SmellBench Refactoring (OpenHands): leaderboard
SmellBench (2026, code refactoring) injects code smells into clean code from seven real Python repositories and asks a code agent to remove them; it is unrelated to the SmellBench board on architectural smell repair. This board is the smell elimination score, an LLM judge rating from 0 to 100 of how completely the injected smell is removed, over 294 cases with the OpenHands agent harness; higher is better.
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 February 2027. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 47.93 | #250 |
| 2 | GPT-5 Mini | 42.35 | #348 |
| 3 | Qwen 3 Coder 480B A35B Instruct | 40.8 | #643 |
| 4 | DeepSeek V3.2 | 37.33 | #406 |
| 5 | Qwen 3 Coder 30B A3B Instruct | 30.04 | #972 |
| 6 | Gemini 2.5 Flash | 23.27 | #453 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=smellbench-refactoring-openhands · How It Works · Data refreshed daily, snapshot 2026-11-13.