Open LMM Reasoning - WeMath - InsufficientKnowledge (Loose): leaderboard
Metric: Accuracy (%). Source: huggingface.co. 83 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 97.7 |
| 2 | Llama 3.2 11B Instruct | 80 |
| 3 | Qwen 2 VL 2B | 65.9 |
| 4 | InternVL2.5-2B | 63.8 |
| 5 | Aquila-VL-2B | 54.9 |
| 6 | Qwen 2 VL 7B | 50.1 |
| 7 | InternVL2-8B | 47 |
| 8 | InternVL2.5-8B-BoN-8 | 45.9 |
| 9 | Gemma 3 4B | 43.6 |
| 10 | Gemma 3 12B | 39.6 |
| 11 | Taichu-VLR-3B | 38.9 |
| 12 | Qwen 2 VL 72B | 37.3 |
| 13 | URSA-8B | 37.3 |
| 14 | VLAA-Thinker-Qwen2.5VL-3B | 36.6 |
| 15 | VLM-R1-3B-Math-0305 | 36.2 |
Interactive version: theaggregate.ai/benchmark?slug=open-lmm-reasoning-wemath-insufficientknowledge-loose · How It Works · Data refreshed daily, snapshot 2026-09-05.