{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "Python code",
        "application API calls"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50",
          "population": "original AppWorld benchmark (2024 paper)",
          "qualifier": "exact",
          "reference_url": "https://arxiv.org/abs/2407.18901",
          "unit": "tasks",
          "value": 750
        },
        {
          "basis": "reported",
          "evidence_url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50",
          "population": "original AppWorld environment (2024 paper)",
          "qualifier": "exact",
          "reference_url": "https://arxiv.org/abs/2407.18901",
          "unit": "applications",
          "value": 9
        }
      ],
      "evaluation": "State-based unit tests check task outcomes and unintended changes.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/stonybrooknlp/appworld/HEAD/README.md",
        "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"
      ],
      "focus": [
        "interactive coding",
        "cross-app tool use"
      ],
      "notes": "This is an adjacent API/coding benchmark, not a screenshot-only task suite. Preserve the named release; task counts here refer to the original paper.",
      "observations": [
        "API documentation",
        "execution feedback"
      ],
      "setting": "interactive"
    },
    "leaderboard_url": "https://appworld.dev/appworld/leaderboard"
  },
  "environments": [
    "unspecified"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T10:45:03Z",
      "role": "primary",
      "sha256": "f4049141b6e520217395b7ccd9f27048c8e0f90331690dcbef300d2bc4ff7bdd",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol",
        "details.leaderboard_url"
      ],
      "url": "https://raw.githubusercontent.com/stonybrooknlp/appworld/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:31:32Z",
      "role": "primary",
      "sha256": "b9a83994d8ac36ccdb606a5219511f8bb35ad3948ade4f9f3e28d386221aedfb",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://export.arxiv.org/api/query?id_list=2406.12814%2C2406.13719%2C2406.14056%2C2406.14250%2C2406.14314%2C2406.18082%2C2406.19263%2C2407.00993%2C2407.01476%2C2407.01489%2C2407.01511%2C2407.01558%2C2407.03037%2C2407.03913%2C2407.04346%2C2407.05291%2C2407.07061%2C2407.08850%2C2407.09018%2C2407.09295%2C2407.10956%2C2407.13032%2C2407.13063%2C2407.15673%2C2407.15711%2C2407.16741%2C2407.17490%2C2407.18901%2C2407.19056%2C2407.20183%2C2408.00203%2C2408.02544%2C2408.06327%2C2408.07199%2C2408.11824%2C2408.15978%2C2409.02453%2C2409.04566%2C2409.07429%2C2409.08264%2C2409.09354%2C2409.10741%2C2409.11295%2C2409.13711%2C2409.14337%2C2409.14818%2C2409.15441%2C2409.15637%2C2409.17140%2C2409.20566&max_results=50"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T10:48:42Z",
      "role": "primary",
      "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/StonyBrookNLP/appworld/HEAD/LICENSE"
    }
  ],
  "id": "github:stonybrooknlp/appworld",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T10:45:03Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-16T10:48:42Z",
      "url": "https://raw.githubusercontent.com/StonyBrookNLP/appworld/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/StonyBrookNLP/appworld"
    }
  ],
  "name": "AppWorld",
  "notes": "Primarily API and coding interaction; included as an adjacent comparison for GUI and hybrid agents.",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/stonybrooknlp/appworld/HEAD/README.md",
      "target_id": "arxiv:2407.18901",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "adjacent",
  "summary": "Simulated applications, user data, and state-based task checks for evaluating agents that interact through APIs and code.",
  "topics": [
    "evaluation",
    "tool-integration",
    "cross-app"
  ],
  "updated_at": null,
  "url": "https://github.com/StonyBrookNLP/appworld"
}