Error detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
44.5Accuracy
15
Feb 26, 2026
0.403Accuracy
15
Feb 26, 2026
45.3Accuracy
15
Feb 26, 2026
61.8Accuracy (Mean)
14
Feb 26, 2026
6.4EC (Detection@1)
13
Feb 26, 2026
55.4Recall
12
Jun 19, 2026
11.8Overall EDA
12
Feb 26, 2026
97.8F1 Score
11
Feb 26, 2026
0.453F1 Score
10
Feb 26, 2026
80.9F1 Score
10
Feb 26, 2026
0.872F1 Score
10
Feb 26, 2026
79F1 Score
10
Feb 26, 2026
88.1F1 Score
10
Feb 26, 2026
37.72Precision
9
Feb 26, 2026
25.14P
9
Feb 26, 2026
70.64AuROC
7
Feb 26, 2026
77.34AuROC
7
Feb 26, 2026
0.761AuROC
7
Feb 26, 2026
83.51AuROC
7
Feb 26, 2026
86.19AuROC
7
Feb 26, 2026
0.953AUROC
6
May 12, 2026
52.9F1 Score
6
Mar 25, 2026
45.8F1 Score
6
Mar 25, 2026
100Precision
6
Feb 26, 2026
0.934Precision
6
Feb 26, 2026