SPUR - Morphological Perception: leaderboard
Metric: Accuracy (%) on SPUR the 634 morphological perception multiple-choice questions about multi-panel biomedical experimental figures from PubMed Central papers (questions drafted by GPT-4o, kept only when GPT-4o failed them in at least six of ten text-only attempts, then expert-reviewed): the questions ask the model to analyze cell shape, tissue architecture and other structures in stained preparations; higher is better. Source: arxiv.org. Saturation forecast: Around January 2028. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 67.74 |
| 2 | O4 Mini (High) | 64.5 |
| 3 | Claude 3.7 Sonnet (Thinking) | 64.32 |
| 4 | Seed-1.6 | 63.51 |
| 5 | Gemini 2.5 Pro (Preview 06-05) | 62.97 |
| 6 | GLM-4.5V | 61.99 |
| 7 | GPT-5.1 | 61.72 |
| 8 | Ministral-3-14B-Instruct-2512 | 61.4 |
| 9 | Llama 4 Maverick | 59.78 |
| 10 | Qwen 3 VL 30B A3B (Thinking) | 58 |
| 11 | Ministral-3-8B-Instruct-2512 | 57.03 |
| 12 | Grok 4.1 Fast | 55.99 |
| 13 | Qwen 3 VL 30B A3B Instruct | 53.31 |
| 14 | InternVL3-78B | 51.97 |
| 15 | Mistral Small 3.1 | 51.92 |
Interactive version: theaggregate.ai/benchmark?slug=spur-morphological-perception · How It Works · Data refreshed daily, snapshot 2026-10-07.