Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Sampling on ManyWell-32 N=30 chains
Loading...
3.148
Lambda_hat_K Statistic
CMCD-APT
2.977
4.13125
5.2855
6.43975
Feb 14, 2025
Lambda_hat_K Statistic
R Statistic
CN-R Statistic
Updated 23d ago
Evaluation Results
Method
Method
Links
Lambda_hat_K Statistic
R Statistic
CN-R Statistic
CMCD-APT
K=5, Neural Calls=6, I...
2025.02
3.148
6,678
1,113
CMCD-APT
K=2, Neural Calls=3, I...
2025.02
3.827
5,544
1,848
Diff-APT
K=5, Neural Calls=6, I...
2025.02
3.94
7,634
1,272.3
CMCD-APT
K=1, Neural Calls=2, I...
2025.02
4.384
4,729
2,364.5
Diff-APT
K=2, Neural Calls=3, I...
2025.02
5.225
5,894
1,964.7
PT
Neural Calls=0, Iterat...
2025.02
5.475
3,733
1,866.5
Diff-APT
K=1, Neural Calls=2, I...
2025.02
6.663
4,398
2,199
Diff-PT
K=0, Neural Calls=2, I...
2025.02
7.423
3,440
1,720
Feedback
Search any
task
Search any
task