Visual Instruction Following on SUN Instructive Visual Benchmark
44.68AccuracyLIVE
Evaluation Results
| Method | Links | |
|---|---|---|
| LIVEViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 44.68 | |
| LIVEViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 41.55 | |
| LIVEViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 41.41 | |
| LIVEViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 26.87 | |
| Menon et al.ViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 15.26 | |
| Menon et al.ViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 14.41 | |
| SigLipViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 10.81 | |
| FusionViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 10.54 | |
| SigLipViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 10.08 | |
| FusionViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 10.02 | |
| Menon et al.ViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 9.68 | |
| SigLipViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 8.41 | |
| FusionViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 8.06 | |
| Menon et al.ViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 6.72 | |
| SigLipViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 6.13 | |
| FusionViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 5.5 |