{
  "aliases": [],
  "authors": [],
  "details": {
    "leaderboard_url": "https://docs.google.com/spreadsheets/d/e/2PACX-1vRR3Wl7wsCgHpwUw1_eUXW_fptAPLL3FkhnW_rua0O1Ji_GIVrpTjY5LaKAhwO-WeARjnY_KNw0SYNJ/pubhtml"
  },
  "environments": [
    "cross-platform",
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T10:42:12Z",
      "role": "primary",
      "sha256": "1b7d1f1cd7a74ac9497c639324ec342dd3f8769e9c0c4cd2cd92a4eb6740ac98",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/THUDM/AgentBench/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T10:48:41Z",
      "role": "primary",
      "sha256": "c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/THUDM/AgentBench/HEAD/LICENSE"
    }
  ],
  "id": "github:thudm/agentbench",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T10:42:12Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "Apache-2.0",
      "retrieved_at": "2026-10-16T10:48:41Z",
      "url": "https://raw.githubusercontent.com/THUDM/AgentBench/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/THUDM/AgentBench"
    }
  ],
  "name": "AgentBench",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/THUDM/AgentBench/HEAD/README.md",
      "target_id": "arxiv:2308.03688",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "adjacent",
  "summary": "Agent evaluation suite with containerized tasks and a function-calling interface, including operating-system and shopping environments.",
  "topics": [
    "evaluation",
    "tool-integration"
  ],
  "updated_at": null,
  "url": "https://github.com/THUDM/AgentBench"
}