Calibration
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.85ECE
104
Mar 9, 2026
1.29Oracle ECE
100
May 12, 2026
0.083Brier Score
96
Feb 26, 2026
0.051Worst-group Brier score
66
Jun 4, 2026
0.042Worst-Group Brier Score
66
Jun 4, 2026
0.051Worst-group Brier Score
66
Jun 4, 2026
0.056Brier Score
58
Jun 11, 2026
1.54ECE
57
May 22, 2026
0.046ECE
55
Jun 4, 2026
0.84ECE
52
Feb 26, 2026
0MSE
40
Feb 26, 2026
0.085Brier Score
39
Jun 1, 2026
0.21ECE
33
Feb 26, 2026
2.132Gain
32
Jun 11, 2026
5.87ECE
31
Feb 26, 2026
0.067ECE
31
Feb 26, 2026
7.37ECE
27
Feb 26, 2026
0.264ECE
24
Feb 26, 2026
0.113ECE
24
Feb 26, 2026
0.28ECE
24
Feb 26, 2026
0.285ECE
24
Feb 26, 2026
1.43ECE (%)
24
Feb 26, 2026
0.89ECE (%)
24
Feb 26, 2026
0.01ECE
23
May 12, 2026
1.04ECE
22
Jun 5, 2026