Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

HallBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vision-Language Hallucination EvaluationHallBench
Accuracy64.2
15
Hallucination EvaluationHallBench
Accuracy60.8
10
Hallucination EvaluationHallBench avg
Hallucination Score58.1
7
Showing 3 of 3 rows