{
 "id": "ScaleAI/MA-Bench",
 "owner": "ScaleAI",
 "name": "MA-Bench",
 "downloads": 605,
 "likes": 3,
 "last_modified": "2026-10-16T17:03:25.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-generation"
 ],
 "citation": "@misc{lafuentemercado2026mabench,\n  title         = {{MA-Bench}: Measuring Operational Planning in Language Models},\n  author        = {Lafuente-Mercado, Rodney and Sincero, Robert and Sage, Phil and Xue, Yuan},\n  year          = {2026},\n  eprint        = {2610.19138},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.LG},\n  doi           = {10.48550/arXiv.2610.19138},\n  url           = {https://arxiv.org/abs/2610.19138}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "1845cb319f5938a03836cd8e511f3f37a829a199",
 "stated_evidence": "https://huggingface.co/datasets/ScaleAI/MA-Bench/blob/1845cb319f5938a03836cd8e511f3f37a829a199/README.md",
 "file_evidence": "https://huggingface.co/datasets/ScaleAI/MA-Bench/tree/1845cb319f5938a03836cd8e511f3f37a829a199",
 "card_nc": false
}