Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful Refusal on HarmBench Standard
Loading...
98.2
Refusal Rate (String Match)
LlamaGuard prompt-filter
6.68
30.44
54.2
77.96
Jun 10, 2026
Refusal Rate (String Match)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Refusal Rate (String Match)
LlamaGuard prompt-filter
Draft Model=Llama-3.1-8B
2026.06
98.2
LlamaGuard response-filter
Draft Model=Llama-3.1-8B
2026.06
98.2
Hard prefix
Draft Model=Llama-3.1-...
2026.06
82
ALIGNBEAM
Draft Model=Llama-3.1-...
2026.06
79.6
Base draft
Draft Model=Llama-3.1-8B
2026.06
15
Safety prompt
Draft Model=Llama-3.1-8B
2026.06
10.2
Feedback
Search any
task
Search any
task