Open LMM Reasoning - WeMath - Understanding and Conversion of Units — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o ChatGPT | 95.6 |
| 2 | InternVL3-38B | 95.1 |
| 3 | Claude 3.5 Sonnet (20241022) | 94.4 |
| 4 | Doubao-1.5-Pro | 94.4 |
| 5 | GPT-4.1 (2025-04-14) | 94 |
| 6 | Gemini 1.5 Pro (002) | 92.9 |
| 7 | QVQ-72B-Preview | 91.7 |
| 8 | InternVL3-78B | 90.8 |
| 9 | InternVL3-14B | 88.7 |
| 10 | Gemini 2.0 Flash | 88.7 |
| 11 | Claude 3.7 Sonnet | 87.8 |
| 12 | Gemma 3 12B | 87.6 |
| 13 | Gemma 3 27B | 87.1 |
| 14 | Qwen 2 VL 72B | 81 |
| 15 | Grok 2 (1212) | 80.7 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-understanding-and-conversion-of-units · How the rankings work · Data refreshed daily, snapshot 2026-07-22.