Open LMM Reasoning - WeMath: leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Doubao-1.5-Pro | 65.7 |
| 2 | GPT-4.1 (2025-04-14) | 55.5 |
| 3 | GPT-4o ChatGPT | 50.6 |
| 4 | Gemini 1.5 Pro (002) | 50.5 |
| 5 | InternVL3-38B | 49.3 |
| 6 | Claude 3.7 Sonnet | 49.3 |
| 7 | Gemini 2.0 Flash | 47.4 |
| 8 | InternVL3-78B | 46.1 |
| 9 | Claude 3.5 Sonnet (20241022) | 44 |
| 10 | Taichu-VLR-7B | 44 |
| 11 | VLAA-Thinker-Qwen2.5VL-7B | 41.5 |
| 12 | Gemma 3 27B | 40.7 |
| 13 | InternVL2.5-78B | 39.8 |
| 14 | InternVL3-8B | 39.5 |
| 15 | QVQ-72B-Preview | 39 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath · How It Works · Data refreshed daily, snapshot 2026-09-05.