{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "mobile GUI operations"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending",
          "population": "AppSim-Bench paper-described release",
          "qualifier": "exact",
          "reference_url": "https://arxiv.org/abs/2609.07712",
          "unit": "tasks",
          "value": 557
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/Acrab-Agentic-Labs/AppSim/HEAD/README.md",
          "population": "published simulated app set",
          "qualifier": "exact",
          "unit": "applications",
          "value": 17
        }
      ],
      "evaluation": "Controlled backend data and outcome-based task verification.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/Acrab-Agentic-Labs/AppSim/HEAD/README.md",
        "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"
      ],
      "focus": [
        "mobile task completion"
      ],
      "notes": "Use the simulated apps and controlled backend state supplied by the benchmark. Desktop host instructions are not the platform being evaluated.",
      "observations": [
        "mobile interfaces"
      ],
      "setting": "interactive"
    }
  },
  "environments": [
    "android"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T10:42:12Z",
      "role": "primary",
      "sha256": "12dc2afe339c1ed66e4a6a4ccf5ae13d27ce32f452960341529a4b9016f69059",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/Acrab-Agentic-Labs/AppSim/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:36:32Z",
      "role": "primary",
      "sha256": "13d3fb5811d203f2e6b80eb45d30ebc0b3cfefd88e2034ffa3b1b80687bef285",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://export.arxiv.org/api/query?search_query=%28ti%3A%22computer+use%22+OR+ti%3A%22computer-use%22+OR+ti%3A%22GUI+agent%22+OR+ti%3A%22GUI+agents%22+OR+ti%3A%22GUI+grounding%22+OR+ti%3A%22web+agents%22+OR+ti%3A%22browser+agent%22%29+AND+submittedDate%3A%5B200001010000+TO+202610160636%5D&start=100&max_results=100&sortBy=submittedDate&sortOrder=descending"
    }
  ],
  "id": "github:acrab-agentic-labs/appsim",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T10:42:12Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/Acrab-Agentic-Labs/AppSim"
    }
  ],
  "name": "AppSim-Bench",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/Acrab-Agentic-Labs/AppSim/HEAD/README.md",
      "target_id": "arxiv:2609.07712",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Simulated mobile applications and evaluation tooling for reproducible GUI-agent tasks with controlled application state.",
  "topics": [
    "evaluation",
    "sandbox"
  ],
  "updated_at": null,
  "url": "https://github.com/Acrab-Agentic-Labs/AppSim"
}