Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Item Difficulty Prediction on BEA Shared Task 2024 (test)
Loading...
0.288
RMSE
Qwen-8B
0.28684
0.29467
0.3025
0.31033
Jan 5, 2026
RMSE
Pearson Correlation
Updated 3mo ago
Evaluation Results
Method
Method
Links
RMSE
Pearson Correlation
Qwen-8B
number of parameters=8B
2026.01
0.288
0.381
Ensemble
2026.01
0.292
-
Qwen-14B
number of parameters=14B
2026.01
0.294
0.336
Qwen-32B
number of parameters=32B
2026.01
0.297
0.365
ELECTRA
2026.01
0.299
-
Qwen-4B
number of parameters=4B
2026.01
0.309
0.212
Dummy Regressor Baseline
2026.01
0.31
-
Qwen-1.7B
number of parameters=1.7B
2026.01
0.317
0.157
Feedback
Search any
task
Search any
task