Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.98AUROC
625
Jun 24, 2026
0.928AUROC
294
Jun 23, 2026
98.3AUC-ROC
255
Jun 12, 2026
0.889AUC
199
Jun 23, 2026
0.942AUC (ROC)
182
Jun 19, 2026
98.55AUC-ROC
176
Jun 2, 2026
0.93AUROC
141
Jun 19, 2026
1AUROC
135
Jun 19, 2026
90.07AUROC
134
Jun 12, 2026
90.37AUROC
131
Jun 19, 2026
0.89AUROC
127
Jun 23, 2026
89.5AUC-ROC
112
May 7, 2026
0.858Mean AUROC
107
May 27, 2026
85.1AUROC
107
Apr 3, 2026
81.13AUROC
104
May 28, 2026
0.91AUROC
99
May 11, 2026
96.18AUC
97
Jun 2, 2026
0.885AUROC
91
Jun 2, 2026
95.2AUC ROC
91
May 7, 2026
0.96AUC
84
Feb 26, 2026
0.884AUC
84
Feb 26, 2026
64.8AUROC
80
Jun 12, 2026
0.854AUROC
79
Jun 23, 2026
97AUROC
75
May 19, 2026
81.57Mean AUROC
72
Feb 26, 2026