{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "BrowserGym browser actions"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/README.md",
          "population": "WorkArena-L1 atomic tasks",
          "qualifier": "exact",
          "unit": "task definitions",
          "value": 33
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/README.md",
          "population": "WorkArena-L1 documented instances",
          "qualifier": "exact",
          "unit": "task instances",
          "value": 19912
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/README.md",
          "population": "WorkArena++ compositional tasks",
          "qualifier": "exact",
          "unit": "task definitions",
          "value": 682
        }
      ],
      "evaluation": "Task-specific checks on ServiceNow workflows; levels and task configurations define different evaluations.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/ServiceNow/WorkArena/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=800&max_results=100&sortBy=submittedDate&sortOrder=descending"
      ],
      "focus": [
        "enterprise web workflows",
        "compositional tasks"
      ],
      "notes": "Definitions and instantiated tasks are different units. ServiceNow instance access is gated. WorkArena-L1 and WorkArena++ should be reported separately.",
      "observations": [
        "multimodal browser observations"
      ],
      "setting": "interactive"
    },
    "leaderboard_url": "https://huggingface.co/spaces/ServiceNow/browsergym-leaderboard"
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "834a48f0346036a0fc591a36f9eb6f513b44a2777a66afa0917f28fc63f29334",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol",
        "details.leaderboard_url"
      ],
      "url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:36:58Z",
      "role": "primary",
      "sha256": "c87e97eb397da04806d53145cf9c13be739fc657bb54dca9318c8c4ed2a36249",
      "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=800&max_results=100&sortBy=submittedDate&sortOrder=descending"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "b192c58991e8ff585cc574615d40e74185404d4b96c1109d423071ab1367344b",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/LICENSE"
    }
  ],
  "id": "github:servicenow/workarena",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:35:57Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/ServiceNow/WorkArena"
    }
  ],
  "name": "WorkArena",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/README.md",
      "target_id": "arxiv:2403.07718",
      "type": "documented_by"
    },
    {
      "evidence_url": "https://raw.githubusercontent.com/ServiceNow/WorkArena/HEAD/README.md",
      "target_id": "arxiv:2407.05291",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Browser-based enterprise workflow tasks built around ServiceNow.",
  "topics": [
    "evaluation",
    "workflow"
  ],
  "updated_at": null,
  "url": "https://github.com/ServiceNow/WorkArena"
}