Olfactory Perception Benchmark - Odor Pleasantness: leaderboard
Olfactory Perception task: decide which of two molecules smells more pleasant, based on human psychophysical ratings. Accuracy in percent, higher is better.
Metric: Score (%) on odor pleasantness paired comparison (which of two molecules smells more pleasant, 175 pairs; 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: Not forecast. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | High | 74.9 | #114 |
| 2 | DeepSeek Reasoner (Thinking 16K) (Olfactory Perception checkpoint unspecified) | 74.9 | ||
| 3 | O4 Mini | High | 73.7 | #372 |
| 4 | Grok 3 Mini | High | 73.7 | #559 |
| 5 | Gemini 2.5 Pro | Thinking, 8K | 73.7 | #280 |
| 6 | Claude Opus 4.5 | High | 73.1 | #165 |
| 7 | DeepSeek Reasoner (Thinking 32K) (Olfactory Perception checkpoint unspecified) | 73.1 | ||
| 8 | DeepSeek Reasoner (Thinking 8K) (Olfactory Perception checkpoint unspecified) | 72.6 | ||
| 9 | Llama 3.3 70B Instruct | 72 | #1394 | |
| 10 | GPT-OSS-120B | High | 72 | #712 |
| 11 | GPT-5.2 Pro | High | 72 | #139 |
| 12 | Claude Sonnet 4.5 | 71.4 | #267 | |
| 13 | GPT-5 | High | 71.4 | #185 |
| 14 | GPT-5 Pro | 70.9 | #168 | |
| 15 | Grok 4.1 Fast | 70.3 | #431 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=olfactory-perception-benchmark-odor-pleasantness · How It Works · Data refreshed daily, snapshot 2026-11-22.