SmellBench - True Positive Component: leaderboard
Metric: Mean per-task score s (-1 to 1: 1 for a full repair or a correctly flagged false positive, partial credit for a severity reduction, negative for a worsened smell or a genuine smell flagged as false positive) over the 11 smells the expert judged genuine, 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 January 2027. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.3 Codex | 0.4 |
| 2 | Gemini 3.1 Pro (Preview) | 0.39 |
| 3 | GPT-5.4 | 0.36 |
| 4 | GPT-5.1 Codex Max | 0.3 |
| 5 | Claude Haiku 4.5 | 0.3 |
| 6 | Claude Opus 4.6 | 0.28 |
| 7 | Claude Sonnet 4.6 | 0.28 |
| 8 | Gemini 3.1 Flash Lite (Preview) | -0.63 |
Interactive version: theaggregate.ai/benchmark?slug=smellbench-true-positive-component · How It Works · Data refreshed daily, snapshot 2026-10-07.