{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "mobile interface operations",
        "clarification requests"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md",
          "population": "MobileGUI-VBench release",
          "qualifier": "exact",
          "unit": "tasks",
          "value": 150
        },
        {
          "basis": "reported",
          "evidence_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md",
          "population": "MobileGUI-VBench release",
          "qualifier": "exact",
          "unit": "mobile apps",
          "value": 40
        }
      ],
      "evaluation": "Published task definitions include preconditions and clarification requirements; the metadata review does not independently validate the reported agent scores.",
      "evidence_urls": [
        "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md"
      ],
      "focus": [
        "mobile task completion",
        "clarification behavior",
        "cross-app tasks"
      ],
      "notes": "The card describes 140 single-app and 10 cross-app tasks. Task and app counts are different units.",
      "observations": [
        "mobile app interfaces"
      ],
      "setting": "interactive"
    },
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/tree/main",
    "gated": false,
    "hub_id": "vivo-ai/MobileGUI-VBench"
  },
  "environments": [
    "unspecified"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:42:32Z",
      "role": "primary",
      "sha256": "422ff6a557a1aabd8f6c6ef26e5fd05b992f4acf0e5128ab8bc437021fcc5ea7",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:42:32Z",
      "role": "primary",
      "sha256": "5850fc58f54c877cffe328dba2a0b5e3e98767637aae6d6efd9a037cf06eabce",
      "supports": [
        "identity",
        "release_status",
        "details",
        "licenses.data"
      ],
      "url": "https://huggingface.co/api/datasets/vivo-ai/MobileGUI-VBench"
    }
  ],
  "id": "url:d7a4f34a6a5202af5f64",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T02:42:32Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench"
    }
  ],
  "name": "MobileGUI-VBench",
  "notes": "Public task files are available as JSONL and XLSX with documentation. The card explicitly declares Apache-2.0 for the dataset, despite having no license field in its YAML metadata. It identifies mobile apps without fixing an operating-system taxonomy; model scores are not imported.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench/raw/main/README.md",
      "target_id": "arxiv:2609.12394",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Mobile-app task definitions covering everyday scenarios, with annotated preconditions and clarification requirements for evaluating agent behavior.",
  "topics": [
    "evaluation",
    "mobile-navigation",
    "cross-app"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/vivo-ai/MobileGUI-VBench"
}