Span-level Hallucination Detection
Benchmarks
DatasetSOTA methodMetricTrendResultsLast updated
86.6F1 Score
12
Jul 2, 2026
80.56F1 Score
12
Feb 26, 2026
76.63F1 Score
12
Feb 26, 2026
81.7F1 Score
4
Jul 2, 2026
60.2F1 Score
4
Jul 2, 2026
57.4F1 Score
3
Jul 2, 2026
73.2F1 Score
3
Jul 2, 2026
68.9F1 Score
3
Jul 2, 2026