Visual Reasoning on BabyVision
31.7AccuracySenseNova-U1
Evaluation Results
| Method | Links | |
|---|---|---|
| SenseNova-U1Parameters=30BA3B, Internal Reasoning (Think mode)=true2026.05 | 31.7 | |
| Qwen3.5Parameters=35BA3B, Internal Reasoning (Think mode)=false2026.05 | 29.6 | |
| Qwen3.5Parameters=9B, Internal Reasoning (Think mode)=false2026.05 | 25.8 | |
| SenseNova-U1Parameters=8B, Internal Reasoning (Think mode)=true2026.05 | 25 | |
| Qwen3VLParameters=30BA3B, Internal Reasoning (Think mode)=true2026.05 | 18.6 | |
| Qwen3VLParameters=8B, Internal Reasoning (Think mode)=true2026.05 | 17.78 | |
| DeepLatent-RL-7BModel Category=Latent Visual reasoning Models, Training Stage=RL, Training Data=full DeepLatent-180K dataset2026.05 | 16.2 | |
| DeepLatent-RL-7B*Model Category=Latent Visual reasoning Models, Training Stage=RL, Training Data=visual search data of DeepLatent-180K in SFT Stage 22026.05 | 14.9 | |
| DeepLatent-SFT-7BModel Category=Latent Visual reasoning Models, Training Stage=SFT2026.05 | 14.4 | |
| Qwen2.5-VL-7BModel Category=Open-source Models2026.05 | 12.9 | |
| InternVL3-8BModel Category=Open-source Models2026.05 | 12.9 | |
| Gemma4Parameters=26BA4B, Internal Reasoning (Think mode)=false2026.05 | 11.34 |