Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following Evaluation on Self-instruct Eval
Loading...
56.7
Win Rate (A)
BPO
50.98
52.465
53.95
55.435
Nov 7, 2023
Win Rate (A)
Win Rate (B)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Win Rate (A)
Win Rate (B)
BPO
Base LLM=claude-instan...
2023.11
56.7
43.3
BPO
Base LLM=gpt-3.5-turbo...
2023.11
56.3
43.7
BPO
Base LLM=text-bison, M...
2023.11
56.3
43.7
BPO
Base LLM=claude-2, Met...
2023.11
51.6
48.4
BPO
Base LLM=gpt-4, Method...
2023.11
51.2
48.8
Feedback
Search any
task
Search any
task
