Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety-Utility Trade-off on IFEval and AdvBench
Loading...
84.62
SUT Score
CSULoRA
20.816
37.3805
53.945
70.5095
May 28, 2026
SUT Score
Updated 2d ago
Evaluation Results
Method
Method
Links
SUT Score
CSULoRA
Model=Gemma-3-4B-it
2026.05
84.62
SafeLoRA
Model=Gemma-3-4B-it
2026.05
81.62
CSULoRA
Model=Llama-3.2-3B-Ins...
2026.05
77.83
Base model
Model=Gemma-3-4B-it
2026.05
74.59
Base model
Model=Llama-3.2-3B-Ins...
2026.05
71.59
RESTA
Model=Llama-3.2-3B-Ins...
2026.05
63.02
RESTA
Model=Gemma-3-4B-it
2026.05
59.42
SaLoRA
Model=Llama-3.2-3B-Ins...
2026.05
48.48
SPLoRA
Model=Gemma-3-4B-it
2026.05
43.22
LoRA
Model=Gemma-3-4B-it
2026.05
43.18
AlignGuard
Model=Gemma-3-4B-it
2026.05
42.84
SPLoRA
Model=Llama-3.2-3B-Ins...
2026.05
38.73
SaLoRA
Model=Gemma-3-4B-it
2026.05
38.57
LoRA
Model=Llama-3.2-3B-Ins...
2026.05
32.7
SafeLoRA
Model=Llama-3.2-3B-Ins...
2026.05
30.64
AlignGuard
Model=Llama-3.2-3B-Ins...
2026.05
23.27
Feedback
Search any
task
Search any
task