Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
94.1AUCPR
18
Apr 8, 2026
43AUCPR
18
Apr 8, 2026
71.4AUROC
18
Apr 8, 2026
71.2AUROC
18
Apr 8, 2026
76.4AUROC
18
Apr 8, 2026
74.9AUROC
18
Apr 8, 2026
67.3AUROC
18
Apr 8, 2026
78.14AUC
18
Feb 26, 2026
83.9ROC
18
Feb 26, 2026
77.2Balanced Acc
18
Feb 26, 2026
89.7AUCPR
18
Apr 8, 2026
92.6Accuracy
18
Feb 26, 2026
91.99CNN Performance
17
Jun 9, 2026
96Accuracy
17
Apr 7, 2026
100Accuracy
17
Apr 7, 2026
99.5Accuracy
17
Apr 7, 2026
74.17Accuracy
17
Apr 7, 2026
92.2Accuracy
16
Jun 30, 2026
99.1Accuracy
16
Jun 30, 2026
98.3Accuracy
16
Jun 30, 2026
96.81HDR
16
Jun 30, 2026
94.33HDR
16
Jun 30, 2026
90.89PR AUC
16
Jun 18, 2026
92.16PR-AUC
16
Jun 18, 2026
0.899PR AUC
16
Jun 18, 2026