Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Ethical decision-making on MACHIAVELLI Pendragon Rising 100 steps 10 seeds
Loading...
0
Violations
Always Baseline
-1.2
6.9
15
23.1
May 27, 2026
Violations
Reward
Max_t Lambda_t
Updated 6d ago
Evaluation Results
Method
Method
Links
Violations
Reward
Max_t Lambda_t
Always Baseline
baseline_selection=dyn...
2026.05
0
250
-
CCO
alpha=0.05
2026.05
6.1
316.2
89
CCO
alpha=0.10
2026.05
8.2
332.2
76
CCO
alpha=0.15
2026.05
12
343.3
71
λ = 0
lambda=0, description=...
2026.05
30
435
-
Feedback
Search any
task
Search any
task