Preprint · 2025

SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents

Muhammad Shihab Rashid, Christian Bock, Yuan Zhuang, Alexander Buchholz, Tim Esler, Simon Valentin, Luca Franceschi, Martin Wistuba, Prabhu Teja Sivaprasad, Woo Jung Kim, Anoop Deoras, Giovanni Zappella, Laurent Callot

Abstract

Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We introduce SWE-PolyBench, a new multi-language benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code refactoring. We provide a task and repository-stratified subsample (SWE-PolyBench500) and release an evaluation harness allowing for fully automated evaluation. To enable a more comprehensive comparison of coding agents, this work also presents a novel set of metrics rooted in syntax tree analysis. We evaluate leading open source coding agents on SWE-PolyBench, revealing their strengths and limitations across languages, task types, and complexity classes. Our experiments show that current agents exhibit uneven performances across languages and struggle with complex problems while showing higher performance on simpler tasks. SWE-PolyBench aims to drive progress in developing more versatile and robust AI coding assistants for real-world software engineering. Our datasets and code are available at: https://github.com/amazon-science/SWE-PolyBench

BibTeX Copy

@misc{rashid_swe-polybench_2025,
	title = {{SWE}-{PolyBench}: {A} multi-language benchmark for repository level evaluation of coding agents},
	shorttitle = {{SWE}-{PolyBench}},
	url = {http://arxiv.org/abs/2504.08703},
	doi = {10.48550/arXiv.2504.08703},
	abstract = {Coding agents powered by large language models have shown impressive capabilities in software engineering tasks, but evaluating their performance across diverse programming languages and real-world scenarios remains challenging. We introduce SWE-PolyBench, a new multi-language benchmark for repository-level, execution-based evaluation of coding agents. SWE-PolyBench contains 2110 instances from 21 repositories and includes tasks in Java (165), JavaScript (1017), TypeScript (729) and Python (199), covering bug fixes, feature additions, and code refactoring. We provide a task and repository-stratified subsample (SWE-PolyBench500) and release an evaluation harness allowing for fully automated evaluation. To enable a more comprehensive comparison of coding agents, this work also presents a novel set of metrics rooted in syntax tree analysis. We evaluate leading open source coding agents on SWE-PolyBench, revealing their strengths and limitations across languages, task types, and complexity classes. Our experiments show that current agents exhibit uneven performances across languages and struggle with complex problems while showing higher performance on simpler tasks. SWE-PolyBench aims to drive progress in developing more versatile and robust AI coding assistants for real-world software engineering. Our datasets and code are available at: https://github.com/amazon-science/SWE-PolyBench},
	urldate = {2026-11-06},
	publisher = {arXiv},
	author = {Rashid, Muhammad Shihab and Bock, Christian and Zhuang, Yuan and Buchholz, Alexander and Esler, Tim and Valentin, Simon and Franceschi, Luca and Wistuba, Martin and Sivaprasad, Prabhu Teja and Kim, Woo Jung and Deoras, Anoop and Zappella, Giovanni and Callot, Laurent},
	month = apr,
	year = {2025},
	note = {arXiv:2504.08703 [cs.SE]},
	keywords = {Computer Science - Software Engineering},
}