SciVQR - Mathematics: leaderboard
Metric: Mathematics accuracy (%) with zero-shot chain-of-thought prompting on SciVQR (3,254 image-based scientific questions from competitions, entrance exams and graduate-level sources, 78 percent multiple-choice and 22 percent free-form, in English and Chinese, high-school to graduate level); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 15 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O4 Mini | 84.5 |
| 2 | Gemini 2.5 Flash (Preview 04-17) | 83.2 |
| 3 | O1 | 79.2 |
| 4 | Qwen 2.5 VL 72B Instruct | 54.3 |
| 5 | GPT-4o | 47.4 |
| 6 | Qwen 2.5 VL 7B Instruct | 35.4 |
Interactive version: theaggregate.ai/benchmark?slug=scivqr-mathematics · How It Works · Data refreshed daily, snapshot 2026-10-07.