Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful prompt detection on TChat
Loading...
76.51
F1 Score
MLPM
53.214
59.262
65.31
71.358
Feb 22, 2025
F1 Score
Updated 1d ago
Evaluation Results
Method
Method
Links
F1 Score
MLPM
Backbone=OLMo2-7B-Inst...
2025.02
76.51
Aegis-Guard-D
Methodology=Guard Model
2025.02
75.61
GraniteGuardian-3-1-8B
Methodology=Guard Model
2025.02
73.25
Abdelnabi et al.
Backbone=OLMo2-7B-Inst...
2025.02
72.53
WildGuard
Methodology=Guard Model
2025.02
70.14
MLPM
Backbone=Llama-8B-Inst...
2025.02
69.17
Ayub & Majumdar
Backbone=Qwen3-8B-Inst...
2025.02
68.9
ShieldGemma-9B
Methodology=Guard Model
2025.02
68.13
MLPM
Backbone=Mistral-7B-In...
2025.02
66.33
Ayub & Majumdar
Backbone=OLMo2-7B-Inst...
2025.02
65.63
MLPM
Backbone=Qwen3-8B-Inst...
2025.02
64.4
Ayub & Majumdar
Backbone=Mistral-7B-In...
2025.02
63.44
Abdelnabi et al.
Backbone=Qwen3-8B-Inst...
2025.02
60.94
Abdelnabi et al.
Backbone=Llama-8B-Inst...
2025.02
59.59
Abdelnabi et al.
Backbone=Mistral-7B-In...
2025.02
57.63
Ayub & Majumdar
Backbone=Llama-8B-Inst...
2025.02
55.62
LlamaGuard3
Methodology=Guard Model
2025.02
54.11
Feedback
Search any
task
Search any
task