Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination Detection on HaluEval
Loading...
0.8021
AUROC
ICR Probe
0.663572
0.699536
0.7355
0.771464
Jul 22, 2025
AUROC
Updated 4d ago
Evaluation Results
Method
Method
Links
AUROC
ICR Probe
Model=Qwen2.5-14B
2025.07
0.8021
ICR Probe
Model=Qwen2.5-3B
2025.07
0.7917
SAPLMA
Model=Qwen2.5-14B
2025.07
0.772
SAPLMA
Model=Qwen2.5-3B
2025.07
0.7538
SEP
Model=Qwen2.5-14B
2025.07
0.7016
SEP
Model=Qwen2.5-3B
2025.07
0.6689
Feedback
Search any
task
Search any
task