Seldon
Seldon and Seldon-Mini where added as classification and regression models.
Changelog
Material changes to the benchmark, public artifacts, and website are recorded here.
Seldon and Seldon-Mini where added as classification and regression models.
Added the FTFM-1 model and Kumo Tabular (L), the largest variant of the Kumo Tabular family.
Added the Tox21 SR-MMP and NR-AhR molecular property tasks and the ST001000 stool metabolomics dataset comparing Crohn's disease with ulcerative colitis.
Added a failure map view that visualizes the failure rates at different feature and sample budgets. A tuned version of MLP was also added.
Added LimiX-2 and GeneICL models.
Added Causalio, Kumo Tabular (M), TabPFN 3.5 and tuned variants of classical ml models.
Probability metrics retain the complete labelled class space. ROC-AUC is undefined when a test fold lacks a task class; those folds are omitted from ROC-AUC Elo. Rebuilding reports can therefore change ROC-AUC rankings and published numbers. Log loss uses every probability column without dropping absent test classes.
Added detailed visualisations of each model's strengths and weaknesses across dataset modalities and training budgets.
Added improved per-dataset model comparisons and learning curves across feature and sample budgets.
Published the first TabBench-Bio benchmark website, interactive results, dataset registry, and versioned result artifacts.