Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
CTT-difficulty prediction on BEA (466/201 split)
Loading...
0.309
Standard Deviation (SD)
Shared-task winner
0.29355
0.301275
0.309
0.316725
Jul 8, 2026
Standard Deviation (SD)
Root Mean Square Error (RMSE)
RMSE / SD Ratio
R-squared (R2)
Updated 16d ago
Evaluation Results
Method
Method
Links
Standard Deviation (SD)
Root Mean Square Error (RMSE)
RMSE / SD Ratio
R-squared (R2)
Shared-task winner
ntrain / ntest=466 / 2...
2026.07
0.309
0.299
0.97
-
Dummy (mean) baseline
ntrain / ntest=466 / 2...
2026.07
0.309
0.311
1.01
0
Fine-tuned ensemble
ntrain / ntest=466 / 2...
2026.07
0.309
0.2926
0.95
-
Feedback
Search any
task
Search any
task