Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary safety classification on XSafety
Loading...
48
F1 Score
ML-GUARD
18.88
26.44
34
41.56
May 1, 2026
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
ML-GUARD
Parameters=1.5B
2026.05
48
Llama-Guard-3
Parameters=1B
2026.05
44
PolyGuard-Qwen
2026.05
44
ML-GUARD
Parameters=7B
2026.05
44
Nemotron
Parameters=8B
2026.05
40
DuoGuard
Parameters=1.5B
2026.05
33
gpt-oss-safeguard
Parameters=20B
2026.05
33
Qwen3Guard-Gen
Parameters=0.6B
2026.05
28
Qwen3Guard-Gen
Parameters=4B
2026.05
27
Qwen3Guard-Gen
Parameters=8B
2026.05
27
Llama-Guard-3
Parameters=8B
2026.05
23
Llama-Guard-4
Parameters=12B
2026.05
22
Omni-moderation
2026.05
20
Feedback
Search any
task
Search any
task