Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Hallucination Detection on TyDiQA-GP
Loading...
0.9404
AUC ROC
HaloScope
0.634432
0.713866
0.7933
0.872734
Dec 8, 2025
AUC ROC
Updated 4d ago
Evaluation Results
Method
Method
Links
AUC ROC
HaloScope
Model=LLaMA-2-7B
2025.12
0.9404
HALLUSHIFT++
Model=LLaMA-2-7B
2025.12
0.8966
HALLUSHIFT
Model=LLaMA-2-7B
2025.12
0.8761
HALLUSHIFT++
Model=OPT-6.7B
2025.12
0.8758
HALLUSHIFT
Model=OPT-6.7B
2025.12
0.8511
HaloScope
Model=OPT-6.7B
2025.12
0.8098
CCS*
Model=LLaMA-2-7B
2025.12
0.8038
CCS*
Model=OPT-6.7B
2025.12
0.6462
Feedback
Search any
task
Search any
task