Failure Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
3.4Average Rank
16
Apr 1, 2026
0.15E-AURC
16
Apr 1, 2026
12E-AURC
16
Apr 1, 2026
0.04E-AURC
16
Apr 1, 2026
0.13E-AURC
16
Apr 1, 2026
100TPR
15
Mar 13, 2026
100TPR
15
Mar 13, 2026
1TPR
15
Mar 13, 2026
98AUCPR
12
Jun 23, 2026
98AUCPR
12
Jun 23, 2026
100AUCPR (PR)
12
Jun 23, 2026
98AUCPR (PR)
12
Jun 23, 2026
91AUCPR
12
Jun 23, 2026
95AUCPR
12
Jun 23, 2026
71.3bACC
12
Jun 1, 2026
85.6Balanced Accuracy (bACC)
12
Jun 1, 2026
0.215Brier Score
11
Apr 23, 2026
0.15Brier Score
11
Apr 23, 2026
0.153Brier Score
11
Apr 23, 2026
0.096Brier Score
11
Apr 23, 2026
67Accuracy
11
Mar 17, 2026
431.12AURC
11
Feb 26, 2026
238.18AURC
11
Feb 26, 2026
90.64Accuracy
10
Feb 26, 2026
409.89AURC
10
Feb 26, 2026