SPUR - Information Localization: leaderboard
Metric: Accuracy (%) on SPUR the 621 information localization 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 map panels to their experimental conditions; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 59.67 |
| 2 | GLM-4.5V | 57.65 |
| 3 | Claude 3.7 Sonnet (Thinking) | 57.45 |
| 4 | Ministral-3-8B-Instruct-2512 | 57.03 |
| 5 | Llama 4 Maverick | 56.61 |
| 6 | Seed-1.6 | 56.61 |
| 7 | Ministral-3-14B-Instruct-2512 | 56.56 |
| 8 | Gemini 2.5 Pro (Preview 06-05) | 56.47 |
| 9 | O4 Mini (High) | 55.34 |
| 10 | Qwen 3 VL 30B A3B (Thinking) | 55.27 |
| 11 | GPT-5.1 | 54.47 |
| 12 | Mistral Small 3.1 | 53.48 |
| 13 | Grok 4.1 Fast | 52.98 |
| 14 | Qwen 3 VL 30B A3B Instruct | 51.05 |
| 15 | InternVL3-78B | 49.84 |
Interactive version: theaggregate.ai/benchmark?slug=spur-information-localization · How It Works · Data refreshed daily, snapshot 2026-10-07.