Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Large Model Performance Prediction on Frontier Top-20 pattern shift
Loading...
9.71
RMSE
STAR
9.5348
10.7174
11.9
13.0826
Feb 12, 2026
RMSE
MAE
Score Avg
SRCC
KRCC
MAE@3%
Rank Avg
Total Score
Updated 4d ago
Evaluation Results
Method
Method
Links
RMSE
MAE
Score Avg
SRCC
KRCC
MAE@3%
Rank Avg
Total Score
STAR
Shift Type=Model-side,...
2026.02
9.71
7.79
8.75
95.55
87.38
55.41
79.45
-
CPMF
Shift Type=Model-side,...
2026.02
10.71
8.93
9.82
94.97
86.35
50.64
77.32
-
PMF
Shift Type=Model-side,...
2026.02
14.09
12.35
13.22
92.66
83.28
50.64
75.53
-
Feedback
Search any
task
Search any
task
