Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Response-level Hallucination Detection on RAGognize
Loading...
94.91
AUROC
RAGognizer
60.1428
69.1689
78.195
87.2211
Apr 17, 2026
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
RAGognizer
Detector category=Whit...
2026.04
94.91
LookbackLens
Detector category=Whit...
2026.04
94.36
MiniCheck-7B
Detector category=Blac...
2026.04
83.48
HallucinationProbes
Detector category=Whit...
2026.04
83.25
HDM-2-3B
Detector category=Blac...
2026.04
75.41
SelfCheckGPT (NLI)
Detector category=Blac...
2026.04
74.22
HaloScope
Detector category=Whit...
2026.04
71.38
DeBERTa-v3 (Ent.)
Detector category=Blac...
2026.04
68.21
LettuceDetect-L
Detector category=Blac...
2026.04
65.75
INSIDE (EigenScore)
Detector category=Whit...
2026.04
64.49
DeBERTa-v3 (Con.)
Detector category=Blac...
2026.04
64.31
HHEM-2.1-Open
Detector category=Blac...
2026.04
61.49
Semantic Entropy
Detector category=Whit...
2026.04
61.48
Feedback
Search any
task
Search any
task