Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Best Arm Identification on New Yorker Cartoon Caption Contest Caption 854
Loading...
0.04
False Selection Probability
iKG
0.0312
0.0906
0.15
0.2094
Oct 27, 2023
False Selection Probability
Updated 1mo ago
Evaluation Results
Method
Method
Links
False Selection Probability
iKG
Sample size=18000
2023.10
0.04
KG
Sample size=18000
2023.10
0.05
TTEI
Sample size=18000
2023.10
0.06
iKG
Sample size=12000
2023.10
0.07
TTEI
Sample size=12000
2023.10
0.1
KG
Sample size=12000
2023.10
0.11
Equal Allocation
Sample size=18000
2023.10
0.18
EI
Sample size=18000
2023.10
0.23
Equal Allocation
Sample size=12000
2023.10
0.26
EI
Sample size=12000
2023.10
0.26
Feedback
Search any
task
Search any
task