BigCodeBench
收藏arXiv2025-09-30 收录
下载链接：
https://github.com/bigcode-project/bigcodebench
下载链接
链接失效反馈官方服务：
资源简介：
该数据集名为BigCodeBench，它侧重于工程导向的任务，并作为评估代码生成工作流程的基准。此外，该数据集还用于评估FlowReasoner系统根据用户查询生成定制工作流程的性能。其所涉及的任务是代码生成。
This dataset, named BigCodeBench, focuses on engineering-oriented tasks and serves as a benchmark for evaluating code generation workflows. Additionally, this dataset is also utilized to evaluate the performance of the FlowReasoner system in generating customized workflows based on user queries. The tasks involved in this dataset are code generation.
提供机构：
BigCodeBench Project
