Visual Instruction Following on ImageNet Instructive Visual Benchmark
85AccuracyLIVE
Evaluation Results
| Method | Links | |
|---|---|---|
| LIVEViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 85 | |
| LIVEViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 84.54 | |
| LIVEViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 83.51 | |
| LIVEViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 71.72 | |
| FusionViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 10.91 | |
| FusionViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 10.85 | |
| FusionViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 10.46 | |
| Menon et al.ViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 9.5 | |
| Menon et al.ViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 9.43 | |
| FusionViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 9.35 | |
| SigLipViT Model=SigLip 2 B/16, Evaluation Protocol=Zero-Shot2026.06 | 9.29 | |
| SigLipViT Model=SigLip 2 So400m, Evaluation Protocol=Zero-Shot2026.06 | 9.21 | |
| SigLipViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 8.45 | |
| Menon et al.ViT Model=SigLip B/16, Evaluation Protocol=Zero-Shot2026.06 | 8.17 | |
| Menon et al.ViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 7.93 | |
| SigLipViT Model=SigLip T/14, Evaluation Protocol=Zero-Shot2026.06 | 7.84 |