rStar Coder is a large-scale competition-level code problem dataset released by Microsoft in 2025. The related paper results are "rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset", which aims to enhance the code reasoning capabilities of large language models, especially in dealing with competition-level code problems. The dataset contains 418,000 competition-level programming problems, 580,000 long reasoning solutions, and a rich variety of test cases (with varying degrees of difficulty). Each solution has been verified by various simulated test cases of different difficulty levels.

Citation

@misc{liu2025rstarcoderscalingcompetitivecode,
title={rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset},
author={Yifei Liu and Li Lyna Zhang and Yi Zhu and Bingcheng Dong and Xudong Zhou and Ning Shang and Fan Yang and Mao Yang},
year={2025},
eprint={2505.21297},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2505.21297},
}