Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Harmful Refusal on StrongREJECT vani harm
Loading...
99.5
RTA Rate (vani harm)
Qwen2.5-14B-IT + SELF-REDTEAM
8.604
32.202
55.8
79.398
Jun 9, 2025
RTA Rate (vani harm)
Updated 18d ago
Evaluation Results
Method
Method
Links
RTA Rate (vani harm)
Qwen2.5-14B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
99.5
Qwen2.5-7B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
97.9
Qwen2.5-3B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
97.1
Qwen2.5-14B-IT
Training=Instruction-t...
2025.06
97.1
Llama3.1-8B-IT
Training=Instruction-t...
2025.06
97.1
Llama3.1-8B-IT + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
95.8
Qwen2.5-3B-IT
Training=Instruction-t...
2025.06
92
Qwen2.5-7B-IT
Training=Instruction-t...
2025.06
92
Llama3.1-8B-IT-AB + SELF-REDTEAM
Training=SELF-REDTEAM...
2025.06
91.2
Llama3.1-8B-IT-AB
Training=Instruction-t...
2025.06
12.1
Feedback
Search any
task
Search any
task