Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Boston

Benchmarks

Task NameDataset NameSOTA ResultTrend
RegressionBoston UCI (test)
RMSE2.555
32
RegressionBoston
RMSE2.61
17
RegressionBoston
RAE0.41
10
RegressionBoston
Average RRSE0.48
10
RegressionBoston
MSE11.789
9
Regressionboston
Training Loss0.3075
8
RegressionBoston (test)
NLL2.589
8
Bayesian Neural Network InferenceBoston (UCI) (test)
Test Log-Likelihood-2.42
8
RegressionBoston
Average Training Time (s)1.479
6
RegressionBoston
Avg Relative Absolute Error44
6
RegressionBoston
NLL2.35
6
Uncertainty CalibrationBoston
MACE5
6
Faithfulness under retrainingBoston
AURC1.809
5
Out-of-distribution detectionBoston (UCI) (test)
OOD Detection Accuracy96.9
5
RegressionBoston
QICE3.37
5
RegressionBoston Focused Outliers
MAE0.244
5
RegressionBoston Asymmetric Outliers
MAE0.335
5
RegressionBoston Uniform Outliers
MAE0.203
5
RegressionBoston No Outliers
MAE0.208
5
RegressionBoston Uniform Outliers (test)
NLPD0.452
5
RegressionBoston No Outliers (test)
NLPD0.0924
5
Instance attribution explanationBoston (test)
Wall-clock Time (s)0.02
4
RegressionBoston
Predictive MSE1.82
4
Regressionboston
R290.42
4
Circle PackingBoston large variance
NP10.341
4
Showing 25 of 39 rows