# TabBench-Bio

> TabBench-Bio is a living benchmark for tabular learning in high-dimensional biomedical regimes. It compares classical models, neural networks, AutoML, and tabular foundation models across controlled feature and sample budgets.

Use the pages below for context and the canonical SQLite database for exact, structured results. Rankings are operating-point dependent and descriptive rather than universal. The primary charts and rankings use strict nominal-cell results. The interactive sensitivity view may reuse a verified smaller training-sample cell after a training out-of-memory failure and is not treated as performance at the requested larger sample size.

## Current snapshot

- Generated from the published result bundle at 2026-09-08T15:09:33.519526Z.
- 43 registered datasets: 30 classification, 13 regression.
- Dataset modalities: DNA methylation: 4, GLM/PLM Embeddings: 4, Gene expression: 11, Genomic prediction: 4, Metagenomics: 10, Molecular properties: 8, Other: 2.
- 19 configured model configurations; 21 currently represented in aggregate results.
- 28 feature-by-sample operating points currently have aggregate metrics.
- 6,020 configured dataset-cell-fold evaluation points per model.
- Run monitoring has recorded 81,683 of 120,830 planned units (67.6%): 55,762 pass, 23,061 design skip, and 2,860 fail.

## Current reference results

The predeclared reference operating point is p=10,000, n=100. Bradley–Terry Elo combines the classification and regression target comparisons at this cell and anchors Random Forest at 1,000. Target-bootstrap intervals quantify ranking uncertainty.

1. RealTabPFN v2.5: Elo 1,274 (95% CI 1,187–1,366; 39 targets)
2. Logistic Regression: Elo 1,129 (95% CI 1,027–1,237; 39 targets)
3. AutoGluon: Elo 1,124 (95% CI 1,025–1,227; 39 targets)
4. TabDPT: Elo 1,108 (95% CI 1,023–1,196; 39 targets)
5. TabPFN v3: Elo 1,102 (95% CI 1,024–1,183; 39 targets)

The leading intervals overlap, so the displayed order should not be interpreted as a statistically resolved universal ranking. Use the interactive controls or canonical database for other operating points.

## Evaluated models

AutoGluon, CatBoost, Constant, Extra Trees, KNN, LightGBM, Logistic Regression, MITRA, MLP, Random Forest, RealMLP, RealTabPFN v2, RealTabPFN v2.5, TabDPT, TabFM, TabICL, TabM, TabPFN Wide (8k), TabPFN Wide 5k (ne3), TabPFN v3, XGBoost.

## Training-data overlap

- † TabDPT: Part of the benchmark training data was used in the training process of this model.

These models remain in the benchmark results but are excluded from the Reference leaders podium and social card.

## Agent skill

Here is a skill for your agent: [TabBench-Bio model selection](https://tabbench-bio.eu/skill.md).
Use it to match task, modality, budgets and compute constraints, and interpret uncertainty and training-data overlap.
Download the Markdown file directly; no repository clone is needed.

## Primary pages

- [Benchmark and interactive results](https://tabbench-bio.eu/)
- [Dataset registry](https://tabbench-bio.eu/datasets.html)
- [Artifact browser](https://tabbench-bio.eu/artifacts.html)
- [Manuscript](https://arxiv.org/abs/2609.07441)

## Machine-readable data

- [Dashboard JSON](https://tabbench-bio.eu/data/dashboard.json): modality-specific rankings, costs, coverage, analysis views and model flags.
- [Leaderboard JSON](https://tabbench-bio.eu/data/leaderboard.json): aggregate rankings.
- [Dataset index JSON](https://tabbench-bio.eu/data/datasets/index.json): task-specific metrics and links to per-dataset scores.

- Canonical results SQLite: release upload pending; 689.7 MB, SHA-256 `3fbf73832c5d99fe2b275e96060713285bcba6213165dad81995842983e9a737`

## Citation

If you read or use the benchmark, website, or published result artifacts, cite:

Kreuer, J.; Ouaari, S.; Hellmig, J.; Braitinger, J.; Pfeifer, N. (2026). TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables. arXiv:2609.07441. https://doi.org/10.48550/arXiv.2609.07441

- [Citation File Format metadata](https://tabbench-bio.eu/CITATION.cff)
- Citation target: [TabBench-Bio paper](https://doi.org/10.48550/arXiv.2609.07441)
- Authors: Jules Kreuer, Sofiane Ouaari, Julia Hellmig, Julius Braitinger, and Nico Pfeifer
- DOI: [10.48550/arXiv.2609.07441](https://doi.org/10.48550/arXiv.2609.07441)
- arXiv: [2609.07441](https://arxiv.org/abs/2609.07441)

## Optional

- [Changelog](https://tabbench-bio.eu/changelog.html): notable benchmark and website updates
- [GitHub repository](https://github.com/not-a-feature/TabBench-Bio): canonical source code and issue tracker