{
 "id": "leiqf/UtilityBench",
 "owner": "leiqf",
 "name": "UtilityBench",
 "downloads": 189,
 "likes": 1,
 "last_modified": "2026-10-21T02:56:02.000Z",
 "stated_licence": "mit",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "question-answering",
  "multiple-choice"
 ],
 "citation": "@misc{lei2026utilitybench,\n  author        = {Qifeng Lei and Zhiyong Yang and Zitai Wang and Shilong Bao and Linchao Zhang and Qianqian Xu and Qingming Huang},\n  title         = {{UtilityBench}: Measuring Language Model Utility When Errors Have Different Costs},\n  year          = {2026},\n  eprint        = {2610.25924},\n  archiveprefix = {arXiv},\n}",
 "signal": "permissive",
 "reason": "The declared licence (mit) is classified as permissive.",
 "revision": "0cf90a65373d88ca2c0c07c0d5c79220b87807d9",
 "stated_evidence": "https://huggingface.co/datasets/leiqf/UtilityBench/blob/0cf90a65373d88ca2c0c07c0d5c79220b87807d9/README.md",
 "file_evidence": "https://huggingface.co/datasets/leiqf/UtilityBench/tree/0cf90a65373d88ca2c0c07c0d5c79220b87807d9",
 "card_nc": false
}