Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Preference Prediction on Sushi Preference Category B
Loading...
67
Accuracy (0.25 Quantile)
logit
49.32
53.91
58.5
63.09
Oct 17, 2025
Accuracy (0.25 Quantile)
Accuracy (0.50 Quantile)
Accuracy (0.75 Quantile)
Updated 6d ago
Evaluation Results
Method
Method
Links
Accuracy (0.25 Quantile)
Accuracy (0.50 Quantile)
Accuracy (0.75 Quantile)
logit
Features=onehot
2025.10
67
67
68
matrix completion
Features=onehot
2025.10
67
68
68
probit (best-of-three)
Features=onehot
2025.10
67
67
68
matrix completion
Features=default
2025.10
66
66
66
probit (pairwise)
Features=onehot
2025.10
66
66
66
logit
Features=default
2025.10
65
65
65
probit (best-of-three)
Features=default
2025.10
65
65
65
probit (pairwise)
Features=default
2025.10
64
64
64
direct
Features=default
2025.10
51
51
51
direct
Features=onehot
2025.10
50
50
50
Feedback
Search any
task
Search any
task