SWE-bench/SWE-bench_Lite
收藏Hugging Face2025-04-29 更新2025-07-05 收录
下载链接：
https://hf-mirror.com/datasets/SWE-bench/SWE-bench_Lite
下载链接
链接失效反馈官方服务：
资源简介：
SWE-bench Lite是SWE-bench数据集的一个子集，用于测试系统自动解决GitHub问题的能力。该数据集从11个流行的Python项目中收集了300个测试问题-拉取请求对。评估通过单元测试验证进行，使用PR之后的操作作为参考解决方案。数据集作为论文《SWE-bench: Can Language Models Resolve Real-World GitHub Issues?》的一部分发布。
SWE-bench Lite is a subset of the SWE-bench dataset, which tests systems ability to automatically resolve GitHub issues. The dataset collects 300 test Issue-Pull Request pairs from 11 popular Python projects. Evaluation is performed by unit test verification using post-PR behavior as the reference solution. The dataset was released as part of the paper SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
提供机构：
SWE-bench
