{
 "id": "JetBrains/git_good_bench-lite",
 "owner": "JetBrains",
 "name": "git_good_bench-lite",
 "downloads": 156,
 "likes": 1,
 "last_modified": "2025-11-18T09:06:11.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{lindenbauer-etal-2025-gitgoodbench,\n    title = \"{G}it{G}ood{B}ench: A Novel Benchmark For Evaluating Agentic Performance On Git\",\n    author = \"Lindenbauer, Tobias  and\n      Bogomolov, Egor  and\n      Zharov, Yaroslav\",\n    editor = \"Kamalloo, Ehsan  and\n      Gontier, Nicolas  and\n      Lu, Xing Han  and\n      Dziri, Nouha  and\n      Murty, Shikhar  and\n      Lacoste, Alexandre\",\n    booktitle = \"Proceedings of the 1st Workshop for Research on Agent Language Models (REALM 2025)\",\n    month = jul,\n    year = \"2025\",\n    address = \"Vienna, Austria\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.realm-1.19/\",\n    doi = \"10.18653/v1/2025.realm-1.19\",\n    pages = \"272--288\",\n    ISBN = \"979-8-89176-264-0\",\n    abstract = \"Benchmarks for Software Engineering (SE) AI agents, most notably SWE-bench, have catalyzed progress in programming capabilities of AI agents. However, they overlook critical developer workflows such as Version Control System (VCS) operations. To address this issue, we present GitGoodBench, a novel benchmark for evaluating AI agent performance on Version Control System (VCS) tasks. GitGoodBench covers three core Git scenarios extracted from permissive open-source Python, Java, and Kotlin repositories. Our benchmark provides three datasets: a comprehensive evaluation suite (900 samples), a rapid prototyping version (120 samples), and a training corpus (17,469 samples). We establish baseline p",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive.",
 "revision": "086d113d9e584ad0dde7cd08a693b17546800f2d",
 "stated_evidence": "https://huggingface.co/datasets/JetBrains/git_good_bench-lite/blob/086d113d9e584ad0dde7cd08a693b17546800f2d/README.md",
 "file_evidence": "https://huggingface.co/datasets/JetBrains/git_good_bench-lite/tree/086d113d9e584ad0dde7cd08a693b17546800f2d",
 "card_nc": false
}