Uncertainty Estimation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.90895% PI
6
Feb 26, 2026
98.195% PI Coverage
6
Feb 26, 2026
0.634Brier Score
5
Mar 13, 2026
4.113NLL
5
Feb 26, 2026
2.727NLL
5
Feb 26, 2026
2.815NLL
5
Feb 26, 2026
3.866NLL
5
Feb 26, 2026
2.152NLL
5
Feb 26, 2026
2.754NLL
5
Feb 26, 2026
1.81NLL
5
Feb 26, 2026
1.996NLL
5
Feb 26, 2026
4.196NLL
5
Feb 26, 2026
3.805NLL
5
Feb 26, 2026
3.598NLL
5
Feb 26, 2026
3.703NLL
5
Feb 26, 2026
3.651NLL (All)
5
Feb 26, 2026
99.5r-Coverage
4
Jun 30, 2026
0.001ECE
4
May 12, 2026
0.12AUSE
4
Apr 14, 2026
0.26AUSE
4
Apr 14, 2026
0.009NLL
4
Mar 13, 2026
5.4ECE
4
Feb 26, 2026
0.76Delta 1
3
May 25, 2026
2.86AUPRC Difference (pp)
3
Mar 25, 2026
1.37AUPRC Difference
3
Mar 25, 2026