Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Confidence Estimation on MMLU (test)
Loading...
0.07
ECE (Smoothed)
NWKR
0.066
0.093
0.12
0.147
Jun 5, 2026
ECE (Smoothed)
AUC-EURO (low)
AUC-EURO (med)
AUC-EURO (high)
AUC-EURO (all)
Updated 1mo ago
Evaluation Results
Method
Method
Links
ECE (Smoothed)
AUC-EURO (low)
AUC-EURO (med)
AUC-EURO (high)
AUC-EURO (all)
NWKR
estimator=NWKR
2026.06
0.07
0.9
0.73
0.74
0.79
ACUTE
estimator=acute early act
2026.06
0.07
0.91
0.73
0.74
0.79
ACUTE
estimator=acute mid act
2026.06
0.07
0.91
0.76
0.78
0.82
ACUTE
estimator=acute late act
2026.06
0.07
0.91
0.77
0.8
0.83
ACUTE
estimator=acute pca10
2026.06
0.08
0.91
0.76
0.78
0.82
ACUTE
estimator=acute pca20
2026.06
0.08
0.91
0.76
0.77
0.81
ACUTE
estimator=acute cosine
2026.06
0.09
0.9
0.75
0.78
0.81
HRE
estimator=HRE
2026.06
0.11
0.87
0.72
0.71
0.77
Raw Conf
estimator=Raw Conf
2026.06
0.17
0.9
0.71
0.54
0.72
Feedback
Search any
task
Search any
task
