Open LMM Reasoning - MathVista - SCI: leaderboard
The "MathVista - SCI" 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 | GPT-4.1-mini-20250414 | 77.9 | |
| 2 | GPT-4.1-20250414 | 76.2 | |
| 3 | HunYuan-Standard-Vision | 74.6 | |
| 4 | ChatGPT-4o-latest | 74.6 | |
| 5 | Claude3.5-Sonnet-20241022 | 73.8 | |
| 6 | InternVL3-14B | 73.8 | #505 |
| 7 | SenseNova | 73 | |
| 8 | Gemini-2.0-Flash | 73 | |
| 9 | Ovis2-34B | 73 | |
| 10 | InternVL3-38B | 73 | #405 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-sci · How It Works · Data refreshed daily, snapshot 2026-10-20.