Open LMM Reasoning - WeMath - Calculation of Plane Figures: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 90.7 |
| 2 | InternVL3-38B | 83.5 |
| 3 | GPT-4.1 (2025-04-14) | 83.3 |
| 4 | Claude 3.7 Sonnet | 82.2 |
| 5 | VLAA-Thinker-Qwen2.5VL-7B | 82 |
| 6 | Taichu-VLR-7B | 81.3 |
| 7 | Claude 3.5 Sonnet (20241022) | 80.9 |
| 8 | Gemini 1.5 Pro (002) | 80.8 |
| 9 | InternVL2.5-78B | 80.4 |
| 10 | InternVL3-78B | 80.3 |
| 11 | GPT-4o ChatGPT | 80.1 |
| 12 | Gemini 2.0 Flash | 79.9 |
| 13 | InternVL3-8B | 78 |
| 14 | QVQ-72B-Preview | 77.7 |
| 15 | InternVL2.5-8B-BoN-8 | 77.6 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-calculation-of-plane-figures · How It Works · Data refreshed daily, snapshot 2026-09-05.