Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Insulting Behavior Detection on PKU-SafeRLHF
Loading...
78
Accuracy
Single agent
74.1
76.05
78
79.95
Dec 1, 2025
Accuracy
Precision
Recall
F1 Score
ROC-AUC
Pearson Rho
Pearson R
Updated 4d ago
Evaluation Results
Method
Method
Links
Accuracy
Precision
Recall
F1 Score
ROC-AUC
Pearson Rho
Pearson R
Single agent
Backbone=DeepSeek-R1
2025.12
78
71.9
92
80.7
77.8
0.541
0.551
Feedback
Search any
task
Search any
task