Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Harmfulness Detection on XD-Violence
Loading...
96.82
F1 Score
GuardReasoner-Omni 2B
14.6288
35.9669
57.305
78.6431
Feb 3, 2026
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
GuardReasoner-Omni 2B
Model Category=VLM Gua...
2026.02
96.82
HolmesVAU 2B
Model Category=VAD Model
2026.02
95.92
GuardReasoner-Omni 4B
Model Category=VLM Gua...
2026.02
95.71
GuardReasoner-VL 7B
Model Category=VLM Gua...
2026.02
85.79
HolmesVAD 7B
Model Category=VAD Model
2026.02
83.77
GuardReasoner-VL 3B
Model Category=VLM Gua...
2026.02
83.74
LLaMA Guard 4 12B
Model Category=VLM Gua...
2026.02
17.79
Feedback
Search any
task
Search any
task