{
  "aliases": [],
  "authors": [],
  "details": {},
  "environments": [
    "desktop"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:58Z",
      "role": "primary",
      "sha256": "ea54ea82b86548ff38913ef328ec18152ace71a3fe9bb497bcabcaad24e6a678",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations"
      ],
      "url": "https://raw.githubusercontent.com/showlab/WorldGUI/HEAD/README.md"
    }
  ],
  "id": "github:showlab/worldgui",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:35:58Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/showlab/WorldGUI"
    }
  ],
  "name": "WorldGUI",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/showlab/WorldGUI/HEAD/README.md",
      "target_id": "arxiv:2502.08047",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "611 desktop GUI tasks that agents must complete from varied starting points, shipped with instructional videos and project files, plus the self-reflective WorldGUI-Agent baseline.",
  "topics": [
    "evaluation",
    "robustness"
  ],
  "updated_at": null,
  "url": "https://github.com/showlab/WorldGUI"
}