{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "browser element actions"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/web-arena-x/webarena/HEAD/README.md",
          "population": "canonical WebArena evaluation suite",
          "qualifier": "exact",
          "unit": "task examples",
          "value": 812
        }
      ],
      "evaluation": "Functional correctness of completed web tasks.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/web-arena-x/webarena/HEAD/README.md",
        "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"
      ],
      "focus": [
        "web task completion"
      ],
      "notes": "The canonical repository documents self-hosted websites and environment resets. Its README recommends BrowserGym/AgentLab for newer infrastructure; harness changes must be recorded.",
      "observations": [
        "HTML or accessibility tree"
      ],
      "setting": "interactive"
    },
    "leaderboard_url": "https://docs.google.com/spreadsheets/d/1M801lEpBbKSNwP-vDBkC_pF7LdyGU1f_ufZb_NWNBZQ/edit?usp=sharing"
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "081c826497f9b7da4952771ee128c2215ec3532379db0fe9f7fcbd899d9c9287",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol",
        "details.leaderboard_url"
      ],
      "url": "https://raw.githubusercontent.com/web-arena-x/webarena/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:31:20Z",
      "role": "primary",
      "sha256": "cbe8bfcbce4170a94a6cf42de01fbe0a448e7b1d29fa75a0de877105a98ec08e",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://export.arxiv.org/api/query?id_list=1802.08802%2C1808.09132%2C2005.03776%2C2101.09465%2C2103.16057%2C2104.08560%2C2105.13231%2C2107.03374%2C2107.13731%2C2108.03353%2C2202.02312%2C2202.08137%2C2204.01691%2C2205.11029%2C2207.01206%2C2209.08199%2C2209.08655%2C2209.14927%2C2209.15099%2C2210.02663%2C2210.03629%2C2210.03945%2C2211.07615%2C2301.10165%2C2301.13280%2C2302.04761%2C2303.07280%2C2303.08774%2C2303.17491%2C2303.17580%2C2304.04370%2C2304.07061%2C2305.04091%2C2305.05662%2C2305.08144%2C2305.10601%2C2305.11854%2C2305.12487%2C2305.14257%2C2305.14325%2C2305.16504%2C2305.16653%2C2305.19308%2C2306.00245%2C2306.06070%2C2306.07863%2C2307.10088%2C2307.12856%2C2307.13854%2C2308.01990&max_results=50"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/web-arena-x/webarena/HEAD/LICENSE"
    }
  ],
  "id": "github:web-arena-x/webarena",
  "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/web-arena-x/webarena/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/web-arena-x/webarena"
    }
  ],
  "name": "WebArena",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/web-arena-x/webarena/HEAD/README.md",
      "target_id": "arxiv:2307.13854",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Self-hosted web environments and tasks for evaluating autonomous web agents.",
  "topics": [
    "evaluation",
    "web-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/web-arena-x/webarena"
}