Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Performance Prediction on Winogrande (WG) 1.3k (test)
Loading...
1
MAE
DISCO
0.896
1.598
2.3
3.002
Oct 9, 2025
MAE
Rank Correlation
Updated 1mo ago
Evaluation Results
Method
Method
Links
MAE
Rank Correlation
DISCO
Selection=High PDS, Pr...
2025.10
1
0.967
DISCO
Selection=High JSD, Pr...
2025.10
1.09
0.973
DISCO
Selection=High PDS, Pr...
2025.10
1.19
0.951
Metabench
Selection=Best for val...
2025.10
1.23
0.947
DISCO
Selection=High JSD, Pr...
2025.10
1.26
0.955
Model signature
Selection=Random, Pred...
2025.10
1.29
0.926
Model signature
Selection=Random, Pred...
2025.10
1.58
0.92
tinyBenchmarks
Selection=Random, Pred...
2025.10
1.64
0.928
tinyBenchmarks
Selection=Anchor-corr,...
2025.10
1.95
0.918
tinyBenchmarks
Selection=Anchor-IRT,...
2025.10
2.24
0.85
Baseline
Selection=Random, Pred...
2025.10
3.6
0.827
Feedback
Search any
task
Search any
task