Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety Evaluation on Crescendo
Loading...
12
ASR
Claude 3.5 Sonnet
10.22
22.235
34.25
46.265
Feb 28, 2025
ASR
Updated 1mo ago
Evaluation Results
Method
Method
Links
ASR
Claude 3.5 Sonnet
NBF steering=true
2025.02
12
Claude 3.5 Sonnet
NBF steering=false
2025.02
21.5
GPT-3.5-turbo
NBF steering=true
2025.02
23.5
GPT-4o
NBF steering=true
2025.02
26
o1
NBF steering=true
2025.02
28
o1
NBF steering=false
2025.02
44.5
GPT-3.5-turbo
NBF steering=false
2025.02
56
GPT-4o
NBF steering=false
2025.02
56.5
Feedback
Search any
task
Search any
task