Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.265PRR
8
Jun 18, 2026
0.509PRR
8
Jun 18, 2026
0.477PRR
8
Jun 18, 2026
46.4PRR
8
Jun 18, 2026
0.37PRR
8
Jun 18, 2026
0Detection Delay (ARL0=50)
8
Jun 12, 2026
0False Alarm Rate
8
May 21, 2026
48.3F1 Score
8
May 7, 2026
44.23AUC-PR
8
May 7, 2026
0Hallucination Rate
8
Apr 23, 2026
1.23Hallucination Rate (%)
8
Apr 23, 2026
11.56Hallucination Rate (%)
8
Apr 23, 2026
2.03Hallucination Rate (%)
8
Apr 23, 2026
0.77AUROC
8
Feb 26, 2026
0.84AUROC
8
Feb 26, 2026
84AUROC
8
Feb 26, 2026
78.9TPR
8
Feb 26, 2026
92.5AUC-PR (Nonfactual)
8
Feb 26, 2026
0.987AUC
8
Feb 26, 2026
91.7AUC
8
Feb 26, 2026
0.744AUROC
7
Jun 12, 2026
83.41AUC
7
May 27, 2026
0.838AUC
7
May 11, 2026
93.8AUC
7
May 11, 2026
0.8AUROC
7
May 7, 2026