-Plus",
    "lab": "alibaba",
    "date": "2026-04-02",
    "source": "https://qwen.ai/blog?id=qwen3.6",
    "source_title": "Qwen3.6-Plus: Towards Real World Agents",
    "flagship": false,
    "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
    "releases": [],
    "variant_of": null,
    "made_by": "Alibaba",
    "url": "https://frontierlog.ai/model/qwen3-6-plus",
    "results": [
      {
        "id": "qwen3-6-plus:swe-bench-verified:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "swe-bench-verified",
        "benchmark_name": "SWE-bench Verified",
        "setting": "default",
        "setting_name": "",
        "score": 78.8,
        "unit": "%",
        "printed": "78.8",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'SWE-bench Verified', column 'Qwen3.6-Plus'",
        "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/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:swe-bench-pro:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "swe-bench-pro",
        "benchmark_name": "SWE-bench Pro",
        "setting": "default",
        "setting_name": "",
        "score": 56.6,
        "unit": "%",
        "printed": "56.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'SWE-bench Pro', column 'Qwen3.6-Plus'",
        "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-5.1",
            "name": "GLM-5.1",
            "title": "GLM-5.1: Towards Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-04-07",
            "printed": "56.6",
            "where": "Benchmark table, row 'SWE-Bench Pro', column 'Qwen3.6-Plus'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:terminal-bench-2-0:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "terminal-bench-2-0",
        "benchmark_name": "Terminal-Bench 2.0",
        "setting": "default",
        "setting_name": "",
        "score": 61.6,
        "unit": "%",
        "printed": "61.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'Terminal-Bench 2.0', column 'Qwen3.6-Plus'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "Terminus 2 harness on Harbor; 3h timeout; 256K context; average of 5 runs",
        "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-5.1",
            "name": "GLM-5.1",
            "title": "GLM-5.1: Towards Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-04-07",
            "printed": "61.6",
            "where": "Benchmark table, row 'Terminal-Bench 2.0 Terminus-2', column 'Qwen3.6-Plus'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:mcp-atlas:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "mcp-atlas",
        "benchmark_name": "MCP Atlas",
        "setting": "default",
        "setting_name": "",
        "score": 74.1,
        "unit": "%",
        "printed": "74.1",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'MCP-Atlas', column 'Qwen3.6-Plus'",
        "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-5.1",
            "name": "GLM-5.1",
            "title": "GLM-5.1: Towards Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-04-07",
            "printed": "74.1",
            "where": "Benchmark table, row 'MCP-Atlas Public Set', column 'Qwen3.6-Plus'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:hle:with-tools:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 50.6,
        "unit": "%",
        "printed": "50.6",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'HLE w/ tool', column 'Qwen3.6-Plus'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "256K context with context folding",
        "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-5.1",
            "name": "GLM-5.1",
            "title": "GLM-5.1: Towards Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-04-07",
            "printed": "50.6",
            "where": "Benchmark table, row 'HLE w/ Tools (* = full set for Opus 4.6, Gemini 3.1 Pro, GPT-5.4)', column 'Qwen3.6-Plus'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:mmlu-pro:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "mmlu-pro",
        "benchmark_name": "MMLU-Pro",
        "setting": "default",
        "setting_name": "",
        "score": 88.5,
        "unit": "%",
        "printed": "88.5",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'MMLU-Pro', column 'Qwen3.6-Plus'",
        "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/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:gpqa-diamond:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "gpqa-diamond",
        "benchmark_name": "GPQA Diamond",
        "setting": "default",
        "setting_name": "",
        "score": 90.4,
        "unit": "%",
        "printed": "90.4",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'GPQA', column 'Qwen3.6-Plus'",
        "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-5.1",
            "name": "GLM-5.1",
            "title": "GLM-5.1: Towards Long-Horizon Tasks",
            "lab": "zai",
            "date": "2026-04-07",
            "printed": "90.4",
            "where": "Benchmark table, row 'GPQA-Diamond', column 'Qwen3.6-Plus'"
          }
        ],
        "source_capture": "https://frontierlog.ai/captures/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:hle:no-tools:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 28.8,
        "unit": "%",
        "printed": "28.8",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'HLE', column 'Qwen3.6-Plus'",
        "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/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:livecodebench:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "livecodebench",
        "benchmark_name": "LiveCodeBench",
        "setting": "default",
        "setting_name": "",
        "score": 87.1,
        "unit": "%",
        "printed": "87.1",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'LiveCodeBench v6', column 'Qwen3.6-Plus'",
        "own": true,
        "primary": true,
        "parallel": false,
        "notes": "LiveCodeBench v6",
        "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/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:hmmt-2025:no-tools:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "hmmt-2025",
        "benchmark_name": "HMMT February 2025",
        "setting": "no-tools",
        "setting_name": "No tools",
        "score": 96.7,
        "unit": "%",
        "printed": "96.7",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Language' table, row 'HMMT Feb 25', column 'Qwen3.6-Plus'",
        "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/6f4855b376c670b4.png"
      },
      {
        "id": "qwen3-6-plus:osworld-verified:default:1",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "osworld-verified",
        "benchmark_name": "OSWorld-Verified",
        "setting": "default",
        "setting_name": "",
        "score": 62.5,
        "unit": "%",
        "printed": "62.5",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.6",
        "source_title": "Qwen3.6-Plus: Towards Real World Agents",
        "source_date": "2026-04-02",
        "where": "'Performance' section, 'Vision Language' table, row 'OSWorld-Verified', column 'Qwen3.6-Plus'",
        "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/87e3a9ddb42dfe8b.png"
      },
      {
        "id": "qwen3-6-plus:hle:with-tools:2",
        "model": "qwen3-6-plus",
        "model_name": "Qwen3.6-Plus",
        "model_date": "2026-04-02",
        "event": "https://frontierlog.ai/event/2026-04-02-qwen3-6-plus",
        "benchmark": "hle",
        "benchmark_name": "Humanity's Last Exam",
        "setting": "with-tools",
        "setting_name": "With tools",
        "score": 50.2,
        "unit": "%",
        "printed": "50.2",
        "reported_by": "alibaba",
        "run_by": null,
        "label": "Qwen3.6-Plus",
        "source": "https://qwen.ai/blog?id=qwen3.7",
        "source_title": "Qwen3.7: The Agent Frontier",
        "source_date": "2026-05-20",
        "where": "Qwen3.7 post, 'Performance' table, row 'HLE w/ tools', column 'Qwen3.6-Plus'",
        "own": false,
        "primary": false,
        "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"
      }
    ]
  }
}