Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Detection on RAGTruth Span-level, leakage-clean protocol
Loading...
0.702
AUC
GASP+base (trained)
0.51584
0.56417
0.6125
0.66083
Jul 5, 2026
AUC
Updated 18d ago
Evaluation Results
Method
Method
Links
AUC
GASP+base (trained)
Scorer=SmolLM2-1.7B, P...
2026.07
0.702
GASP-threshold (default)
Scorer=SmolLM2-1.7B, P...
2026.07
0.681
GASP+base (trained)
Scorer=Qwen2.5-1.5B, P...
2026.07
0.678
GASP+base (trained)
Scorer=Qwen2.5-0.5B, P...
2026.07
0.676
GASP-threshold (default)
Scorer=Qwen2.5-1.5B, P...
2026.07
0.673
GASP-threshold (default)
Scorer=Qwen2.5-0.5B, P...
2026.07
0.672
GASP-trained
Scorer=SmolLM2-1.7B, P...
2026.07
0.657
GASP-trained
Scorer=Qwen2.5-1.5B, P...
2026.07
0.645
GASP-trained
Scorer=Qwen2.5-0.5B, P...
2026.07
0.635
Perplexity
Scorer=SmolLM2-1.7B, P...
2026.07
0.615
Perplexity
Scorer=Qwen2.5-1.5B, P...
2026.07
0.565
Length
Scorer=Qwen2.5-1.5B, P...
2026.07
0.548
Length
Scorer=Qwen2.5-0.5B, P...
2026.07
0.547
Perplexity
Scorer=Qwen2.5-0.5B, P...
2026.07
0.536
Length
Scorer=SmolLM2-1.7B, P...
2026.07
0.523
Feedback
Search any
task
Search any
task