Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Behavioral Steering on Behavioral Choice Steering Dataset
Loading...
25.4
Self-awareness Score
Curveball
-0.392
6.304
13
19.696
Mar 10, 2026
Self-awareness Score
Wealth-seeking Score
Power-seeking Score
Corrigibility Score
Updated 4mo ago
Evaluation Results
Method
Method
Links
Self-awareness Score
Wealth-seeking Score
Power-seeking Score
Corrigibility Score
Curveball
Model=Phi-3.5-mini-It
2026.03
25.4
6.7
14.9
93.4
Curveball
Model=Llama-3.2-1B-It
2026.03
24
28
47
17
Linear
Model=Llama-3.2-1B-It
2026.03
14
15
16
21
Linear
Model=Phi-3.5-mini-It
2026.03
0.6
2.3
2.9
2.1
Feedback
Search any
task
Search any
task
