List your company
ResearchFormerly WizWand

Vision-language alignment on ImageNet-100 (Accuracy)

83.67AccuracyGADL
-3.003619.49824264.5018Sep 11, 2025
Updated 4mo ago

Evaluation results

MethodLinks
GADLVision Family=DINOv2, Vision Backbone=ViT-B/14, Language Model=all-mpnet-base-v22025.0983.67
GADLVision Family=CLIP, Vision Backbone=ViT-L/14, Language Model=all-mpnet-base-v22025.0974
GADLVision Family=DINOv2, Vision Backbone=ViT-L/14, Language Model=All-Roberta-large-v12025.0969.67
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16, Language Model=all-mpnet-base-v22025.0967.33
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0967.33
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16d@384, Language Model=All-Roberta-large-v12025.0965.67
GADLVision Family=CLIP, Vision Backbone=RN50x16, Language Model=All-Roberta-large-v12025.0963.67
GADLVision Family=DINOv2, Vision Backbone=ViT-S/14, Language Model=All-Roberta-large-v12025.0963.67
GADLVision Family=CLIP, Vision Backbone=ViT-L/14, Language Model=All-Roberta-large-v12025.0961
GADLVision Family=DINOv2, Vision Backbone=ViT-B/14, Language Model=All-Roberta-large-v12025.0960.33
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16, Language Model=All-Roberta-large-v12025.0958.67
GADLVision Family=CLIP, Vision Backbone=RN50x64, Language Model=All-Roberta-large-v12025.0958
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16@384, Language Model=All-Roberta-large-v12025.0957.67
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16d, Language Model=All-Roberta-large-v12025.0954.33
GADLVision Family=DINOv2, Vision Backbone=ViT-G/14, Language Model=All-Roberta-large-v12025.0949.33
GADLVision Family=DINOv2, Vision Backbone=ViT-L/14, Language Model=all-mpnet-base-v22025.0948.33
GADLVision Family=CLIP, Vision Backbone=ViT-L/14@336, Language Model=All-Roberta-large-v12025.0945.33
GADLVision Family=DINOv2, Vision Backbone=ViT-G/14, Language Model=all-mpnet-base-v22025.0944.33
GADLVision Family=CLIP, Vision Backbone=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0941.33
GADLVision Family=CLIP, Vision Backbone=RN50x16, Language Model=all-mpnet-base-v22025.0940.67
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16d, Language Model=all-mpnet-base-v22025.0938.33
GADLVision Family=CLIP, Vision Backbone=RN50x64, Language Model=all-mpnet-base-v22025.0937.33
GADLVision Family=DINOv2, Vision Backbone=ViT-S/14, Language Model=all-mpnet-base-v22025.0935.67
GADLVision Family=DeiT, Vision Backbone=DeiT-B/16@384, Language Model=all-mpnet-base-v22025.0935.33
GADLVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.0920.2
GADLVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.0919.6
GADLVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.0913
GADLVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.0910.4
LocalCKAVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.099.33
GADLVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.098.8
LocalCKAVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.098.33
LocalCKAVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.098.33
LocalCKAVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.098
Hahn-GrantVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.096.33
LocalCKAVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.096
GADLVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.095.8
LocalCKAVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.095.33
Hahn-GrantVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.094.93
MPOptVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.094.67
Hahn-GrantVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.094.67
GurobiVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.094.5
FAQVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.094.33
FAQVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.094.33
MPOptVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.094
FAQVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.093.67
GurobiVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.093.56
FAQVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.093.33
GurobiVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.093.22
GurobiVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.093
FAQVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.093
MPOptVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.092.67
MPOptVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.092.67
GurobiVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.092.5
FAQVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.092.33
OTVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.092
Hahn-GrantVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-mpnet-base-v22025.091.67
GurobiVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.091.5
OTVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-mpnet-base-v22025.091.33
Hahn-GrantVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.091.33
Hahn-GrantVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.091.22
OTVision Model=CLIP, Vision Model Architecture=ViT-L/14@336, Language Model=all-roberta-large-v12025.091
MPOptVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.091
OTVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-mpnet-base-v22025.091
OTVision Model=DeiT, Vision Model Architecture=DeiT-B/16d@384, Language Model=all-roberta-large-v12025.090.67
MPOptVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.090.67
OTVision Model=DINOv2, Vision Model Architecture=ViT-G/14, Language Model=all-roberta-large-v12025.090.33