Olfactory Perception Benchmark - Smell Identification: leaderboard
Olfactory Perception task: identify the odor source, such as a food or drink, of a mixture described by its volatile compounds, from four options. Accuracy in percent, higher is better.
Metric: Score (%) on smell identification (pick the odor source, such as a food, of a volatile-compound mixture from four options, 30 questions) 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: Around February 2027. 16 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 80 | #261 | |
| 2 | Claude Opus 4.6 | Max | 80 | #113 |
| 3 | GPT-5 Pro | 80 | #163 | |
| 4 | GPT-5 | High | 76.7 | #178 |
| 5 | Grok 4.1 Fast | 73.3 | #427 | |
| 6 | O4 Mini | High | 73.3 | #368 |
| 7 | Grok 3 Mini | Low | 73.3 | #565 |
| 8 | GPT-5.2 Pro | High | 73.3 | #137 |
| 9 | DeepSeek Reasoner (Thinking 32K) (Olfactory Perception checkpoint unspecified) | 73.3 | ||
| 10 | O3 | High | 70 | #237 |
| 11 | Claude Opus 4.5 | High | 70 | #160 |
| 12 | Gemini 2.5 Pro | Thinking, 32K | 70 | #276 |
| 13 | DeepSeek Reasoner (Thinking 16K) (Olfactory Perception checkpoint unspecified) | 70 | ||
| 14 | DeepSeek Reasoner (Thinking 8K) (Olfactory Perception checkpoint unspecified) | 63.3 | ||
| 15 | GPT-OSS-120B | High | 56.7 | #704 |
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-smell-identification · How It Works · Data refreshed daily, snapshot 2026-11-21.