Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-objective preference selection on OpenAI models Setup A1: K=5, M*=2
Loading...
0.055
Cost ($)
ϵ-greedy
0.05076
0.07938
0.108
0.13662
May 30, 2026
Cost ($)
CR
CP
Updated 1mo ago
Evaluation Results
Method
Method
Links
Cost ($)
CR
CP
ϵ-greedy
2026.05
0.055
2.5
80
CUPID
2026.05
0.056
2.2
100
CUPID without language
Ablation=without language
2026.05
0.06
4.2
100
CUPID without cost penalty
Ablation=without cost...
2026.05
0.081
4.2
100
Cost-constrained LMA
2026.05
0.091
5.75
80
Latent Dueling Bandits
2026.05
0.108
-
0
LMA
2026.05
0.115
5
60
RUCB
2026.05
0.161
-
0
Feedback
Search any
task
Search any
task