Open LMM Reasoning - WeMath - Angles and Length — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.

Top models

#ModelScore
1Doubao-1.5-Pro66.3
2Gemini 1.5 Pro (002)61.8
3Gemini 2.0 Flash56.3
4GPT-4.1 (2025-04-14)55.1
5Gemma 3 27B53.7
6Qwen 2 VL 72B45.1
7Ovis2-8B44.4
8InternVL3-38B42.5
9GPT-4o ChatGPT42.5
10Aquila-VL-2B41.8
11Gemma 3 4B41
12Qwen 2 VL 7B38.4
13InternVL3-8B37.7
14InternVL3-14B37.2
15QVQ-72B-Preview35.1

Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-angles-and-length · How the rankings work · Data refreshed daily, snapshot 2026-07-22.