Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Moderation on StrongReject
Loading...
100
F1 Score
YuFeng-XGuard
-3.376
23.462
50.3
77.138
May 6, 2026
F1 Score
Updated 26d ago
Evaluation Results
Method
Method
Links
F1 Score
YuFeng-XGuard
Size=8B, Task=s-cls
2026.05
100
GLiGuard Omni
Size=209M, Task=s-cls+IE
2026.05
99.7
WildGuard
Size=7B, Task=s-cls
2026.05
99.5
NemotronGuardV2
Size=8B, Task=s-cls
2026.05
99.5
GPT-OSS-SafeGuard
Size=20B, Task=s-cls
2026.05
99.2
Llama3Guard
Size=8B, Task=s-cls
2026.05
98.5
GLiGuard uni-enc
Size=147M, Task=s-cls+IE
2026.05
98.5
GLiGuard bi-enc
Size=145M, Task=s-cls+IE
2026.05
97.7
GLiNER2 Multi v1
Size=209M, Task=cls+IE
2026.05
95.7
Llama4Guard
Size=12B, Task=s-cls
2026.05
95.3
GLiClass Base v1.0
Size=150M, Task=cls
2026.05
91.3
ShieldGemma
Size=9B, Task=s-cls
2026.05
90
Longformer-harmful-ro
Size=149M, Task=s-cls
2026.05
81.7
PromptGuard 2*
Size=86M, Task=s-cls
2026.05
16.4
DeBERTa-v3-base-PI
Size=184M, Task=p-inj
2026.05
0.6
Feedback
Search any
task
Search any
task