Hallucination Prediction
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
64.87Accuracy
20
Mar 11, 2026
80.91Accuracy
20
Mar 11, 2026
75.51AUROC
20
Mar 11, 2026
77.89AUROC
20
Mar 11, 2026
65Accuracy (Time)
16
Feb 27, 2026
75.51AUROC
10
Mar 11, 2026
83.39AUROC
10
Mar 11, 2026
69.24Accuracy
10
Mar 11, 2026
82.29Accuracy
10
Mar 11, 2026
79.41AUROC
10
Mar 11, 2026
79.41AUROC
10
Mar 11, 2026
70.04AUROC
10
Mar 11, 2026
85.42AUROC
10
Mar 11, 2026
61.22Flare
7
Jun 2, 2026
65Accuracy
6
Feb 27, 2026
29.4Accuracy (entity)
4
Feb 27, 2026