{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "CLICK",
        "TYPE",
        "SELECT"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md",
          "population": "train split",
          "qualifier": "exact",
          "unit": "task instances",
          "value": 1009
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md",
          "population": "cross-task test split",
          "qualifier": "exact",
          "unit": "task instances",
          "value": 252
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md",
          "population": "cross-website test split",
          "qualifier": "exact",
          "unit": "task instances",
          "value": 177
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md",
          "population": "cross-domain test split",
          "qualifier": "exact",
          "unit": "task instances",
          "value": 912
        }
      ],
      "evaluation": "Offline candidate and action evaluation against recorded demonstrations; the repository distinguishes macro from micro averaging.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md"
      ],
      "focus": [
        "web action prediction",
        "generalization to unseen sites and domains"
      ],
      "notes": "These are reported split inventories, not online task-success measurements. Original Mind2Web, Multimodal-Mind2Web, and Online-Mind2Web have different inputs/protocols. The authors require macro-average metrics for comparison with the paper; test archives remain upstream.",
      "observations": [
        "task instructions",
        "HTML",
        "recorded action history"
      ],
      "setting": "offline"
    }
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "157dbd840264ea29f958c0b7383d63783845c573b3e19a1f39b773be22e0b32d",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "157dbd840264ea29f958c0b7383d63783845c573b3e19a1f39b773be22e0b32d",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "953ff47dbbc0c0563d1ec2d245b06d1206f2f38c4ed2f0da728e027ae2e5a973",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/LICENSE"
    }
  ],
  "id": "github:osu-nlp-group/mind2web",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:35:57Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "MIT",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/OSU-NLP-Group/Mind2Web"
    }
  ],
  "name": "Mind2Web",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web/HEAD/README.md",
      "target_id": "arxiv:2306.06070",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Human demonstrations and tasks for generalist web navigation research.",
  "topics": [
    "evaluation",
    "web-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/OSU-NLP-Group/Mind2Web"
}