Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

HaloQuest

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hallucination DetectionHaloQuest
ROC0.834
27
Hallucination EvaluationHaloQuest
Score S80.8
19
Hallucination ClassificationHaloQuest
Balanced Accuracy60
3
Showing 3 of 3 rows