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

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

Top models

#ModelScore
1Doubao-1.5-Pro90.7
2InternVL3-38B83.5
3GPT-4.1 (2025-04-14)83.3
4Claude 3.7 Sonnet82.2
5Claude 3.5 Sonnet (20241022)80.9
6Gemini 1.5 Pro (002)80.8
7InternVL2.5-78B80.4
8InternVL3-78B80.3
9GPT-4o ChatGPT80.1
10Gemini 2.0 Flash79.9
11InternVL3-14B78.4
12InternVL3-8B78
13QVQ-72B-Preview77.7
14Grok 2 (1212)74.3
15InternVL2-8B72.7

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