Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
UMUI Judgment Calibration on UNLI (full)
Loading...
0.0573
MSE
CLUE-D
0.028472
0.223061
0.41765
0.612239
Apr 9, 2026
MSE
NLL
ECE
Updated 6d ago
Evaluation Results
Method
Method
Links
MSE
NLL
ECE
CLUE-D
Parameters=3B
2026.04
0.0573
0.509
0.0592
Q3-VL
Parameters=32B
2026.04
0.0753
0.666
0.0298
TMTO
Parameters=14B
2026.04
0.0757
0.555
0.147
CLUE-T
Parameters=3B
2026.04
0.081
0.955
0.097
Q3
Parameters=32B
2026.04
0.106
1.09
0.133
Q2.5-O
Parameters=7B
2026.04
0.114
1.51
0.142
Q2.5-VL
Parameters=32B
2026.04
0.126
3.1
0.155
AF
Parameters=7B
2026.04
0.272
8.87
0.385
Q2-A
Parameters=7B
2026.04
0.778
8.85
0.379
Feedback
Search any
task
Search any
task
