Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Uncertainty Estimation on VLM-are-biased
Loading...
0.722
Verb-U
Verb-U
0.59512
0.62806
0.661
0.69394
Jun 30, 2026
Verb-U
A-E
SE
C&U
VL-U
VSE
Updated 24d ago
Evaluation Results
Method
Method
Links
Verb-U
A-E
SE
C&U
VL-U
VSE
Verb-U
Model=Qwen2.5-VL
2026.06
0.722
-
-
-
-
-
Verb-U
Model=Gemma3
2026.06
0.6
-
-
-
-
-
A-E
Model=Qwen2.5-VL
2026.06
-
0.537
-
-
-
-
SE
Model=Qwen2.5-VL
2026.06
-
-
0.728
-
-
-
C&U
Model=Qwen2.5-VL
2026.06
-
-
-
0.697
-
-
VL-U
Model=Qwen2.5-VL
2026.06
-
-
-
-
0.783
-
VSE
Model=Qwen2.5-VL
2026.06
-
-
-
-
-
0.826
A-E
Model=Gemma3
2026.06
-
0.694
-
-
-
-
SE
Model=Gemma3
2026.06
-
-
0.7
-
-
-
C&U
Model=Gemma3
2026.06
-
-
-
0.737
-
-
VL-U
Model=Gemma3
2026.06
-
-
-
-
0.758
-
VSE
Model=Gemma3
2026.06
-
-
-
-
-
0.776
Feedback
Search any
task
Search any
task