SmellBench - True Positive Component: leaderboard
SmellBench (2026) scores coding-agent CLIs on repairing 65 expert-validated architectural code smells in scikit-learn. This board averages the per-task score over the 11 smells the expert judged genuine, where 1 is a full repair, a severity reduction earns partial credit and a worsened smell or a genuine smell dismissed as a false positive scores below 0; range -1 to 1, higher is better.
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 February 2027. 10 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.3 Codex | 0.402 | #124 |
| 2 | Gemini 3.1 Pro (Preview) | 0.389 | #99 |
| 3 | GPT-5.3 Codex Spark | 0.383 | |
| 4 | GPT-5.4 | 0.357 | #135 |
| 5 | GPT-5.1 Codex Max | 0.304 | #207 |
| 6 | Claude Haiku 4.5 | 0.3 | #583 |
| 7 | Claude Opus 4.6 | 0.285 | #113 |
| 8 | Claude Sonnet 4.6 | 0.278 | #173 |
| 9 | Mistral Vibe + Devstral 2 | -0.176 | |
| 10 | Gemini 3.1 Flash Lite (Preview) | -0.627 | #417 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=smellbench-true-positive-component · How It Works · Data refreshed daily, snapshot 2026-11-21.