Olfactory Perception Benchmark - Odor Classification: leaderboard
Olfactory Perception task: decide whether a molecule, given by compound name, is odorous or odorless, on a balanced set of 175 molecules. Accuracy in percent, higher is better.
Metric: Score (%) on odor classification (odorous or odorless, 175 molecules, balanced; any-overlap accuracy) of the 1,010 questions of the Olfactory Perception (OP) benchmark presented with compound-name prompts (the isomeric SMILES variant is reported only in figures), constrained option lists, provider APIs without web search or tools, each model at its stated reasoning effort or thinking budget; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | Max | 92 | #113 |
| 2 | GPT-5 Pro | 92 | #163 | |
| 3 | Claude Opus 4.5 | High | 92 | #160 |
| 4 | GPT-5 | Low | 90.3 | #178 |
| 5 | Gemini 2.5 Pro | Thinking, 16K | 89.7 | #276 |
| 6 | Claude Sonnet 4.5 | 89.1 | #261 | |
| 7 | O3 | High | 89.1 | #237 |
| 8 | Grok 4.1 Fast | 88.6 | #427 | |
| 9 | O4 Mini | High | 88.6 | #368 |
| 10 | GPT-5.2 Pro | High | 88.6 | #137 |
| 11 | Llama 3.3 70B Instruct | 83.4 | #1385 | |
| 12 | GPT-OSS-120B | High | 82.9 | #704 |
| 13 | Grok 3 Mini | High | 81.7 | #565 |
| 14 | DeepSeek Reasoner (Thinking 32K) (Olfactory Perception checkpoint unspecified) | 81.1 | ||
| 15 | DeepSeek Reasoner (Thinking 8K) (Olfactory Perception checkpoint unspecified) | 80.6 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=olfactory-perception-benchmark-odor-classification · How It Works · Data refreshed daily, snapshot 2026-11-21.