{
  "aliases": [],
  "authors": [],
  "details": {},
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:58Z",
      "role": "primary",
      "sha256": "e1d75e8a196f19af6050c53694383f069561244c810ca259c5f8075ee91f72b1",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations"
      ],
      "url": "https://raw.githubusercontent.com/MobileAgentBench/mobile-agent-bench/HEAD/README.md"
    }
  ],
  "id": "github:mobileagentbench/mobile-agent-bench",
  "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/MobileAgentBench/mobile-agent-bench"
    }
  ],
  "name": "MobileAgentBench",
  "notes": "",
  "published_at": null,
  "relations": [],
  "review_status": "curated",
  "scope": "core",
  "summary": "Automated benchmark for mobile LLM agents whose default tasks use ten Simple Mobile Tools Android apps, installed as a Python library that detects task completion.",
  "topics": [
    "evaluation",
    "mobile-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/MobileAgentBench/mobile-agent-bench"
}