← All datasets

Molecular properties

Glucocorticoid Receptor Bioactivity

This dataset pairs chemical structures with measured bioactivity against the human glucocorticoid receptor. The benchmark represents each molecule as a fingerprint and predicts its median pChEMBL value, which summarizes potency or affinity on a logarithmic scale.

RegressionLicence: CC BY-SA 3.0CHEMBL2034Target: pchembl_valuechembl ↗

Mean cross-validation scores for this dataset. Each score comes from the requested feature- and sample-cap cell, and failed fits use the constant predictor.

At this operating point

Model comparison

p=10,000, n=100 · Lower RMSE is better

Random Forest is marked with a diamond. Models are ordered by the selected metric.

Across sample budgets

Learning curves

All metric values at this operating point
ModelRMSEMAER²
RealTabPFN 2.50.93880.73120.2478
TabICL v20.9430.72670.2411
AutoGluon0.94320.72690.2409
Random Forest0.94550.72790.237
Extra Trees0.94740.72970.234
RealTabPFN v20.95070.74280.2287
CatBoost0.95250.73640.2254
Logistic Regression0.95690.73910.2185
TabFM0.96230.73210.2091
MLP0.96380.74660.2081
TabM0.96440.75950.2054
KNN0.96510.74950.204
MITRA0.96570.75670.2031
TabPFN 30.96710.74780.2008
TabDPT †0.97490.74190.189
XGBoost0.97510.75820.1879
RealMLP0.97580.7640.1866
LightGBM1.0040.78780.1395