Open LMM Reasoning - MathVista - TQA — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 79.1 |
| 2 | GPT-4.1 Mini | 77.8 |
| 3 | Gemini 2.0 Flash | 77.8 |
| 4 | GPT-4o ChatGPT | 77.2 |
| 5 | GPT-4.1 (2025-04-14) | 76.6 |
| 6 | InternVL2.5-78B | 75.9 |
| 7 | Gemini 1.5 Pro (002) | 75.3 |
| 8 | Claude 3.7 Sonnet | 74.7 |
| 9 | InternVL3-78B | 74.1 |
| 10 | Qwen 2 VL 72B | 74.1 |
| 11 | InternVL3-38B | 74.1 |
| 12 | Claude 3.5 Sonnet (20241022) | 74.1 |
| 13 | InternVL3-14B | 72.8 |
| 14 | Ovis2-8B | 72.2 |
| 15 | Gemma 3 27B | 70.9 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-tqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.