Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal In-context Learning on Multimodal Benchmarks Average
Loading...
67.2
Accuracy
AIMv2
38.184
45.717
53.25
60.783
Nov 21, 2024
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
AIMv2
architecture=ViT-L/14,...
2024.11
67.2
DFN-CLIP
architecture=ViT-H/14,...
2024.11
66.4
OAI CLIP
architecture=ViT-L/14,...
2024.11
66.1
AIMv2
architecture=ViT-L/14,...
2024.11
63.8
DFN-CLIP
architecture=ViT-H/14,...
2024.11
62.5
OAI CLIP
architecture=ViT-L/14,...
2024.11
62.2
DFN-CLIP
architecture=ViT-H/14,...
2024.11
40.9
AIMv2
architecture=ViT-L/14,...
2024.11
39.6
OAI CLIP
architecture=ViT-L/14,...
2024.11
39.3
Feedback
Search any
task
Search any
task
