Open LMM Reasoning - MathVision - topology — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 100 models tracked.

Top models

#ModelScore
1GPT-4.1 Mini43.5
2InternVL2.5-78B39.1
3InternVL3-38B34.8
4InternVL2.5-2B34.8
5InternVL3-8B30.4
6MiniCPM-V-2.630.4
7Gemma 3 12B30.4
8InternVL3-78B26.1
9InternVL2-8B26.1
10InternVL3-14B21.7
11Ovis2-8B21.7
12Gemma 3 27B21.7
13Gemini 2.0 Flash21.7
14GPT-4.1 (2025-04-14)21.7
15Qwen 2 VL 72B17.4

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