Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on GuardSet-X (test)
Loading...
96.85
Accuracy
LPG-4B
59.254
69.0145
78.775
88.5355
May 17, 2026
Accuracy
F1 Score
Updated 15d ago
Evaluation Results
Method
Method
Links
Accuracy
F1 Score
LPG-4B
Latency (ms)=625
2026.05
96.85
96.88
DynaGuard-8B
Latency (ms)=1501
2026.05
81.65
79.73
DynaGuard-4B
Latency (ms)=222
2026.05
81
79.33
Qwen3-4B-Thinking
Latency (ms)=9747
2026.05
77.25
74.07
Qwen3-4B
Latency (ms)=249
2026.05
75.6
71.86
GuardReasoner-8B
Latency (ms)=4072
2026.05
63.16
22.48
GuardReasoner-3B
Latency (ms)=3537
2026.05
60.7
38.3
Feedback
Search any
task
Search any
task