CodeEditorBench: Evaluating Code Editing Capability of Large Language Models
This provides a benchmark for researchers and practitioners to evaluate LLMs in real-world code editing scenarios, though it is incremental as it builds on existing code generation benchmarks.
The authors tackled the problem of evaluating large language models' code editing capabilities by introducing CodeEditorBench, a framework that assesses performance in tasks like debugging and translating across diverse programming languages, and found that closed-source models like Gemini-Ultra and GPT-4 outperformed open-source models.
Large Language Models (LLMs) for code are rapidly evolving, with code editing emerging as a critical capability. We introduce CodeEditorBench, an evaluation framework designed to rigorously assess the performance of LLMs in code editing tasks, including debugging, translating, polishing, and requirement switching. Unlike existing benchmarks focusing solely on code generation, CodeEditorBench emphasizes real-world scenarios and practical aspects of software development. We curate diverse coding challenges and scenarios from five sources, covering various programming languages, complexity levels, and editing tasks. Evaluation of 19 LLMs reveals that closed-source models (particularly Gemini-Ultra and GPT-4), outperform open-source models in CodeEditorBench, highlighting differences in model performance based on problem types and prompt sensitivities. CodeEditorBench aims to catalyze advancements in LLMs by providing a robust platform for assessing code editing capabilities. We will release all prompts and datasets to enable the community to expand the dataset and benchmark emerging LLMs. By introducing CodeEditorBench, we contribute to the advancement of LLMs in code editing and provide a valuable resource for researchers and practitioners.