Open LMM Reasoning - MathVista - TQA: leaderboard
The "MathVista - TQA" subtask of Open LMM Reasoning. A task from the Open LMM Reasoning leaderboard, which evaluates large multimodal models on multi-step visual, mathematical and logical reasoning problems.
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Doubao-1.5-Pro | 79.1 | #287 |
| 2 | Gemini-2.0-Flash | 77.8 | |
| 3 | GPT-4.1-mini-20250414 | 77.8 | |
| 4 | Gemini-2.0-Pro | 77.2 | |
| 5 | ChatGPT-4o-latest | 77.2 | |
| 6 | GPT-4.1-20250414 | 76.6 | |
| 7 | InternVL2.5-78B | 75.9 | #431 |
| 8 | Gemini-1.5-Pro-002 | 75.3 | |
| 9 | Claude3.7-Sonnet | 74.7 | |
| 10 | InternVL2.5-78B-COT | 74.7 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-tqa · How It Works · Data refreshed daily, snapshot 2026-10-20.