{
  "api_version": "1",
  "updated": "2026-11-10",
  "latest_event": "2026-11-09",
  "rights": "© Frontier Log, all rights reserved.",
  "benchmark": {
    "slug": "osworld-2-0-no-release",
    "name": "OSWorld 2.0, no release named",
    "family": "osworld",
    "unit": "%",
    "higher_is_better": true,
    "status": "superseded",
    "active": false,
    "superseded_by": "osworld-2-1",
    "retired": null,
    "benchmark_url": "https://huggingface.co/papers/2606.29537",
    "introduced": "2026-06-28",
    "creator": "XLANG Lab",
    "introduced_source": "https://arxiv.org/abs/2606.29537",
    "settings": [
      {
        "setting": "unstated",
        "name": "Set and scoring not stated",
        "url": "https://frontierlog.ai/benchmark/osworld-2-0-no-release",
        "results": 4
      },
      {
        "setting": "set-unstated-partial",
        "name": "Set not stated, partial score",
        "url": "https://frontierlog.ai/benchmark/osworld-2-0-no-release/set-unstated-partial",
        "results": 1
      }
    ]
  },
  "total": 1,
  "results": [
    {
      "id": "qwen3-8-max:osworld-2-0-no-release:set-unstated-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-no-release",
      "benchmark_name": "OSWorld 2.0, no release named",
      "setting": "set-unstated-partial",
      "setting_name": "Set not stated, 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": "binary score 19.4 in the same cell",
      "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"
    }
  ]
}