Hallucination Detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.939AUROC
12
Jun 2, 2026
5,351Inference Throughput (Samples/sec)
12
May 12, 2026
5,224Throughput (Samples/sec)
12
May 12, 2026
5,303Inference Throughput (Samples/sec)
12
May 12, 2026
0.73AUROC
12
Mar 24, 2026
0.86AuROC
12
Feb 26, 2026
98.8AuROC
12
Feb 26, 2026
65.9F1 Score
12
Mar 23, 2026
94.44Accuracy
12
Mar 23, 2026
61.9Precision
11
Jul 2, 2026
87.4F1 Score
11
Jun 2, 2026
84.3F1 Score
11
Jun 2, 2026
87.4F1 Score
11
Jun 2, 2026
88.2Precision (HP)
11
May 25, 2026
45.15F1 Score
11
Apr 7, 2026
0.794AUROC
11
Feb 26, 2026
0.877AUROC
11
Feb 26, 2026
41PRR
10
Jun 19, 2026
80.2PRR
10
Jun 19, 2026
87.5PRR
10
Jun 19, 2026
94AUC
10
Jun 2, 2026
0.963AUC
10
Jun 2, 2026
6.16Average Rank
10
May 28, 2026
75MF1 Score
10
May 25, 2026
85HF1
10
May 25, 2026