Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on WildGuard (Safe)
Loading...
30.7
Refusal Rate
Target feature
2.516
9.833
17.15
24.467
Jun 25, 2026
Refusal Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Refusal Rate
Target feature
Model=Qwen3-4B-it
2026.06
30.7
Target feature
Model=Qwen3-1.7B-it
2026.06
18.3
Random feature
Model=Qwen3-1.7B-it
2026.06
5.3
No Steering
Model=Qwen3-4B-it
2026.06
4.4
No Steering
Model=Qwen3-1.7B-it
2026.06
4.3
Random feature
Model=Qwen3-4B-it
2026.06
3.6
Feedback
Search any
task
Search any
task