Open LMM Reasoning - MathVision - metric geometry - length — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 62.1 |
| 2 | GPT-4.1 (2025-04-14) | 53.2 |
| 3 | GPT-4o ChatGPT | 52.6 |
| 4 | GPT-4.1 Mini | 51.4 |
| 5 | Gemini 2.0 Flash | 51.2 |
| 6 | Gemini 1.5 Pro (002) | 48.3 |
| 7 | InternVL3-78B | 46.5 |
| 8 | Gemma 3 27B | 45.2 |
| 9 | Claude 3.7 Sonnet | 44.3 |
| 10 | InternVL3-38B | 41.6 |
| 11 | QVQ-72B-Preview | 40.3 |
| 12 | Claude 3.5 Sonnet (20241022) | 38.3 |
| 13 | InternVL3-14B | 37.4 |
| 14 | InternVL2.5-78B | 35 |
| 15 | Gemma 3 12B | 34.5 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-mathvision-metric-geometry-length · How the rankings work · Data refreshed daily, snapshot 2026-07-22.