{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "predicted browser actions"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50",
          "population": "original paper benchmark",
          "qualifier": "approximately",
          "unit": "interactions",
          "value": 100000
        },
        {
          "basis": "reported",
          "evidence_url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50",
          "population": "original paper benchmark",
          "qualifier": "approximately",
          "unit": "expert demonstrations",
          "value": 2300
        },
        {
          "basis": "reported",
          "evidence_url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50",
          "population": "original paper benchmark",
          "qualifier": "more-than",
          "unit": "websites",
          "value": 150
        }
      ],
      "evaluation": "Offline evaluation compares action predictions against recorded human demonstrations.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/README.md",
        "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50",
        "https://huggingface.co/datasets/McGill-NLP/WebLINX/raw/main/README.md"
      ],
      "focus": [
        "conversational web navigation",
        "next-action prediction"
      ],
      "notes": "The figures are rounded descriptions from the original paper. WebLINX 1.1 / BrowserGym removes some demonstrations and changes evaluated steps, including tab actions; do not mix those results or counts with the original release. This profile does not treat replayed demonstration steps as live task completion.",
      "observations": [
        "dialogue history",
        "HTML",
        "screenshots",
        "action history"
      ],
      "setting": "offline"
    }
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "15c3f1656afd861894b180bca7d9214b4cf78a6ad9cd0601c80f5d67d2839528",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "15c3f1656afd861894b180bca7d9214b4cf78a6ad9cd0601c80f5d67d2839528",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:31:24Z",
      "role": "primary",
      "sha256": "3aac6e9748769efff3c475ede0da192776daa03431d231b5f67e2aa50f8a3be9",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://export.arxiv.org/api/query?id_list=2308.03688%2C2308.15272%2C2309.08172%2C2309.11436%2C2310.04716%2C2310.04869%2C2310.05126%2C2310.06770%2C2310.08740%2C2310.10634%2C2310.11441%2C2310.16042%2C2310.18331%2C2311.01767%2C2311.07562%2C2311.09278%2C2311.12983%2C2311.18751%2C2312.03003%2C2312.06677%2C2312.08914%2C2312.11671%2C2312.13108%2C2312.13771%2C2312.15820%2C2312.16062%2C2401.01614%2C2401.04124%2C2401.07781%2C2401.10935%2C2401.13178%2C2401.13649%2C2401.13919%2C2401.14268%2C2401.16158%2C2402.01030%2C2402.04476%2C2402.04615%2C2402.05930%2C2402.06596%2C2402.07456%2C2402.07939%2C2402.07945%2C2402.08567%2C2402.11941%2C2402.14073%2C2402.15057%2C2402.16965%2C2402.17553%2C2403.02713&max_results=50"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T02:03:23Z",
      "role": "primary",
      "sha256": "9bd7512e257f5914d66b091530d7eb711a6f90bc21dc89cbba53015c7136c527",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://huggingface.co/datasets/McGill-NLP/WebLINX/raw/main/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "cc0156153933fb96f6f3bf8d736c15e24d78d0838945c2ed456e3ada96cf67c4",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/LICENSE"
    }
  ],
  "id": "github:mcgill-nlp/weblinx",
  "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/mcgill-nlp/weblinx/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/mcgill-nlp/weblinx"
    }
  ],
  "name": "WebLINX",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/mcgill-nlp/weblinx/HEAD/README.md",
      "target_id": "arxiv:2402.05930",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Demonstrations and evaluation for conversational web navigation.",
  "topics": [
    "evaluation",
    "web-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/mcgill-nlp/weblinx"
}