Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Safe Completion on SEval Response 2.0
Loading...
80.8
F1 Score
YuFeng-XGuard-8B
5.088
24.744
44.4
64.056
Jan 22, 2026
F1 Score
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 Score
YuFeng-XGuard-8B
2026.01
80.8
YuFeng-XGuard-0.6B
2026.01
78.1
GPT-OSS-SafeGuard-20B
2026.01
75.5
Qwen3Guard-Gen-4B
Evaluation Strategy=st...
2026.01
66.5
Qwen3Guard-Gen-8B
Evaluation Strategy=st...
2026.01
66.3
Qwen3Guard-Gen-0.6B
Evaluation Strategy=st...
2026.01
59.7
PolyGuard-7B
2026.01
57.1
Qwen3Guard-Gen-0.6B
Evaluation Strategy=loose
2026.01
43
NemotronReasoning-4B
2026.01
41.2
Llama3Guard-8B
2026.01
40.8
Qwen3Guard-Gen-4B
Evaluation Strategy=loose
2026.01
39.9
Qwen3Guard-Gen-8B
Evaluation Strategy=loose
2026.01
38.1
Llama4Guard-12B
2026.01
34.4
NemotronGuardV2-8B
2026.01
33
WildGuard-7B
2026.01
25.7
ShieldGemma-9B
2026.01
8
Feedback
Search any
task
Search any
task