InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models

Linyi Li, Shijie Geng, Zhenwen Li, Yibo He, Hao Yu, Ziyue Hua, Guanghan Ning, Siwei Wang, Tao Xie, Hongxia Yang

Keywords: Benchmark, Code LLMs, Freeform QA

TL;DR: A comprehensive benchmark for code large language models evaluating model ability on answering freeform real-world questions in the code domain.

Abstract: 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.

Submission Number: 2355