Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Behavioral Steering on Anthropic Model-Written Evaluations AI Coordination (test)
Loading...
34
Average Token Probability
HiDRA
0.72
9.36
18
26.64
Jun 13, 2026
Average Token Probability
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Token Probability
HiDRA
System prompt=positive...
2026.06
34
CAA
System prompt=positive...
2026.06
30
SAS
System prompt=positive...
2026.06
10
CAA
System prompt=positive...
2026.06
8
SAS
System prompt=positive...
2026.06
8
No steering
System prompt=positive
2026.06
8
HiDRA
System prompt=positive...
2026.06
2
Feedback
Search any
task
Search any
task
