{
 "id": "Hubble42/ResolveBench",
 "owner": "Hubble42",
 "name": "ResolveBench",
 "downloads": 61,
 "likes": 1,
 "last_modified": "2026-08-20T22:15:05.000Z",
 "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{resolvebench2026,\n  title        = {ResolveBench: An Operational-Reliability Benchmark for Customer-Support AI Agents},\n  author       = {Siddiqui, Osamah Ahmad and Jamil, Muhammad Aghnus and Mir, Muhammad Saad and Sabah, Fahad},\n  organization = {Hubble42 Inc.},\n  year         = {2026},\n  month        = {7},\n  note         = {v2.1 (8 model configurations, 6,400 scored runs)},\n  url          = {https://resolvebench.com}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "6e8f58fd29aa794d8b8eb9e3e01ffe44b48f4b0e",
 "stated_evidence": "https://huggingface.co/datasets/Hubble42/ResolveBench/blob/6e8f58fd29aa794d8b8eb9e3e01ffe44b48f4b0e/README.md",
 "file_evidence": "https://huggingface.co/datasets/Hubble42/ResolveBench/tree/6e8f58fd29aa794d8b8eb9e3e01ffe44b48f4b0e",
 "card_nc": false
}