Open LMM Reasoning - MathVista - LOG: leaderboard
The "MathVista - LOG" 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-4.1-20250414 | 54.1 | |
| 2 | GPT-4.1-mini-20250414 | 51.4 | |
| 3 | Claude3.5-Sonnet-20241022 | 45.9 | |
| 4 | Qwen2.5-VL-72B | 45.9 | |
| 5 | SenseNova | 43.2 | |
| 6 | Gemini-2.0-Pro | 43.2 | |
| 7 | ChatGPT-4o-latest | 43.2 | |
| 8 | Doubao-1.5-Pro | 37.8 | #287 |
| 9 | Ovis2-34B | 37.8 | |
| 10 | InternVL3-9B | 37.8 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvista-log · How It Works · Data refreshed daily, snapshot 2026-10-20.