Visual Question Answering on VQA v2 (Acc.)
82.8AccuracyLLaVA-Next
Evaluation Results
| Method | Links | |
|---|---|---|
| LLaVA-NextParams (B)=13, Text Gen Arch=AR, Image Gen Arch=-2025.05 | 82.8 | |
| QWEN-VLParams (B)=7, Text Gen Arch=AR, Image Gen Arch=-2025.05 | 78.2 | |
| MudditParams (B)=1, Text Gen Arch=Discrete Diff., Image Gen Arch=Discrete Diff., Resolution=1024×10242025.05 | 70.2 | |
| Show-OParams (B)=1.3, Text Gen Arch=AR, Image Gen Arch=Discrete Diff., Resolution=512×5122025.05 | 69.4 | |
| MudditParams (B)=1, Text Gen Arch=Discrete Diff., Image Gen Arch=Discrete Diff., Resolution=512×5122025.05 | 68.2 | |
| BLIP-2Params (B)=13, Text Gen Arch=AR, Image Gen Arch=-2025.05 | 65 | |
| Show-OParams (B)=1.3, Text Gen Arch=AR, Image Gen Arch=Discrete Diff., Resolution=256×2562025.05 | 64.7 | |
| D-DiTParams (B)=2, Text Gen Arch=Discrete Diff., Image Gen Arch=Diffusion, Resolution=512×5122025.05 | 60.1 | |
| D-DiTParams (B)=2, Text Gen Arch=Discrete Diff., Image Gen Arch=Diffusion, Resolution=256×2562025.05 | 59.5 | |
| LWMParams (B)=7, Text Gen Arch=AR, Image Gen Arch=AR2025.05 | 55.8 | |
| FlamingoParams (B)=9, Text Gen Arch=AR, Image Gen Arch=-2025.05 | 51.8 | |
| OpenFlamingoParams (B)=9, Text Gen Arch=AR, Image Gen Arch=-2025.05 | 43.5 |