Open LMM Reasoning - MathVista - GEO: leaderboard
The "MathVista - GEO" 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 | 89.1 | #287 |
| 2 | InternVL2.5-78B-MPO | 84.1 | |
| 3 | Gemini-2.0-Pro | 83.7 | |
| 4 | InternVL3-78B | 83.3 | #352 |
| 5 | GLM-4v-Plus-20250111 | 82.8 | |
| 6 | SenseNova | 82 | |
| 7 | Gemini-2.0-Flash | 81.6 | |
| 8 | Ovis2-34B | 81.2 | |
| 9 | InternVL2.5-38B-MPO | 80.8 | |
| 10 | Gemini-1.5-Pro-002 | 80.3 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-geo · How It Works · Data refreshed daily, snapshot 2026-10-20.