Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
UMUI Judgment Calibration on WIKIVIDEO (v)
Loading...
0.0784
MSE
CLUE-D
0.075456
0.095328
0.1152
0.135072
Apr 9, 2026
MSE
NLL
ECE
Updated 6d ago
Evaluation Results
Method
Method
Links
MSE
NLL
ECE
CLUE-D
Parameters=3B
2026.04
0.0784
0.497
8.47
CLUE-D
Parameters=3B
2026.04
0.0792
0.503
8.42
CLUE-T
Parameters=3B
2026.04
0.0978
0.872
12.1
CLUE-T
Parameters=3B
2026.04
0.1
0.801
12.1
Q3-VL
Parameters=32B
2026.04
0.105
2.71
11.5
Q2.5-VL
Parameters=32B
2026.04
0.133
2.57
17.4
Q2.5-O
Parameters=7B
2026.04
0.142
3.94
16.2
Q2.5-O
Parameters=7B
2026.04
0.152
4.06
18.5
Feedback
Search any
task
Search any
task
