List your company
ResearchFormerly WizWand

Self-evaluation on MMVet (AUROC)

0.886AUROCVAUQ
0.269280.429390.58950.74961Feb 24, 2026
Updated 8mo ago

Evaluation results

MethodLinks
VAUQModel=LLaVA-1.5-13B2026.020.886
Semantic EntropyModel=LLaVA-1.5-13B2026.020.864
VL-UncertaintyModel=LLaVA-1.5-13B2026.020.859
EigenScoreModel=LLaVA-1.5-13B2026.020.851
VL-UncertaintyModel=LLaVA-1.5-7B2026.020.823
VAUQModel=LLaVA-1.5-7B2026.020.815
Semantic EntropyModel=LLaVA-1.5-7B2026.020.813
PerplexityModel=LLaVA-1.5-13B2026.020.813
PerplexityModel=LLaVA-1.5-7B2026.020.793
VAUQBackbone=Qwen-2.5-VL-7B2026.020.783
EigenScoreModel=LLaVA-1.5-7B2026.020.782
PerplexityBackbone=Qwen-2.5-VL-7B2026.020.766
VAUQBackbone=InternVL3.5-8B2026.020.758
VL-UncertaintyBackbone=InternVL3.5-8B2026.020.757
VerbalizedModel=LLaVA-1.5-7B2026.020.717
Contextual LensModel=LLaVA-1.5-7B2026.020.708
Semantic EntropyBackbone=InternVL3.5-8B2026.020.704
VL-UncertaintyBackbone=Qwen-2.5-VL-7B2026.020.697
PerplexityBackbone=InternVL3.5-8B2026.020.675
VerbalizedModel=LLaVA-1.5-13B2026.020.672
Contextual LensBackbone=Qwen-2.5-VL-7B2026.020.655
EigenScoreBackbone=InternVL3.5-8B2026.020.641
Contextual LensModel=LLaVA-1.5-13B2026.020.614
Chain-of-EmbeddingsModel=LLaVA-1.5-7B2026.020.608
EigenScoreBackbone=Qwen-2.5-VL-7B2026.020.608
Semantic EntropyBackbone=Qwen-2.5-VL-7B2026.020.601
Chain-of-EmbeddingsBackbone=Qwen-2.5-VL-7B2026.020.598
Contextual LensBackbone=InternVL3.5-8B2026.020.596
VerbalizedBackbone=InternVL3.5-8B2026.020.594
SVARBackbone=Qwen-2.5-VL-7B2026.020.546
Chain-of-EmbeddingsBackbone=InternVL3.5-8B2026.020.528
VerbalizedBackbone=Qwen-2.5-VL-7B2026.020.519
SVARBackbone=InternVL3.5-8B2026.020.497
Chain-of-EmbeddingsModel=LLaVA-1.5-13B2026.020.444
SVARModel=LLaVA-1.5-13B2026.020.342
SVARModel=LLaVA-1.5-7B2026.020.293