{
  "aliases": [],
  "authors": [],
  "details": {},
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:40:51Z",
      "role": "primary",
      "sha256": "dfcbaa088cc21dd4e3c67d6eb3b3a1dc476217165ce2ca0daa2facfda71b5a38",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations"
      ],
      "url": "https://github.com/jacklishufan/MobileWorld"
    }
  ],
  "id": "github:jacklishufan/mobileworld",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:40:51Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/jacklishufan/MobileWorld"
    }
  ],
  "name": "MobileWorldBench",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://github.com/jacklishufan/MobileWorld",
      "target_id": "arxiv:2512.14014",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Benchmark of semantic world modeling for mobile agents, with question-answering tasks and GPT-judged generation tasks, plus training data built on AitW and AndroidControl screens.",
  "topics": [
    "evaluation",
    "mobile-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/jacklishufan/MobileWorld"
}