ProjectTest: A Project-level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms
This addresses a practical gap in evaluating LLMs for software testing, though it is incremental as it extends existing benchmarks to a more challenging project-level scope.
The authors tackled the lack of project-level benchmarks for LLM unit test generation by introducing ProjectTest, a benchmark covering Python, Java, and JavaScript with 20 projects per language, and found that frontier LLMs show moderate performance, with significant errors like compilation issues.
Unit test generation has become a promising and important use case of LLMs. However, existing evaluation benchmarks for assessing LLM unit test generation capabilities focus on function- or class-level code rather than more practical and challenging project-level codebases. To address such limitation, we propose ProjectTest, a project-level benchmark for unit test generation covering Python, Java, and JavaScript. ProjectTest features 20 moderate-sized and high-quality projects per language. We evaluate nine frontier LLMs on ProjectTest and the results show that all frontier LLMs tested exhibit moderate performance on ProjectTest on Python and Java, highlighting the difficulty of ProjectTest. We also conduct a thorough error analysis, which shows that even frontier LLMs, such as Claude-3.5-Sonnet, have significant basic yet critical errors, including compilation and cascade errors. Motivated by this observation, we further evaluate all frontier LLMs under manual error-fixing and self-error-fixing scenarios to assess their potential when equipped with error-fixing mechanisms. Our code and dataset is available at \href{https://github.com/YiboWANG214/ProjectTest}{ProjectTest}.