{
  "aliases": [],
  "authors": [],
  "details": {
    "disabled": false,
    "download_url": "https://huggingface.co/datasets/wanlilll/WeaveBench/tree/main",
    "gated": false,
    "hub_id": "wanlilll/WeaveBench",
    "languages": [
      "en"
    ],
    "modalities": [],
    "size_category_reported": [
      "n<1K"
    ]
  },
  "environments": [
    "desktop",
    "linux"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:38:27Z",
      "role": "primary",
      "sha256": "e65e5793fe5b251ef7793a0618f4e8139fe5c92c2cf8093d0cc6142e8ece9d02",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations"
      ],
      "url": "https://huggingface.co/api/datasets/wanlilll/WeaveBench"
    },
    {
      "method": "huggingface_api",
      "retrieved_at": "2026-10-16T06:38:27Z",
      "role": "primary",
      "sha256": "e65e5793fe5b251ef7793a0618f4e8139fe5c92c2cf8093d0cc6142e8ece9d02",
      "supports": [
        "details",
        "licenses.data"
      ],
      "url": "https://huggingface.co/api/datasets/wanlilll/WeaveBench"
    }
  ],
  "id": "url:6a212bc12f82c824f6b9",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:38:27Z",
  "licenses": {
    "code": null,
    "data": {
      "basis": "publisher model/dataset card",
      "declared": "mit",
      "retrieved_at": "2026-10-16T06:38:27Z",
      "url": "https://huggingface.co/datasets/wanlilll/WeaveBench"
    },
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://huggingface.co/datasets/wanlilll/WeaveBench"
    }
  ],
  "name": "WeaveBench",
  "notes": "",
  "published_at": null,
  "relations": [],
  "review_status": "curated",
  "scope": "core",
  "summary": "Computer-use benchmark mixing graphical interaction and code execution.",
  "topics": [
    "evaluation",
    "tool-integration"
  ],
  "updated_at": null,
  "url": "https://huggingface.co/datasets/wanlilll/WeaveBench"
}