Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Understanding on Multiple Datasets Aggregate
Loading...
79.09
Average Score
UniFlow-XL
45.5084
54.2267
62.945
71.6633
Oct 12, 2025
Nov 3, 2025
Nov 25, 2025
Dec 18, 2025
Jan 9, 2026
Jan 31, 2026
Feb 23, 2026
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Score
UniFlow-XL
Vision Encoder=InternV...
2025.10
79.09
TokenFlow-XL
Vision Encoder=SigLIP-...
2025.10
73.04
UniFlow-LV
Vision Encoder=InternV...
2025.10
69.04
UniFlow-LV
Vision Encoder=SigLIP2...
2025.10
67.87
UniFlow-LV
Vision Encoder=DFN-CLI...
2025.10
65.02
TokenFlow-L
Vision Encoder=ViTamin...
2025.10
62.4
Mobile-O-0.5B
Type=Und. and Gen. ≤ 2...
2026.02
62.1
FastVLM-0.5B
Type=Und. Only ≤ 1B, #...
2026.02
60.5
TokenFlow-B
Vision Encoder=CLIP-B,...
2025.10
60.21
EMU3-8B
Type=Und. and Gen. > 2...
2026.02
59.4
UniFlow-LV
Vision Encoder=DINOv2-...
2025.10
58.92
JanusFlow
Type=Und. and Gen. ≤ 2...
2026.02
57
Janus
Type=Und. and Gen. ≤ 2...
2026.02
54
Show-o-Clip-ViT
Type=Und. and Gen. ≤ 2...
2026.02
46.8
Feedback
Search any
task
Search any
task