Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Best-of-N Alignment on HH-RLHF (test)
Loading...
98
Percent batches with BWR > 0.50
AdaBoN
52.24
64.12
76
87.88
May 17, 2025
Percent batches with BWR > 0.50
Updated 1mo ago
Evaluation Results
Method
Method
Links
Percent batches with BWR > 0.50
AdaBoN
LM=Llama, RM=Mistral,...
2025.05
98
AdaBoN
LM=Mistral, RM=Mistral...
2025.05
94
AdaBoN
LM=Mistral, RM=FsfairX...
2025.05
94
AdaBoN
LM=Mistral, RM=Armo, K...
2025.05
92
AdaBoN
LM=Llama, RM=Armo, K=5...
2025.05
92
AdaBoN
LM=Llama, RM=FsfairX,...
2025.05
82
AdaBoN
LM=Qwen, RM=Mistral, K...
2025.05
80
AdaBoN
LM=Qwen, RM=FsfairX, K...
2025.05
76
AdaBoN
LM=Gemma, RM=Armo, K=5...
2025.05
76
AdaBoN
LM=Qwen, RM=Armo, K=5,...
2025.05
72
AdaBoN
LM=Gemma, RM=Mistral,...
2025.05
70
AdaBoN
LM=Gemma, RM=FsfairX,...
2025.05
54
Feedback
Search any
task
Search any
task
