Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Performance Prediction on MMLU Pro STEM
Loading...
0.897
Train R-squared
Rphi
0.1378
0.3349
0.532
0.7291
Sep 25, 2025
Train R-squared
Test MAE
Updated 23d ago
Evaluation Results
Method
Method
Links
Train R-squared
Test MAE
Rphi
Scaling Scenario=1B ->...
2025.09
0.897
0.575
RBRIDGE
Scaling Scenario=1B ->...
2025.09
0.897
0.574
NLL
Scaling Scenario=1B ->...
2025.09
0.207
12.582
MPCA
Scaling Scenario=1B ->...
2025.09
0.2
1.495
TED
Scaling Scenario=1B ->...
2025.09
0.199
1.572
Acc./p@1
Scaling Scenario=1B ->...
2025.09
0.167
1.624
Feedback
Search any
task
Search any
task