Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Large Model Performance Prediction on Paradigm RLHF pattern shift
Loading...
9.55
RMSE
STAR
9.406
10.378
11.35
12.322
Feb 12, 2026
RMSE
MAE
Average Score
SRCC
KRCC
MAE@3%
Average Rank
Total Score
Updated 4d ago
Evaluation Results
Method
Method
Links
RMSE
MAE
Average Score
SRCC
KRCC
MAE@3%
Average Rank
Total Score
STAR
Shift Type=Model-side,...
2026.02
9.55
7.33
8.44
92.48
84.07
39.37
71.97
-
CPMF
Shift Type=Model-side,...
2026.02
10.14
7.94
9.04
91.88
83.26
36.35
70.5
-
PMF
Shift Type=Model-side,...
2026.02
13.15
10.32
11.74
88.51
79.54
24.02
64.02
-
Feedback
Search any
task
Search any
task