Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Score prediction on PRISM held-out-user (test)
Loading...
23.33
RMSE
PEBS (EB-shrunk)
23.178
24.204
25.23
26.256
Jun 25, 2026
RMSE
Median Error
Percentage Change vs Population
Wilcoxon p
Updated 27d ago
Evaluation Results
Method
Method
Links
RMSE
Median Error
Percentage Change vs Population
Wilcoxon p
PEBS (EB-shrunk)
Arm=EB-shrunk (ours),...
2026.06
23.33
23.12
-8.58
3.8
Per-user OLS
Arm=Per-user OLS, Base...
2026.06
23.73
23.36
-7.02
1.2
Population slope
Arm=Population slope,...
2026.06
25.52
25.26
-
-
No calibration
Arm=No calibration, Ba...
2026.06
27.13
27.13
6.3
-
Feedback
Search any
task
Search any
task