Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Refusal steering on N512 objective checks
Loading...
94.8
Target Success Rate
Residual Paving
74.312
79.631
84.95
90.269
May 18, 2026
Target Success Rate
Benign Keep Rate
Harm ASR Rate
Harm Refusal Rate
Updated 13d ago
Evaluation Results
Method
Method
Links
Target Success Rate
Benign Keep Rate
Harm ASR Rate
Harm Refusal Rate
Residual Paving
Model=Qwen2.5-1.5B, Ob...
2026.05
94.8
97.6
60.2
27.1
Residual Paving
Model=Qwen2.5-1.5B, Ob...
2026.05
93.2
97.6
12.2
80.6
Residual Paving
Model=Qwen2.5-7B, Obje...
2026.05
79.9
99.2
52
30.6
Residual Paving
Model=Qwen2.5-7B, Obje...
2026.05
75.1
99.2
4.1
74.5
Feedback
Search any
task
Search any
task