Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Instruction Following Safety on Instruction Hierarchy Phrase and Password Protection
Loading...
91
Phrase Protection Adherence (User)
OpenAI o1
73.32
77.91
82.5
87.09
Dec 21, 2024
Phrase Protection Adherence (User)
Phrase Protection Adherence (Developer)
Password Protection Adherence (User)
Password Protection Adherence (Developer)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Phrase Protection Adherence (User)
Phrase Protection Adherence (Developer)
Password Protection Adherence (User)
Password Protection Adherence (Developer)
OpenAI o1
2024.12
91
70
100
96
GPT-4o
2024.12
74
82
85
69
Feedback
Search any
task
Search any
task
