Abstract
A large-scale benchmark of 94 curated biomedical tabular datasets standardizes evaluation across classification, regression, and multi-target tasks and finds that foundation models lead overall while tree-based models and tuned multilayer perceptrons remain competitive under cost constraints.
Recent advances in machine learning have accelerated biomedical prediction, but evaluation on structured biomedical data remains fragmented, especially for datasets with high dimensionality, large sample size, missingness, and class imbalance. We introduce TabBioMed, a large-scale benchmark of 94 curated public biomedical tabular datasets spanning electronic health records, drug discovery, genomics, transcriptomics, proteomics, metabolomics, single-cell omics, and systems biology. TabBioMed unifies these datasets through a standardized, dataset-aware preprocessing and evaluation framework, enabling reproducible comparison across classification, regression, and multi-target tasks. We benchmark 23 models across classical baselines, gradient-boosted trees, neural tabular architectures, and tabular foundation models. Foundation models deliver the strongest family-level predictive performance. However, their gains are regime-dependent: tree-based models and tuned multilayer perceptrons remain highly competitive, often dominating under inference-time or training-cost constraints. Overall, TabBioMed shows that biomedical tabular learning is strongly context-dependent, with optimal model choice depending on data regime, task type, and computational budget. We release TabBioMed with curated datasets and splits, preprocessing code, baselines, and results, providing a reproducible benchmark for practical model selection and future methods development in biomedical machine learning, available at https://github.com/AI-sandbox/TabBioMed.
Community
We’re releasing TabBioMed, a benchmark for biomedical tabular learning with curated public datasets spanning electronic health records, drug discovery, genomics, transcriptomics, proteomics, metabolomics, single-cell omics, and systems biology.
We evaluate classical baselines, gradient-boosted trees, models for tabular deep learning, and tabular foundation models. TabBioMed uses standardized, dataset-aware preprocessing and evaluation for classification, regression, and multi-target prediction. Foundation models performed best as a family overall, while tree-based models and tuned MLPs often led when training cost or inference time was constrained.
We’re sharing the datasets, splits, preprocessing code, baselines, and results so others can reproduce the comparisons and benchmark new models!
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- SurvICL: a Foundation Model for in-context Survival Analysis (2026)
- GeneICL: A Tabular Foundation Model for Bulk Transcriptomics (2026)
- ARO: Aligned Representation learning for multi-Omics data (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.23779 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 0
No model linking this paper

