rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset

Yifei Liu, Li Lyna Zhang, Yi Zhu, bingcheng dong, Xudong Zhou, Ning Shang, Fan Yang, Cheng Li, Mao Yang

University of Science and Technology of China· Microsoft· Dalian University of Technology· Shanghai Jiao Tong University

Large Language Models Code Reasoning Test Case Generation

⋅ NeurIPS ⋅ OpenReview

Abstract

Advancing code reasoning in large language models (LLMs) is fundamentally limited by the scarcity of high-difficulty datasets, especially those with verifiable input-output test cases necessary for rigorous solution validation at scale. We introduce rStar-Coder, which significantly improves LLM code reasoning capabilities by constructing a large-scale, verified dataset of 418K competition-level code problems, 580K long-reasoning solutions along with rich test cases of varying difficulty.

This is achieved through three core contributions:

we curate competitive programming code problems and solutions to synthesize new, solvable problems;
we introduce a reliable input-output test case synthesis pipeline that decouples the generation into a three-step input generation method and a mutual verification mechanism for effective output labeling;
we augment problems with high-quality, test-case-verified long-reasoning solutions.

Extensive experiments on Qwen models (1.5B-14B) across various code reasoning benchmarks demonstrate the superiority of rStar-Coder dataset, achieving leading performance comparable to frontier reasoning LLMs with significantly smaller model sizes.

On LiveCodeBench, rStar-Coder improves Qwen2.5-7B from 17.4% to an impressive 57.3%, and Qwen2.5-14B from 23.3% to 62.5%, surpassing o3-mini (low) by 3.1%. On the more challenging USA Computing Olympiad, our 7B model achieves an average pass@1 accuracy of 16.15%, outperforming the frontier-level QWQ-32B.

rStar-Coder dataset is publicly available at https://huggingface.co/datasets/microsoft/rStar-Coder.