Open LMM Reasoning - MathVista - MWP: leaderboard
The "MathVista - MWP" 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 | InternVL3-78B | 91.4 | #352 |
| 2 | SenseNova | 89.8 | |
| 3 | Ovis2-16B | 89.2 | |
| 4 | InternVL3-14B | 89.2 | #505 |
| 5 | InternVL3-38B | 88.2 | #405 |
| 6 | InternVL2.5-78B-MPO | 87.1 | |
| 7 | Step-1o | 87.1 | |
| 8 | SAIL-VL-1.5-8B | 87.1 | |
| 9 | SAIL-VL-1.6-8B | 87.1 | |
| 10 | Ovis2-34B | 86.6 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-mwp · How It Works · Data refreshed daily, snapshot 2026-10-20.