Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary safety classification on CSRT
Loading...
81
F1 Score
PolyGuard-Qwen
40.44
50.97
61.5
72.03
May 1, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
PolyGuard-Qwen
2026.05
81
ML-GUARD
Parameters=1.5B
2026.05
81
ML-GUARD
Parameters=7B
2026.05
81
Nemotron
Parameters=8B
2026.05
79
Llama-Guard-4
Parameters=12B
2026.05
63
gpt-oss-safeguard
Parameters=20B
2026.05
63
Llama-Guard-3
Parameters=8B
2026.05
61
Omni-moderation
2026.05
58
Qwen3Guard-Gen
Parameters=4B
2026.05
56
Qwen3Guard-Gen
Parameters=8B
2026.05
56
Qwen3Guard-Gen
Parameters=0.6B
2026.05
54
DuoGuard
Parameters=1.5B
2026.05
42
Llama-Guard-3
Parameters=1B
2026.05
42
Feedback
Search any
task
Search any
task