Open LMM Reasoning - WeMath - Angles and Length — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 66.3 |
| 2 | Gemini 1.5 Pro (002) | 61.8 |
| 3 | Gemini 2.0 Flash | 56.3 |
| 4 | GPT-4.1 (2025-04-14) | 55.1 |
| 5 | Gemma 3 27B | 53.7 |
| 6 | Qwen 2 VL 72B | 45.1 |
| 7 | Ovis2-8B | 44.4 |
| 8 | InternVL3-38B | 42.5 |
| 9 | GPT-4o ChatGPT | 42.5 |
| 10 | Aquila-VL-2B | 41.8 |
| 11 | Gemma 3 4B | 41 |
| 12 | Qwen 2 VL 7B | 38.4 |
| 13 | InternVL3-8B | 37.7 |
| 14 | InternVL3-14B | 37.2 |
| 15 | QVQ-72B-Preview | 35.1 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-angles-and-length · How the rankings work · Data refreshed daily, snapshot 2026-07-22.