Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
71.9AUC
20
Mar 24, 2026
49.3HRP
20
Mar 20, 2026
47.7HRP
20
Mar 20, 2026
53.1HRP
20
Mar 20, 2026
68.8Accuracy
20
Jul 7, 2026
89.01AUPRC
20
Mar 9, 2026
67.08AUPRC
20
Mar 9, 2026
80.62AUROC
20
Feb 26, 2026
83.92Recall
19
Feb 26, 2026
0.974Recall
19
Feb 26, 2026
87.28Recall
19
Feb 26, 2026
78.6Recall
19
Feb 26, 2026
80.68Recall
19
Feb 26, 2026
0.833Recall
19
Feb 26, 2026
96.5AUC ROC
19
Feb 26, 2026
91.7AUC ROC
19
Feb 26, 2026
97.77F1-Score
18
Jul 7, 2026
87.8F1-Score
18
Jul 7, 2026
88.34F1-Score
18
Jul 7, 2026
0.571PRR
18
Jun 19, 2026
98.86Avg-M Score
18
May 22, 2026
89.66Hallucination Rate (%)
18
Apr 23, 2026
91.1AUCPR
18
Apr 8, 2026
93.4AUCPR
18
Apr 8, 2026
95.3AUCPR
18
Apr 8, 2026