Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Steering on Human study
Loading...
93
Human-likeness Win Rate
Task Tokens
44.12
56.81
69.5
82.19
Mar 28, 2025
Human-likeness Win Rate
Updated 20d ago
Evaluation Results
Method
Method
Links
Human-likeness Win Rate
Task Tokens
Wins v.s. Algorithm=PPO
2025.03
93
Task Tokens
Wins v.s. Algorithm=Ma...
2025.03
90
Task Tokens
Wins v.s. Algorithm=Ma...
2025.03
89
Task Tokens
Wins v.s. Algorithm=AMP
2025.03
84
Task Tokens
Wins v.s. Algorithm=Ma...
2025.03
75
Task Tokens
Wins v.s. Algorithm=PULSE
2025.03
46
Feedback
Search any
task
Search any
task