Open LMM Reasoning - WeMath - Calculation of Solid Figures — leaderboard

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

Top models

#ModelScore
1Doubao-1.5-Pro90.5
2Claude 3.7 Sonnet85.5
3GPT-4.1 (2025-04-14)85.5
4GPT-4o ChatGPT85.3
5InternVL3-8B82.4
6Gemma 3 4B81.7
7Gemma 3 27B81.3
8InternVL3-78B81.2
9Claude 3.5 Sonnet (20241022)80.9
10InternVL3-14B80.7
11InternVL3-38B80
12Gemini 2.0 Flash77.8
13Gemma 3 12B77.5
14Gemini 1.5 Pro (002)76.9
15Qwen 2 VL 72B76.7

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