Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary Safety Classification on PGP Query
Loading...
89
F1 Score
PolyGuard-Qwen
42.2
54.35
66.5
78.65
May 1, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
PolyGuard-Qwen
2026.05
89
ML-GUARD
Parameters=7B
2026.05
89
gpt-oss-safeguard
Parameters=20B
2026.05
86
Qwen3Guard-Gen
Parameters=4B
2026.05
85
Qwen3Guard-Gen
Parameters=8B
2026.05
85
Qwen3Guard-Gen
Parameters=0.6B
2026.05
83
ML-GUARD
Parameters=1.5B
2026.05
83
Nemotron
Parameters=8B
2026.05
80
Llama-Guard-3
Parameters=8B
2026.05
73
DuoGuard
Parameters=1.5B
2026.05
72
Llama-Guard-4
Parameters=12B
2026.05
66
Omni-moderation
2026.05
62
Llama-Guard-3
Parameters=1B
2026.05
44
Feedback
Search any
task
Search any
task