Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Calibration on MASSIVE
Loading...
0.586
ECE (Wrong Samples)
CUD
0.57612
0.64281
0.7095
0.77619
Feb 13, 2026
ECE (Wrong Samples)
Brier Score (Wrong Samples)
Updated 4d ago
Evaluation Results
Method
Method
Links
ECE (Wrong Samples)
Brier Score (Wrong Samples)
CUD
Teacher Training=Fine-...
2026.02
0.586
1.213
TinyBERT
Teacher Training=Fine-...
2026.02
0.692
1.469
CKD
Teacher Training=Fine-...
2026.02
0.764
1.54
AD-KD
Teacher Training=Fine-...
2026.02
0.833
1.667
Feedback
Search any
task
Search any
task