{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Public task definitions, evaluator and container orchestration source.",
    "benchmark_protocol": {
      "actions": [
        "Android GUI operations",
        "MCP calls when enabled",
        "agent-user interaction when enabled"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md",
          "population": "README benchmark overview",
          "qualifier": "exact",
          "unit": "tasks",
          "value": 201
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md",
          "population": "README benchmark overview",
          "qualifier": "exact",
          "unit": "mobile applications",
          "value": 20
        }
      ],
      "evaluation": "The publisher documents text-answer matching, backend database verification, local-storage inspection and application callbacks.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md"
      ],
      "focus": [
        "Android task completion",
        "agent-user interaction",
        "hybrid GUI and MCP use"
      ],
      "notes": "Publisher-reported inventory. GUI-only, agent-user and MCP-augmented configurations have different dependencies and task eligibility; preserve enabled modes and step budget with results.",
      "observations": [
        "Android application interface",
        "user-agent interaction when enabled"
      ],
      "setting": "interactive"
    },
    "leaderboard_url": "https://tongyi-mai.github.io/MobileWorld/#leaderboard",
    "license_review": {
      "code": {
        "evidence_urls": [
          "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/LICENSE"
        ],
        "reason": "Repository code license; self-hosted applications, model APIs and MCP services keep their own terms."
      }
    },
    "repository_revision": "e7eee8981135ecbe39005a231edf63574defd79c"
  },
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:12:16Z",
      "role": "primary",
      "sha256": "fbc306b3414dfdb230171358efd6eb8d67573fbb94e11487a4a7e971e2abf0d9",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "notes",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:12:15Z",
      "role": "primary",
      "sha256": "266e1fe5b5b1a4c1540ab0fd5eba206395084ee283f0079f424930a156cf8e18",
      "supports": [
        "identity"
      ],
      "url": "https://api.github.com/repos/Tongyi-MAI/MobileWorld"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:14:08Z",
      "role": "primary",
      "sha256": "14500ed2dfa14bb5c34211090f0c8827e4a16c3233e35a2d695c0d7261f9358b",
      "supports": [
        "release_status"
      ],
      "url": "https://api.github.com/repos/Tongyi-MAI/MobileWorld/git/trees/main?recursive=1"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:14:09Z",
      "role": "primary",
      "sha256": "b09fcaf4fbc265223c2479c410beef2b98c5e687c78ecedf3452aa12ffc465f1",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/LICENSE"
    }
  ],
  "id": "github:tongyi-mai/mobileworld",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T09:12:16Z",
  "licenses": {
    "code": {
      "basis": "Repository code license; self-hosted applications, model APIs and MCP services keep their own terms.",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-17T09:14:09Z",
      "url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/Tongyi-MAI/MobileWorld"
    }
  ],
  "name": "MobileWorld (Tongyi-MAI)",
  "notes": "This is Tongyi-MAI/MobileWorld, distinct from jacklishufan/MobileWorld (MobileWorldBench). Public source includes task definitions, verification logic and environment orchestration. The README reports 201 tasks across 20 applications; this is not an independent count of the evolving task tree. Linux/KVM or WSL2/KVM is required by the documented host setup, with macOS support in progress. MCP and simulated-user settings can require separate external services.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/Tongyi-MAI/MobileWorld/HEAD/README.md",
      "target_id": "arxiv:2512.19432",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "A containerized Android evaluation environment with GUI-only, agent-user interaction and MCP-augmented tasks, plus checks on application and backend state.",
  "topics": [
    "evaluation",
    "mobile-navigation",
    "human-in-the-loop",
    "tool-integration"
  ],
  "updated_at": null,
  "url": "https://github.com/Tongyi-MAI/MobileWorld"
}