AI Paper Atlas

Research map / Large language models / Agents, code and math

SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models

Jingxuan Xu, Ken Deng, Weihao Li, Songwei Yu, Haoyang Huang, Xinping Lei, Yifan Yao, Huaixi Tang, Zhiyi Lai, Kepeng Lei, Zizheng Zhan, Yanan Wu and 26 more

ICML 2026 · Large language models › Agents, code and math · approach: Software engineering agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
run Claude-Sonnet-4 in Claude Code instead of SWE-Agent (ablation)Claude-Sonnet-4 · SWE-Compassaverage score (%): 31.8 -> 32.9Improved
run Qwen3-Coder-480B in Claude Code instead of SWE-Agent (ablation)Qwen3-Coder-480B-Instruct · SWE-Compassaverage score (%): 27.2 -> 21.9Hurt
run Qwen3-Coder-30B in Claude Code instead of SWE-Agent (ablation)Qwen3-Coder-30B-Instruct · SWE-Compassaverage score (%): 20.7 -> 21.6Improved
choose framework by task: SWE-Agent for bug fixing and feature implementation, Claude Code for test generation and configuration (ablation)SWE-Agent vs Claude Code · SWE-Compass task typesscoreMixed
allow more interaction turnsagentic frameworks · SWE-CompassPass@1Mixed
higher overall performanceevaluated models · SWE-Compass across languagesperformance variability (CV)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy