SmellBench - Resolution Rate: leaderboard
Metric: Share of all 65 smells (%) that PyExamine no longer detects after the run (a resolution may be a side effect of work on another task), 65 expert-validated hard-severity PyExamine architectural smells in scikit-learn, off-the-shelf coding agent CLIs with the SmellBench agent skill and GEPA-optimized task packets, default reasoning settings, one run per agent; higher is better. Source: arxiv.org. Saturation forecast: Around 2028. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 32.3 |
| 2 | GPT-5.3 Codex | 30.8 |
| 3 | Gemini 3.1 Pro (Preview) | 29.2 |
| 4 | Claude Sonnet 4.6 | 27.7 |
| 5 | Claude Opus 4.6 | 27.7 |
| 6 | Claude Haiku 4.5 | 27.7 |
| 7 | GPT-5.1 Codex Max | 27.7 |
| 8 | Gemini 3.1 Flash Lite (Preview) | 9.2 |
Interactive version: theaggregate.ai/benchmark?slug=smellbench-resolution-rate · How It Works · Data refreshed daily, snapshot 2026-10-07.