Recent advancements in large language models (LLMs) have showcased impressive code generation capabilities, primarily evaluated through language-to-code benchmarks. However, these benchmarks may not fully capture a model's code understanding abilities. We introduce CodeJudge-Eval (CJ-Eval), a novel benchmark designed to assess LLMs' code understanding abilities from the perspective of code judging rather than code generation. CJ-Eval challenges models to determine the correctness of provided code solutions, encompassing various error types and compilation issues. By leveraging a diverse set of problems and a fine-grained judging system, CJ-Eval addresses the limitations of traditional benchmarks, including the potential memorization of solutions. Evaluation of 12 well-known LLMs on CJ-Eval reveals that even state-of-the-art models struggle, highlighting the benchmark's ability to probe deeper into models' code understanding abilities.
More details can be found in our paper.
If you find CodeJudge-Eval useful for your research and applications, please cite using this BibTeX:
@misc{zhao2024codejudgeevallargelanguagemodels,
title={CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?},
author={Yuwei Zhao and Ziyang Luo and Yuchen Tian and Hongzhan Lin and Weixiang Yan and Annan Li and Jing Ma},
year={2024},
eprint={2408.10718},
archivePrefix={arXiv},
primaryClass={cs.SE},
url={https://arxiv.org/abs/2408.10718},
}