Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
LLM Safety Defense on MTSA-R3
Loading...
23.5
ASR
MTSA-T3
21.46
35.23
49
62.77
May 22, 2025
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
MTSA-T3
Target Model=Zephyr-7B...
2025.05
23.5
MTSA-T3
Target Model=Llama2-7B...
2025.05
24
MTSA-T2
Target Model=Llama2-7B...
2025.05
27.5
MTSA-T2
Target Model=Zephyr-7B...
2025.05
30.5
MTSA-T1
Target Model=Llama2-7B...
2025.05
32
MART-T3
Target Model=Llama2-7B...
2025.05
36.5
MART-T2
Target Model=Llama2-7B...
2025.05
37.5
HARM-T3
Target Model=Llama2-7B...
2025.05
39
HARM-T2
Target Model=Llama2-7B...
2025.05
41
MART-T1
Target Model=Llama2-7B...
2025.05
41
MTSA-T1
Target Model=Zephyr-7B...
2025.05
42.5
HARM-T1
Target Model=Llama2-7B...
2025.05
43.5
MART-T3
Target Model=Zephyr-7B...
2025.05
48.5
Baseline
Target Model=Llama2-7B...
2025.05
50.5
MART-T2
Target Model=Zephyr-7B...
2025.05
51
HARM-T3
Target Model=Zephyr-7B...
2025.05
52.5
HARM-T2
Target Model=Zephyr-7B...
2025.05
58.5
MART-T1
Target Model=Zephyr-7B...
2025.05
61.5
HARM-T1
Target Model=Zephyr-7B...
2025.05
65
Baseline
Target Model=Zephyr-7B...
2025.05
74.5
Feedback
Search any
task
Search any
task