{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "web interactions"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md",
          "population": "documented Online-Mind2Web suite",
          "qualifier": "exact",
          "unit": "tasks",
          "value": 300
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md",
          "population": "documented site coverage",
          "qualifier": "exact",
          "unit": "websites",
          "value": 136
        }
      ],
      "evaluation": "Human evaluation and WebJudge-based evaluation are documented as distinct assessment paths.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md"
      ],
      "focus": [
        "live-web task completion"
      ],
      "notes": "Tasks are actively replaced when websites or requirements become invalid. Record the task revision and submission schema; a constant headline task count does not imply an unchanged test set.",
      "observations": [],
      "setting": "interactive"
    },
    "leaderboard_url": "https://huggingface.co/spaces/osunlp/Online_Mind2Web_Leaderboard"
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "49d7cc317fd2ba0df65abf65a0357d1fa2384e59019a96d4e24b784888599eaa",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol",
        "details.leaderboard_url"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:57Z",
      "role": "primary",
      "sha256": "93675f9d13697ae98889d703b8fae86a7200623e7ae8d844c9ee2200ad480583",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/OSU-NLP-Group/Online-Mind2Web/HEAD/LICENSE"
    }
  ],
  "id": "github:osu-nlp-group/online-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/Online-Mind2Web/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/OSU-NLP-Group/Online-Mind2Web"
    }
  ],
  "name": "Online Mind2Web",
  "notes": "",
  "published_at": null,
  "relations": [],
  "review_status": "curated",
  "scope": "core",
  "summary": "300 tasks on 136 live websites for evaluating web agents online, with outdated tasks replaced over time, human-reviewed submissions and the WebJudge automatic evaluator.",
  "topics": [
    "evaluation",
    "web-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/OSU-NLP-Group/Online-Mind2Web"
}