EffiBench
收藏arXiv2024-02-15 更新2024-08-06 收录
下载链接:
http://arxiv.org/abs/2402.02037v2
下载链接
链接失效反馈官方服务:
资源简介:
EffiBench是一个包含1,000个效率关键编码问题的基准,用于评估代码生成模型生成的代码的效率。该数据集包含多样化的LeetCode编码问题,每个问题都配有一个可执行的人类编写的规范解决方案。
EffiBench is a benchmark consisting of 1,000 efficiency-critical coding problems, designed to evaluate the efficiency of code generated by code generation models. This dataset includes a diverse set of LeetCode coding problems, each paired with an executable, human-written canonical solution.
创建时间:
2024-02-03



