{
 "id": "hubertmarek/agent-diff-bench",
 "owner": "hubertmarek",
 "name": "agent-diff-bench",
 "downloads": 156,
 "likes": 2,
 "last_modified": "2026-02-17T14:01:55.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@article{pysklo2025agentdiff,\n  title={Agent-Diff: Benchmarking LLM Agents on Enterprise API Tasks via Code Execution with State-Diff-Based Evaluation},\n  author={Hubert Marek Pysklo and others},\n  journal={arXiv preprint arXiv:2602.11224},\n  year={2025}\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "4a96ea93a8d074daba93ded109f340da7fae2f70",
 "stated_evidence": "https://huggingface.co/datasets/hubertmarek/agent-diff-bench/blob/4a96ea93a8d074daba93ded109f340da7fae2f70/README.md",
 "file_evidence": "https://huggingface.co/datasets/hubertmarek/agent-diff-bench/tree/4a96ea93a8d074daba93ded109f340da7fae2f70",
 "card_nc": false
}