{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "mouse and keyboard via PyAutoGUI"
      ],
      "counts": [
        {
          "basis": "computed",
          "evidence_url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/evaluation_examples/test_all.json",
          "population": "test_all.json",
          "qualifier": "exact",
          "unit": "task definitions",
          "value": 369
        },
        {
          "basis": "computed",
          "evidence_url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/evaluation_examples/test_nogdrive.json",
          "population": "test_nogdrive.json",
          "qualifier": "exact",
          "unit": "task definitions",
          "value": 361
        }
      ],
      "evaluation": "Task-specific execution-based evaluators inspect application or system state.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/README.md",
        "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50",
        "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/evaluation_examples/test_all.json",
        "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/evaluation_examples/test_nogdrive.json"
      ],
      "focus": [
        "task completion",
        "cross-application workflows"
      ],
      "notes": "Counts were computed from unique task identifiers in the two inspected manifests. The subsets differ; record the manifest, repository revision, agent interface, and step budget with a score.",
      "observations": [
        "screenshots"
      ],
      "setting": "interactive"
    },
    "leaderboard_url": "https://os-world.github.io/"
  },
  "environments": [
    "desktop",
    "linux",
    "windows",
    "macos"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "83b8684c2f4ac4f31996b8b4752195fcb6cc5429f89d92398177b9b721d787fc",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol",
        "details.leaderboard_url"
      ],
      "url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:31:28Z",
      "role": "primary",
      "sha256": "be244bfae7f89ef9449b69d85aac44295eb7b5f7e5e1bbedd76df312696676a7",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://export.arxiv.org/api/query?id_list=2403.03186%2C2403.03788%2C2403.07718%2C2403.10170%2C2403.11905%2C2403.16971%2C2403.17918%2C2403.20271%2C2404.01549%2C2404.01744%2C2404.02475%2C2404.03648%2C2404.05427%2C2404.05719%2C2404.05955%2C2404.06474%2C2404.07972%2C2404.08755%2C2404.08860%2C2404.08948%2C2404.09992%2C2404.10887%2C2404.11459%2C2404.16006%2C2404.16048%2C2404.16054%2C2404.16660%2C2404.18074%2C2404.19296%2C2405.00516%2C2405.11120%2C2405.12842%2C2405.14573%2C2405.14751%2C2405.15793%2C2405.16247%2C2405.20309%2C2406.01014%2C2406.01623%2C2406.03679%2C2406.06947%2C2406.07822%2C2406.08184%2C2406.08340%2C2406.08451%2C2406.10227%2C2406.10819%2C2406.11317%2C2406.11896%2C2406.12373&max_results=50"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T11:34:59Z",
      "role": "primary",
      "sha256": "9ebc5187cbd727ef26c24626820076b102fff812863c640a67c467fea9542ab5",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/evaluation_examples/test_all.json"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T11:34:59Z",
      "role": "primary",
      "sha256": "fcb9497e93a8986407345d3012c872c9c2fed253420730fbea64ccfcace67dbb",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/evaluation_examples/test_nogdrive.json"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "a8d1d88a0f9cce3cdbff73b03a80dc5e5d69e3ba2443946c268815a550c9e0ec",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/LICENSE"
    }
  ],
  "id": "github:xlang-ai/osworld",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:35:57Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/xlang-ai/OSWorld"
    }
  ],
  "name": "OSWorld",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/xlang-ai/OSWorld/HEAD/README.md",
      "target_id": "arxiv:2404.07972",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Execution-based evaluation of agents performing tasks in real desktop environments.",
  "topics": [
    "evaluation",
    "cross-app"
  ],
  "updated_at": null,
  "url": "https://github.com/xlang-ai/OSWorld"
}