Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
85.5AUC
40
May 15, 2026
91.74AUROC
39
May 27, 2026
89ROC-AUC
39
Apr 20, 2026
0.976AuROC
38
Jun 2, 2026
78.91AUC
37
May 21, 2026
79.94AUC
37
May 21, 2026
78.65AUC
37
May 21, 2026
99.05HaluEval Score
36
Jun 30, 2026
79.35macF1
36
May 6, 2026
88F1 Score
36
Apr 8, 2026
99.13A-PR
34
Mar 9, 2026
0.933AUROC
33
Apr 14, 2026
0.789F1 Score
33
Jun 8, 2026
81.59AUC
33
Feb 26, 2026
75.37Accuracy
32
Jun 19, 2026
73.07Accuracy
32
Jun 19, 2026
78.82Accuracy
32
Jun 19, 2026
53.2PRR
32
Jun 18, 2026
32.1PRR
32
Jun 18, 2026
49PRR
32
Jun 18, 2026
0.935AUROC
32
Mar 6, 2026
98.4Accuracy (4 Refs)
32
Feb 26, 2026
87.08AUROC
31
Jun 23, 2026
0.782AUROC
31
Feb 26, 2026
64.5Accuracy
30
Mar 5, 2026