SmellBench Refactoring (OpenHands) - Cross-File Coordination: leaderboard

Metric: Cross-file coordination score (0-100): consistent handling of every affected file, import and helper; an LLM judge (model not named) scores the refactoring against the smell analysis on a 0-10 rubric, normalized to 0-100; 294 injected-smell refactoring cases (7 smell types, 3 difficulty levels, guided and targeted instructions) in 7 real Python repositories, run once in the Harbor Docker framework with a 20-minute budget, OpenHands agent harness; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 6 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.548.81
2GPT-5 Mini43.16
3Qwen 3 Coder 480B A35B Instruct39.62
4DeepSeek V3.238.04
5Qwen 3 Coder 30B A3B Instruct30.14
6Gemini 2.5 Flash23.23

Interactive version: theaggregate.ai/benchmark?slug=smellbench-refactoring-openhands-cross-file-coordination · How It Works · Data refreshed daily, snapshot 2026-09-29.