Gene expression

variousCancers_final

The variousCancers_final dataset contains normalized microarray gene expression measurements from the RSCTC 2010 challenge collection. The benchmark predicts the supplied cancer sample class, but the OpenML documentation does not name the individual classes.

ClassificationLicence: PublicOpenML-1088Target: Decisionopenml ↗

At this operating point

Model comparison

p=10,000, n=100 · Higher Macro-F1 is better

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

Across sample budgets

Learning curves

Models

All metric values at this operating point

Model	Macro-F1	MCC	Balanced accuracy	ROC-AUC
Kumo Tabular (M)	0.7367	0.7308	0.7349	0.9549
TabPFN 3.5	0.7319	0.7484	0.7206	0.9581
Causilo	0.7233	0.7244	0.7238	0.9543
RealTabPFN 2.5	0.722	0.7297	0.7141	0.9551
Logistic Regression	0.715	0.7254	0.7056	0.941
MLP (tuned)	0.7039	0.6928	0.7107	0.9283
Logistic Regression (tuned)	0.6952	0.6837	0.7009	0.9276
LimiX2	0.6882	0.6748	0.7486	0.9474
TabPFN Wide 5k (ne3)	0.6757	0.6905	0.6693	0.9449
Extra Trees (tuned)	0.6757	0.6989	0.6429	0.953
RealMLP	0.6686	0.6778	0.6588	0.9315
MLP	0.6459	0.6703	0.6451	0.9265
TabM	0.6404	0.6376	0.6247	0.9353
XGBoost (tuned)	0.5834	0.5907	0.5544	0.9054
AutoGluon	0.5622	0.605	0.5309	0.9388
TabDPT	0.5511	0.5814	0.5087	0.9364
MITRA	0.5497	0.5624	0.531	0.9067
GeneICL	0.5384	0.6169	0.5665	0.9187
XGBoost	0.5293	0.5249	0.5076	0.8749
Random Forest	0.5243	0.5876	0.4981	0.9368
Extra Trees	0.5046	0.5749	0.4726	0.933
Random Forest (tuned)	0.4802	0.5648	0.4602	0.938
RealTabPFN v2	0.3962	0.519	0.4013	0.9249
TabFM	0.2727	0.4008	0.2948	0.9008