Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Prompt Harmfulness Detection on HarmVideo
Loading...
95.5
F1 Score
GuardReasoner-Omni 4B
17.9576
38.0888
58.22
78.3512
Feb 3, 2026
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
GuardReasoner-Omni 4B
Model Category=VLM Gua...
2026.02
95.5
GuardReasoner-Omni 2B
Model Category=VLM Gua...
2026.02
93.32
HolmesVAU 2B
Model Category=VAD Model
2026.02
76.71
GuardReasoner-VL 7B
Model Category=VLM Gua...
2026.02
73.58
GuardReasoner-VL 3B
Model Category=VLM Gua...
2026.02
72.37
HolmesVAD 7B
Model Category=VAD Model
2026.02
40.12
LLaMA Guard 4 12B
Model Category=VLM Gua...
2026.02
20.94
Feedback
Search any
task
Search any
task