SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks

TL;DR

SWE-MERA is a new dynamic benchmark for evaluating large language models on software engineering tasks, addressing data contamination issues in existing datasets by providing a continuously updated, high-quality collection of real-world GitHub issues.

Contribution

It introduces SWE-MERA, a reliable, automated pipeline for collecting and validating real-world software engineering tasks, improving evaluation integrity for LLMs.

Findings

SWE-MERA effectively discriminates between different LLM performances.

Evaluation shows recent LLMs achieve varied success on real-world tasks.

The benchmark reduces data contamination compared to previous datasets.

Abstract

The rapid advancement of Large Language Models (LLMs) in software engineering has revealed critical limitations in existing benchmarks, particularly the widely used SWE-bench dataset. Recent studies have uncovered severe data contamination issues, e.g. SWE-bench reports 32.67% of successful patches involve direct solution leakage and 31.08% pass due to inadequate test cases. We introduce SWE-MERA, a dynamic, continuously updated benchmark designed to address these fundamental challenges through an automated collection of real-world GitHub issues and rigorous quality validation. Our approach implements a reliable pipeline that ensures quality while minimizing contamination risks, resulting in approximately 10,000 potential tasks with 300 samples currently available. Evaluation using the Aider coding agent demonstrates strong discriminative power in state-of-the-art models. We report performance across a dozen recent LLMs evaluated on tasks collected between September 2024 and June 2025.