{
  "aliases": [],
  "authors": [],
  "details": {
    "leaderboard_url": "https://osu-nlp-group.github.io/Mind2Web-2/#leaderboard"
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T17:18:21Z",
      "role": "primary",
      "sha256": "5cc72b992cfc11094dcf341c284d5baadc6c66a302fdfd474b27913fe1c91f6f",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web-2/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-17T17:18:56Z",
      "role": "primary",
      "sha256": "93b43d692b033b76129504448695bfe76ef22d18b11e51352bfab4b5622e5aaa",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web-2/HEAD/LICENSE"
    }
  ],
  "id": "github:osu-nlp-group/mind2web-2",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-17T17:18:21Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "MIT",
      "retrieved_at": "2026-10-17T17:18:56Z",
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Mind2Web-2/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/OSU-NLP-Group/Mind2Web-2"
    }
  ],
  "name": "Mind2Web 2",
  "notes": "",
  "published_at": null,
  "relations": [],
  "review_status": "curated",
  "scope": "core",
  "summary": "Long-horizon agentic web search benchmark whose Agent-as-a-Judge framework scores time-varying, citation-backed answers, with evaluation scripts for its dev and test sets.",
  "topics": [
    "evaluation",
    "web-navigation",
    "long-horizon"
  ],
  "updated_at": null,
  "url": "https://github.com/OSU-NLP-Group/Mind2Web-2"
}