Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
88.9AUC
24
Apr 6, 2026
0.874AUC
24
Apr 6, 2026
66.04Accuracy
24
Mar 17, 2026
81.7Accuracy
24
Mar 17, 2026
87.2Accuracy
24
Mar 17, 2026
0.644Accuracy
24
Mar 17, 2026
0.787AUROC
24
Feb 26, 2026
82F1 Score
22
Jun 2, 2026
69.3Accuracy (Entire)
22
Apr 15, 2026
67.1HRP
22
Mar 20, 2026
68.9HRP
22
Mar 20, 2026
51HRP
22
Mar 20, 2026
70.5HRP
22
Mar 20, 2026
84.88Accuracy
22
Feb 26, 2026
92.7AUROC
21
Jun 2, 2026
75.76Accuracy
21
Feb 26, 2026
83.33Acc
21
Feb 26, 2026
77.78Acc
21
Feb 26, 2026
75.76Accuracy
21
Feb 26, 2026
77.51AUROC
20
May 15, 2026
67.05Hallusion Score
20
Jun 1, 2026
92AUROC
20
May 8, 2026
98AUROC
20
May 8, 2026
0.98AUROC
20
May 8, 2026
82AUC
20
Mar 24, 2026