SmellBench Refactoring (OpenHands): leaderboard
Metric: Smell elimination score (0-100): how completely the injected code smell is removed; 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 June 2027. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 | 47.93 |
| 2 | GPT-5 Mini | 42.35 |
| 3 | Qwen 3 Coder 480B A35B Instruct | 40.8 |
| 4 | DeepSeek V3.2 | 37.33 |
| 5 | Qwen 3 Coder 30B A3B Instruct | 30.04 |
| 6 | Gemini 2.5 Flash | 23.27 |
Interactive version: theaggregate.ai/benchmark?slug=smellbench-refactoring-openhands · How It Works · Data refreshed daily, snapshot 2026-09-29.