While large language models (LLMs) have shown considerable promise in code generation, real-world software development demands advanced repository-level reasoning. This includes understanding dependencies, project structures, and managing multi-file changes. However, the ability of LLMs to effectively comprehend and handle complex code repositories has yet to be fully explored. To address challenges, we introduce a hierarchical benchmark designed to evaluate repository dependency understanding (DependEval). Benchmark is based on 15,576 repositories collected from real-world websites. It evaluates models on three core tasks: Dependency Recognition, Repository Construction, and Multi-file Editing, across 8 programming languages from actual code repositories. Our evaluation of over 25 LLMs reveals substantial performance gaps and provides valuable insights into repository-level code understanding.
@article{arxiv.2503.06689,
title = {DependEval: Benchmarking LLMs for Repository Dependency Understanding},
author = {Junjia Du and Yadi Liu and Hongcheng Guo and Jiawei Wang and Haojian Huang and Yunyi Ni and Zhoujun Li},
journal= {arXiv preprint arXiv:2503.06689},
year = {2025}
}