Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Self-Harm Content Classification on Internal Set
Loading...
84
Precision
GPT-4o
54.88
62.44
70
77.56
Dec 19, 2025
Precision
Recall
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Precision
Recall
F1 Score
GPT-4o
2025.12
84
93
88
CoPE-A
Model Size=9B
2025.12
83
93
88
ShieldGemma
Model Size=9B
2025.12
69
89
78
LlamaGuard3
Model Size=8B
2025.12
65
84
73
Llama-3.1
Model Size=8B
2025.12
56
96
70
Feedback
Search any
task
Search any
task