Open LMM Reasoning - MathVision - combinatorics — leaderboard

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

Top models

#ModelScore
1GPT-4.1 (2025-04-14)51.2
2GPT-4.1 Mini46.4
3GPT-4o ChatGPT42.9
4Doubao-1.5-Pro40.5
5Claude 3.7 Sonnet39.9
6Gemini 2.0 Flash35.7
7Gemma 3 27B33.3
8Gemini 1.5 Pro (002)32.7
9InternVL3-38B32.1
10QVQ-72B-Preview32.1
11InternVL3-78B31
12Claude 3.5 Sonnet (20241022)30.4
13GPT-4.1 Nano29.2
14InternVL2.5-78B29.2
15InternVL3-14B26.2

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