{
  "aliases": [],
  "authors": [],
  "details": {
    "availability": "Ungated v1.0 JSON task-definition file.",
    "benchmark_protocol": {
      "actions": [
        "mobile GUI actions through a separately configured agent"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md",
          "population": "MobBench tasks used in the paper",
          "qualifier": "exact",
          "unit": "tasks",
          "value": 50
        }
      ],
      "evaluation": "The publisher reports a fifty-task real-device evaluation; the inspected release does not establish an automatic correctness judge.",
      "evidence_urls": [
        "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"
      ],
      "focus": [
        "mobile task completion"
      ],
      "notes": "Task definitions are distinct from device images, agent execution and automated scoring.",
      "observations": [
        "Android device interface"
      ],
      "setting": "interactive"
    },
    "license_review": {
      "data": {
        "evidence_urls": [
          "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"
        ],
        "reason": "Dataset-card declaration for the MobBench task-definition release only."
      }
    },
    "release_revision": "28941d10c49a16efb991d4157e512e14204bf3d6"
  },
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:32:07Z",
      "role": "primary",
      "sha256": "231a8f483256c774840c99383ab6536520a0aed0f04d62b4d64f1f59477b906e",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "notes",
        "relations",
        "details.benchmark_protocol",
        "licenses.data"
      ],
      "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T12:32:07Z",
      "role": "primary",
      "sha256": "4e7225f956d7cee98fe671e7bfd91fc407d87dd805d8f0c11c3b0c839714ccf3",
      "supports": [
        "identity",
        "release_status",
        "details.release_revision"
      ],
      "url": "https://huggingface.co/api/datasets/OpenDFM/MobA-MobBench"
    }
  ],
  "id": "url:b53e03a6e4ca4226d126",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T12:32:07Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "Dataset-card declaration for the MobBench task-definition release only.",
      "declared": "cc-by-nc-sa-4.0",
      "retrieved_at": "2026-10-17T12:32:07Z",
      "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench"
    }
  ],
  "name": "MobBench task definitions",
  "notes": "The ungated manifest lists MobBench_tasks_release_v1.0.json and bilingual cards. The card reports fifty tasks; no sample records were downloaded to recount them. This release supplies task definitions and agent setup guidance, not an independently verified automatic judge or a bundled Android environment. The data card declares CC-BY-NC-SA-4.0; code and model licenses are separate.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench/raw/main/README.md",
      "target_id": "arxiv:2410.13757",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "A public set of real-device mobile task definitions used to evaluate MobA, with Chinese and English task material packaged in a versioned JSON release.",
  "topics": [
    "evaluation",
    "mobile-navigation"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/OpenDFM/MobA-MobBench"
}