CodeRankEval
收藏科学数据银行2025-11-17 更新2026-04-23 收录
下载链接:
https://www.scidb.cn/detail?dataSetId=9d14aac9839e40c285e1d960b1d0c64a
下载链接
链接失效反馈官方服务:
资源简介:
This project provides the benchmark dataset introduced in the paper "CodeRankEval: Benchmarking and Analyzing LLM Performance for Code Ranking". It aims to evaluate and analyze the performance of large language models (LLMs) on code ranking tasks. It includes data in three scoring formats: pointwise, pairwise, and listwise.
提供机构:
徐邑江; 李映辉; 张世琨; 高庆; 曾政然; 安睿川; 肖正; 王馨; 王一栋; 陈立果
创建时间:
2025-11-17



