InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
This work addresses the need for better evaluation tools for code LLMs, benefiting researchers and developers by providing a more systematic benchmark, though it is incremental as it builds on existing evaluation practices.
The authors tackled the lack of comprehensive evaluation benchmarks for code large language models (LLMs) by introducing InfiBench, a large-scale freeform question-answering benchmark comprising 234 Stack Overflow questions across 15 programming languages, which they used to evaluate over 100 code LLMs and uncover novel insights for future advancements.
Large Language Models for code (code LLMs) have witnessed tremendous progress in recent years. With the rapid development of code LLMs, many popular evaluation benchmarks, such as HumanEval, DS-1000, and MBPP, have emerged to measure the performance of code LLMs with a particular focus on code generation tasks. However, they are insufficient to cover the full range of expected capabilities of code LLMs, which span beyond code generation to answering diverse coding-related questions. To fill this gap, we propose InfiBench, the first large-scale freeform question-answering (QA) benchmark for code to our knowledge, comprising 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. InfiBench uses four types of model-free automatic metrics to evaluate response correctness where domain experts carefully concretize the criterion for each question. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings. Our detailed analyses showcase potential directions for further advancement of code LLMs. InfiBench is fully open source at https://infi-coder.github.io/infibench and continuously expanding to foster more scientific and systematic practices for code LLM evaluation.