Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Red-teaming Safety Evaluation on Advbench
Loading...
68
HPR
Meta-Llama-3.1-8B (Unaligned)
19.12
31.81
44.5
57.19
May 30, 2025
HPR
HS
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
HPR
HS
ASR
Meta-Llama-3.1-8B (Unaligned)
base_model=Meta-Llama-...
2025.05
68
3.23
44
Meta-Llama-3.1-8B (HH_RLHF-aligned)
base_model=Meta-Llama-...
2025.05
67
3.49
46
Meta-Llama-3.1-8B (WILDCHAT-aligned)
base_model=Meta-Llama-...
2025.05
38
3.07
29
Meta-Llama-3.1-8B (SAFE_RLHF-aligned)
base_model=Meta-Llama-...
2025.05
34
2.6
23
Meta-Llama-3.1-8B (AART-aligned)
base_model=Meta-Llama-...
2025.05
29
2.22
15
Meta-Llama-3.1-8B (ATTAQ-aligned)
base_model=Meta-Llama-...
2025.05
26
2.5
19
Meta-Llama-3.1-8B (WILDBREAK-aligned)
base_model=Meta-Llama-...
2025.05
24
2.31
14
Meta-Llama-3.1-8B (TRIDENT-EDGE-aligned)
base_model=Meta-Llama-...
2025.05
21
1.86
9
Feedback
Search any
task
Search any
task