{
  "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    "status": "superseded",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": 5,
  "results": [
    {
      "id": "gpt-5-6-luna:osworld-2-0-no-release:unstated:1",
      "model": "gpt-5-6-luna",
      "model_name": "GPT-5.6 Luna",
      "model_date": "2026-07-09",
      "event": "https://frontierlog.ai/event/2026-07-09-gpt-5-6",
      "benchmark": "osworld-2-0-no-release",
      "benchmark_name": "OSWorld 2.0, no release named",
      "setting": "unstated",
      "setting_name": "Set and scoring not stated",
      "score": 45.6,
      "unit": "%",
      "printed": "45.6%",
      "reported_by": "openai",
      "run_by": null,
      "label": "GPT‑5.6 Luna",
      "source": "https://openai.com/index/gpt-5-6",
      "source_title": "GPT-5.6: Frontier intelligence that scales with your ambition",
      "source_date": "2026-07-09",
      "where": "computer-use/agentic eval table (HTML), row 'OSWorld 2.0', column 'GPT‑5.6 Luna'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": true,
      "human_verified_on": "2026-10-26",
      "check": "human",
      "corroborated": false,
      "corroborated_on": null,
      "corroborated_by": [],
      "source_capture": "https://frontierlog.ai/captures/2eabd1ed1ba3ff72.png"
    },
    {
      "id": "gpt-5-6-sol:osworld-2-0-no-release:unstated:1",
      "model": "gpt-5-6-sol",
      "model_name": "GPT-5.6 Sol",
      "model_date": "2026-07-09",
      "event": "https://frontierlog.ai/event/2026-07-09-gpt-5-6",
      "benchmark": "osworld-2-0-no-release",
      "benchmark_name": "OSWorld 2.0, no release named",
      "setting": "unstated",
      "setting_name": "Set and scoring not stated",
      "score": 62.6,
      "unit": "%",
      "printed": "62.6%",
      "reported_by": "openai",
      "run_by": null,
      "label": "GPT‑5.6 Sol",
      "source": "https://openai.com/index/gpt-5-6",
      "source_title": "GPT-5.6: Frontier intelligence that scales with your ambition",
      "source_date": "2026-07-09",
      "where": "computer-use/agentic eval table (HTML), row 'OSWorld 2.0', column 'GPT‑5.6 Sol'",
      "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/2eabd1ed1ba3ff72.png"
    },
    {
      "id": "gpt-5-6-terra:osworld-2-0-no-release:unstated:1",
      "model": "gpt-5-6-terra",
      "model_name": "GPT-5.6 Terra",
      "model_date": "2026-07-09",
      "event": "https://frontierlog.ai/event/2026-07-09-gpt-5-6",
      "benchmark": "osworld-2-0-no-release",
      "benchmark_name": "OSWorld 2.0, no release named",
      "setting": "unstated",
      "setting_name": "Set and scoring not stated",
      "score": 50.2,
      "unit": "%",
      "printed": "50.2%",
      "reported_by": "openai",
      "run_by": null,
      "label": "GPT‑5.6 Terra",
      "source": "https://openai.com/index/gpt-5-6",
      "source_title": "GPT-5.6: Frontier intelligence that scales with your ambition",
      "source_date": "2026-07-09",
      "where": "computer-use/agentic eval table (HTML), row 'OSWorld 2.0', column 'GPT‑5.6 Terra'",
      "own": true,
      "primary": true,
      "parallel": false,
      "notes": "",
      "caveat": "",
      "human_verified": false,
      "human_verified_on": null,
      "check": "corroborated",
      "corroborated": true,
      "corroborated_on": "2026-10-26",
      "corroborated_by": [
        {
          "url": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/",
          "name": "Gemini 3.8 Flash and 3.8 Flash Cyber",
          "title": "Introducing Gemini 3.8 Flash and 3.8 Flash Cyber",
          "lab": "google",
          "date": "2026-09-02",
          "printed": "50.2%",
          "where": "Gemini 3.8 Flash launch blog, benchmark table image, row 'OSWorld-2.0' (Partial score, batch tool enabled), column 'GPT-5.6 Terra'."
        },
        {
          "url": "https://deepmind.google/models/model-cards/gemini-3-7-flash/",
          "name": "Gemini 3.7 Flash card",
          "title": "Gemini 3.7 Flash model card",
          "lab": "google",
          "date": "2026-08-13",
          "printed": "50.2%",
          "where": "Gemini 3.7 Flash model card, Results table, row 'OSWorld-2.0', column 'GPT-5.6 Terra'; set/scoring not stated."
        },
        {
          "url": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/",
          "name": "Gemini 3.7 Flash",
          "title": "Introducing Gemini 3.7 Flash",
          "lab": "google",
          "date": "2026-08-13",
          "printed": "50.2%",
          "where": "Gemini 3.7 Flash launch blog, benchmark table image, row 'OSWorld-2.0', column 'GPT-5.6 Terra'; set/scoring not stated."
        }
      ],
      "source_capture": "https://frontierlog.ai/captures/2eabd1ed1ba3ff72.png"
    },
    {
      "id": "claude-opus-5:osworld-2-0-no-release:unstated:1",
      "model": "claude-opus-5",
      "model_name": "Claude Opus 5",
      "model_date": "2026-07-24",
      "event": "https://frontierlog.ai/event/2026-07-24-claude-opus-5",
      "benchmark": "osworld-2-0-no-release",
      "benchmark_name": "OSWorld 2.0, no release named",
      "setting": "unstated",
      "setting_name": "Set and scoring not stated",
      "score": 70.6,
      "unit": "%",
      "printed": "70.6%",
      "reported_by": "anthropic",
      "run_by": null,
      "label": "Opus 5",
      "source": "https://www.anthropic.com/news/claude-opus-5",
      "source_title": "Introducing Claude Opus 5",
      "source_date": "2026-07-24",
      "where": "benchmark table image, row 'Computer use / OSWorld 2.0', column 'Opus 5'",
      "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_image": "https://frontierlog.ai/sources/924165396ca89130.png",
      "source_image_original": "https://www-cdn.anthropic.com/images/4zrzovbb/website/a8fb4f77a9fe240e6f27f3bdc47a137f3c74a29d-2600x2578.png"
    },
    {
      "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"
    }
  ]
}