Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.4F1 Score
6
Mar 23, 2026
91.7F1 Score
6
Mar 23, 2026
91Detection Rate
6
Mar 12, 2026
98.4Accuracy
6
Feb 26, 2026
98.2Accuracy
6
Feb 26, 2026
76.8Pairwise Accuracy
6
Feb 26, 2026
84.21Precision
6
Feb 26, 2026
80.55Precision
6
Feb 26, 2026
41.9Accuracy
6
Feb 26, 2026
26.3Accuracy
6
Feb 26, 2026
50Accuracy
6
Feb 26, 2026
83.9Example-F1
5
Jul 2, 2026
1.68Average Entropy
5
Jun 9, 2026
71.8Detection Accuracy
5
May 19, 2026
245Support (Total Samples)
5
May 13, 2026
99.4AUROC
5
May 8, 2026
0.61AUROC (phi C75)
5
May 7, 2026
2.1P95 Latency (s)
5
Apr 28, 2026
99.3Accuracy
5
Apr 21, 2026
84.7F1 Score
5
Apr 16, 2026
0.858AUC
5
Apr 9, 2026
84.9F1-Score
5
Apr 9, 2026
94.8AUROC
5
Apr 8, 2026
0.694AvgWD
5
Mar 25, 2026
0.742AvgWD
5
Mar 25, 2026