Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Video Action Recognition on Perception Test
Loading...
60.9
Top-1 Accuracy
OV-Encoder (Codec)
47.172
50.736
54.3
57.864
Feb 9, 2026
Top-1 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Top-1 Accuracy
OV-Encoder (Codec)
Backbone=ViT-L/14, Res...
2026.02
60.9
DINOv3
Backbone=ViT-L/14, Res...
2026.02
60.8
OV-Encoder (Frame)
Backbone=ViT-L/14, Res...
2026.02
60.3
OV-Encoder (Codec)
Backbone=ViT-L/14, Res...
2026.02
60
DINOv3
Backbone=ViT-L/14, Res...
2026.02
59.3
OV-Encoder (Frame)
Backbone=ViT-L/14, Res...
2026.02
58.3
AIMv2
Backbone=ViT-L/14, Res...
2026.02
56.4
AIMv2
Backbone=ViT-L/14, Res...
2026.02
55.1
SigLIP2
Backbone=ViT-L/16, Res...
2026.02
53.3
SigLIP2
Backbone=ViT-L/16, Res...
2026.02
52.7
CLIP
Backbone=ViT-L/14, Res...
2026.02
52.2
MetaCLIP2
Backbone=ViT-L/14, Res...
2026.02
51.1
SigLIP
Backbone=ViT-L/16, Res...
2026.02
51
MetaCLIP
Backbone=ViT-L/14, Res...
2026.02
49.8
SigLIP
Backbone=ViT-L/16, Res...
2026.02
48.9
MetaCLIP2
Backbone=ViT-L/14, Res...
2026.02
47.7
Feedback
Search any
task
Search any
task