Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful prompt detection on WGMix
Loading...
88.52
F1 Score
MLPM
57.6944
65.6972
73.7
81.7028
Feb 22, 2025
F1 Score
Updated 1d ago
Evaluation Results
Method
Method
Links
F1 Score
MLPM
Backbone=OLMo2-7B-Inst...
2025.02
88.52
Ayub & Majumdar
Backbone=OLMo2-7B-Inst...
2025.02
88.09
MLPM
Backbone=Llama-8B-Inst...
2025.02
88.04
WildGuard
Methodology=Guard Model
2025.02
88.04
MLPM
Backbone=Mistral-7B-In...
2025.02
87.63
Abdelnabi et al.
Backbone=Llama-8B-Inst...
2025.02
86.27
MLPM
Backbone=Qwen3-8B-Inst...
2025.02
86.21
Abdelnabi et al.
Backbone=OLMo2-7B-Inst...
2025.02
86.2
Abdelnabi et al.
Backbone=Mistral-7B-In...
2025.02
85.73
Abdelnabi et al.
Backbone=Qwen3-8B-Inst...
2025.02
85.18
GraniteGuardian-3-1-8B
Methodology=Guard Model
2025.02
84.57
Ayub & Majumdar
Backbone=Mistral-7B-In...
2025.02
83.31
Ayub & Majumdar
Backbone=Llama-8B-Inst...
2025.02
80.91
Ayub & Majumdar
Backbone=Qwen3-8B-Inst...
2025.02
80.64
LlamaGuard3
Methodology=Guard Model
2025.02
76.76
Aegis-Guard-D
Methodology=Guard Model
2025.02
72.09
ShieldGemma-9B
Methodology=Guard Model
2025.02
58.88
Feedback
Search any
task
Search any
task