SmellBench Refactoring (Qwen Code) - 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, Qwen Code agent harness; higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.551.43
2GPT-5 Mini32.38
3Qwen 3 Coder 480B A35B Instruct28.12
4DeepSeek V3.224.05
5Qwen 3 Coder 30B A3B Instruct23.44
6Gemini 2.5 Flash22.31

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