Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful Refusal on HarmBench vani harm
Loading...
1
ASR
Qwen2.5-14B-IT + SELF-REDTEAM
-1.948
17.951
37.85
57.749
Jun 9, 2025
ASR
Updated 18d ago
Evaluation Results
Method
Method
Links
ASR
Qwen2.5-14B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
1
Qwen2.5-3B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
2
Qwen2.5-7B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
4.4
Llama3.1-8B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
4.4
Llama3.1-8B-IT-AB + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
4.8
Qwen2.5-14B-IT
Training=Instruction-t...
2025.06
5.6
Qwen2.5-3B-IT
Training=Instruction-t...
2025.06
7.2
Qwen2.5-7B-IT
Training=Instruction-t...
2025.06
16.3
Llama3.1-8B-IT
Training=Instruction-t...
2025.06
16.3
Llama3.1-8B-IT-AB
Training=Instruction-t...
2025.06
74.7
Feedback
Search any
task
Search any
task