Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Downstream Performance Prediction on MMLU
Loading...
0.0015
MSE
CSV
0.000184
0.00873
0.017275
0.025821
Jun 16, 2025
MSE
Updated 1mo ago
Evaluation Results
Method
Method
Links
MSE
CSV
loss type=CSV (Capabil...
2025.06
0.0015
All token loss
loss type=All token
2025.06
0.024
Label token loss
loss type=Label token
2025.06
0.0331
Feedback
Search any
task
Search any
task
