Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Distribution Shift Robustness on MNLI matched → mismatched
Loading...
0.0219
ID ECE
UAT-LITE
0.011204
0.083402
0.1556
0.227798
Feb 3, 2026
ID ECE
OOD ECE
ΔECE
Avg ECE
Updated 5d ago
Evaluation Results
Method
Method
Links
ID ECE
OOD ECE
ΔECE
Avg ECE
UAT-LITE
2026.02
0.0219
0.0145
-0.0074
0.0182
BERT-base
2026.02
0.2893
0.3017
0.0124
0.2955
Feedback
Search any
task
Search any
task