Open LMM Reasoning - WeMath - Basic Transformations of Figures — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 76.2 |
| 2 | GPT-4.1 (2025-04-14) | 75.8 |
| 3 | Gemini 2.0 Flash | 71.7 |
| 4 | GPT-4o ChatGPT | 70.6 |
| 5 | Claude 3.7 Sonnet | 66.5 |
| 6 | Claude 3.5 Sonnet (20241022) | 66.2 |
| 7 | Gemini 1.5 Pro (002) | 65.9 |
| 8 | Qwen 2 VL 72B | 64 |
| 9 | InternVL3-38B | 62.6 |
| 10 | InternVL2.5-78B | 62.1 |
| 11 | InternVL3-8B | 61.3 |
| 12 | InternVL3-14B | 59.9 |
| 13 | Gemma 3 27B | 59.9 |
| 14 | InternVL3-78B | 58.4 |
| 15 | Grok 2 (1212) | 54.6 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-basic-transformations-of-figures · How the rankings work · Data refreshed daily, snapshot 2026-07-22.