SmellBench — leaderboard
Metric: Weighted Effectiveness (E) (self-reported). Source: benchmarklist.com. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.3 Codex | 47.8 |
| 2 | Gemini 3.1 Pro (Preview) | 43.5 |
| 3 | GPT-5.4 | 42.8 |
| 4 | Claude Haiku 4.5 | 37.9 |
| 5 | Claude Opus 4.6 | 37 |
| 6 | Claude Sonnet 4.6 | 35.4 |
Interactive version: theaggregate.ai/benchmark?slug=smellbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.