Error detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81AUROC
57
Apr 23, 2026
98.1AuROC
48
Apr 28, 2026
99.38AuROC
46
Apr 28, 2026
90.99AUC
40
Feb 26, 2026
99.1AUC
40
Feb 26, 2026
89.52AUC
40
Feb 26, 2026
0.892AUC
40
Feb 26, 2026
1Precision
36
Feb 26, 2026
100Precision
36
Feb 26, 2026
100Precision
36
Feb 26, 2026
97Precision
36
Feb 26, 2026
92Precision
36
Feb 26, 2026
100Precision
36
Feb 26, 2026
0.93F1 Score
36
Feb 26, 2026
88F1 Score
36
Feb 26, 2026
95F1 Score
36
Feb 26, 2026
91F1 Score
36
Feb 26, 2026
0.94F1 Score
36
Feb 26, 2026
47FDR
36
May 26, 2026
99.92AuROC
29
Mar 18, 2026
75.1AUC
28
Jul 1, 2026
9.1Robo-VQA-E Score
20
Feb 26, 2026
0.716Recall
17
Jun 19, 2026
74.1F0.5 Score
16
Feb 26, 2026
96Recall
15
May 1, 2026