Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt classification on OpenAIM
Loading...
81.1
F1
Qwen3Guard-Gen
65.188
69.319
73.45
77.581
Jan 22, 2026
F1
Updated 4d ago
Evaluation Results
Method
Method
Links
F1
Qwen3Guard-Gen
Model Size=8B, Evaluat...
2026.01
81.1
Qwen3Guard-Gen
Model Size=4B, Evaluat...
2026.01
80.7
GPT-OSS-SafeGuard
Model Size=20B
2026.01
80.5
ShieldGemma
Model Size=9B
2026.01
79.6
Llama3Guard
Model Size=8B
2026.01
79
Qwen3Guard-Gen
Model Size=0.6B, Evalu...
2026.01
77.5
NemotronGuardV2
Model Size=8B
2026.01
75.7
NemotronReasoning
Model Size=4B
2026.01
75.6
PolyGuard
Model Size=7B
2026.01
75.5
Llama4Guard
Model Size=12B
2026.01
73.6
YuFeng-XGuard
Model Size=0.6B
2026.01
72.7
WildGuard
Model Size=7B
2026.01
72.3
YuFeng-XGuard
Model Size=8B
2026.01
72.3
Qwen3Guard-Gen
Model Size=4B, Evaluat...
2026.01
68.1
Qwen3Guard-Gen
Model Size=8B, Evaluat...
2026.01
68.1
Qwen3Guard-Gen
Model Size=0.6B, Evalu...
2026.01
65.8
Feedback
Search any
task
Search any
task