Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Detection on RAGBench
Loading...
67.9
AUC
GASP+base (trained)
56.876
59.738
62.6
65.462
Jul 5, 2026
AUC
Updated 18d ago
Evaluation Results
Method
Method
Links
AUC
GASP+base (trained)
Scorer=Qwen-1.5B
2026.07
67.9
GASP+base (trained)
Scorer=Qwen-0.5B
2026.07
66.8
Perplexity
Scorer=Qwen-1.5B
2026.07
61.9
Perplexity
Scorer=Qwen-0.5B
2026.07
61.3
GASP-trained
Scorer=Qwen-1.5B
2026.07
59.6
GASP-trained
Scorer=Qwen-0.5B
2026.07
59.5
GASP-threshold
Scorer=Qwen-0.5B
2026.07
57.6
GASP-threshold
Scorer=Qwen-1.5B
2026.07
57.3
Feedback
Search any
task
Search any
task