Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary safety classification on PGP Response
Loading...
75
F1 Score
gpt-oss-safeguard
23
36.5
50
63.5
May 1, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
gpt-oss-safeguard
Parameters=20B
2026.05
75
Qwen3Guard-Gen
Parameters=4B
2026.05
71
Qwen3Guard-Gen
Parameters=8B
2026.05
71
ML-GUARD
Parameters=1.5B
2026.05
70
ML-GUARD
Parameters=7B
2026.05
69
Qwen3Guard-Gen
Parameters=0.6B
2026.05
65
Llama-Guard-3
Parameters=8B
2026.05
63
Nemotron
Parameters=8B
2026.05
60
Omni-moderation
2026.05
60
PolyGuard-Qwen
2026.05
57
Llama-Guard-4
Parameters=12B
2026.05
49
DuoGuard
Parameters=1.5B
2026.05
45
Llama-Guard-3
Parameters=1B
2026.05
25
Feedback
Search any
task
Search any
task