OpenVLM MMT-Bench - Handwritten Mathematical Expression Recognition: leaderboard
Metric: Score (%). Source: huggingface.co. 207 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | InternVL3-78B | 90 |
| 2 | InternVL3-8B | 90 |
| 3 | InternVL3-38B | 90 |
| 4 | Claude 3.7 Sonnet | 90 |
| 5 | Gemini 1.5 Pro | 90 |
| 6 | Claude 3.5 Sonnet | 90 |
| 7 | Grok 2 (1212) | 90 |
| 8 | Gemma 3 12B | 90 |
| 9 | InternVL2-8B | 80 |
| 10 | Qwen 2 VL 72B | 80 |
| 11 | Aquila-VL-2B | 80 |
| 12 | Pixtral-12B | 80 |
| 13 | Gemini 1.5 Flash | 80 |
| 14 | GPT-4.1 (2025-04-14) | 80 |
| 15 | Llama 3.2 90B Vision Instruct | 80 |
Interactive version: theaggregate.ai/benchmark?slug=openvlm-mmt-bench-handwritten-mathematical-expression-recognition · How It Works · Data refreshed daily, snapshot 2026-09-05.