LeetCode-Hard
收藏arXiv2025-09-30 收录
官方服务：
资源简介：
该数据集用于评估大型语言模型在生成高质量测试用例方面的性能。在此基础上，采用GPT-4的TestChain方法，相较于基准方法，在准确度上提高了13.84%。该任务的目的是生成测试用例。
This dataset is used to evaluate the performance of large language models (LLMs) in generating high-quality test cases. The GPT-4-powered TestChain method achieves a 13.84% improvement in accuracy compared to the baseline method when evaluated on this dataset. The objective of this task is to generate test cases.
