Open LMM Reasoning - MathVista - FQA: leaderboard
The "MathVista - FQA" 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 | SenseNova | 80.7 | |
| 2 | GPT-4.1-mini-20250414 | 79.2 | |
| 3 | InternVL3-78B | 78.1 | #352 |
| 4 | Qwen2.5-VL-72B | 77.7 | |
| 5 | QVQ-72B-Preview | 77.7 | #440 |
| 6 | Taichu-VLR-7B | 77 | #526 |
| 7 | Qwen2-VL-72B | 76.6 | |
| 8 | GLM-4v-Plus-20250111 | 76.6 | |
| 9 | MUG-U-7B | 76.2 | |
| 10 | InternVL2.5-78B-MPO | 75.5 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-fqa · How It Works · Data refreshed daily, snapshot 2026-10-20.