Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary Safety Classification on OpenAI Moderation (oai_safety)
Loading...
76.76
Macro F1
Nemotron Safety Guard v3
59.184
63.747
68.31
72.873
May 28, 2026
Macro F1
Updated 5d ago
Evaluation Results
Method
Method
Links
Macro F1
Nemotron Safety Guard v3
Architecture=Decoder-b...
2026.05
76.76
PolyGuard-Qwen
Architecture=Decoder-b...
2026.05
72.77
WildGuard (vLLM)
Architecture=Decoder-b...
2026.05
71.72
PolyGuard-Qwen-Smol
Architecture=Decoder-b...
2026.05
67.91
Gliner-Guard-Omni
2026.05
67.85
Qwen3Guard-Gen-8B
Architecture=Decoder-b...
2026.05
67.06
Opir-edge-multilang
Architecture=Encoder-b...
2026.05
63.97
GLiGuard-LLMGuardrails-300M
Architecture=Encoder-b...
2026.05
63.96
Opir-multitask-multilang
Architecture=Encoder-b...
2026.05
61.26
Opir-multitask-large
Architecture=Encoder-b...
2026.05
60.75
Opir-edge
Architecture=Encoder-b...
2026.05
59.86
Feedback
Search any
task
Search any
task