Uncertainty Quantification
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.813V-ID
3
Jun 1, 2026
-355.46Avg Log-Likelihood
3
Apr 15, 2026
-222.686Average Log-Likelihood
3
Apr 15, 2026
-7.81Average Log-Likelihood
3
Apr 15, 2026
-3.05Average Log-Likelihood
3
Apr 15, 2026
8.49AUSE-MSE
3
Apr 6, 2026
8AUSE-MSE
3
Apr 6, 2026
7.22AUSE-MSE
3
Apr 6, 2026
95.14Total C.R.
3
Mar 13, 2026
0.342ECE
3
Mar 6, 2026
0.534Expected Calibration Error (ECE)
3
Mar 6, 2026
29.46Log Likelihood (LL)
2
May 19, 2026
32LL
2
May 19, 2026
0.606Base Error
1
Jun 23, 2026
0.311Base Error
1
Jun 23, 2026
0.335Base Error Rate
1
Jun 23, 2026
0.395Base Error
1
Jun 23, 2026
0.054Base Error
1
Jun 23, 2026
0.27Base Error
1
Jun 23, 2026
—
—Primary metric
0
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026
—
—Primary metric
0
Feb 26, 2026