FullStack Bench: Evaluating LLMs as Full Stack Coders
This addresses the need for broader evaluation of LLMs in code intelligence for researchers and developers, though it is incremental as it builds on existing datasets by expanding scope.
The authors tackled the problem of limited evaluation domains for code large language models by developing FullStack Bench, a comprehensive dataset for full-stack programming across 16 languages, and released SandboxFusion for efficient evaluation, showing its necessity and effectiveness in experiments.
As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing. However, most existing datasets only evaluate limited application domains. To address this gap, we have developed a comprehensive code evaluation dataset FullStack Bench focusing on full-stack programming, which encompasses a wide range of application domains (e.g., basic programming, data analysis, software engineering, mathematics, and machine learning). Besides, to assess multilingual programming capabilities, in FullStack Bench, we design real-world instructions and corresponding unit test cases from 16 widely-used programming languages to reflect real-world usage scenarios rather than simple translations. Moreover, we also release an effective code sandbox execution tool (i.e., SandboxFusion) supporting various programming languages and packages to evaluate the performance of our FullStack Bench efficiently. Comprehensive experimental results on our FullStack Bench demonstrate the necessity and effectiveness of our FullStack Bench and SandboxFusion.