Recent advancements in large language models (LLMs) have significantly enhanced their coding capabilities. However, existing benchmarks predominantly focused on simplified or isolated aspects of programming, such as single-file code generation or repository issue debugging, falling short of measuring the full spectrum of challenges raised by real-world programming activities. To this end, we propose DevBench, a comprehensive benchmark that evaluates LLMs across various stages of the software development lifecycle, including software design, environment setup, implementation, acceptance testing, and unit testing. DevBench features a wide range of programming languages and domains, high-quality data collection, and carefully designed and verified metrics for each task. Empirical studies show that current LLMs, including GPT-4-Turbo, fail to solve the challenges presented within DevBench. Analyses reveal that models struggle with understanding the complex structures in the repository, managing the compilation process, and grasping advanced programming concepts. Our findings offer actionable insights for the future development of LLMs toward real-world programming applications. Our benchmark is available at https://github.com/open-compass/DevBench

翻译：近期，大语言模型（LLMs）的进步显著提升了其编码能力。然而，现有基准测试主要关注编程任务的简化或孤立层面（如单文件代码生成或仓库问题调试），未能全面衡量实际编程活动中的复杂挑战。为此，我们提出DevBench——一个涵盖软件开发全生命周期各阶段（包括软件设计、环境配置、代码实现、验收测试与单元测试）的综合基准测试。DevBench包含多样化的编程语言和领域、高质量的数据集，并为每项任务设计了经过严格验证的评估指标。实证研究表明，包括GPT-4-Turbo在内的当前LLMs无法解决DevBench中的挑战。分析显示，模型难以理解仓库中的复杂结构、管理编译流程以及掌握高级编程概念。我们的发现为未来LLMs向实际编程应用发展提供了可操作的见解。本基准测试已开源：https://github.com/open-compass/DevBench