# PhenoBench: Mapping What a Deeply Phenotyped Human Cohort Can Tell Us

arXiv: https://arxiv.org/abs/2609.06080 · HTML: https://mlsanity.com/paper/2609.06080/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 5 Sep 2026.

## Builds on (most cited first, 10 of 10)

- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models](https://mlsanity.com/paper/2307.02028/) (2023)
- [Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data](https://mlsanity.com/paper/2407.04491/) (2024)
- [MedHELM: Holistic Evaluation of Large Language Models for Medical Tasks](https://mlsanity.com/paper/2505.23802/) (2025)
- [The Last Human-Written Paper: Agent-Native Research Artifacts](https://mlsanity.com/paper/2604.24658/) (2026)
- [TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention](https://mlsanity.com/paper/2606.07345/) (2026)
- [A Multimodal Dataset of 21,412 Recorded Nights for Sleep and Respiratory Research](https://mlsanity.com/paper/2311.08979/) (2023)

## Abstract (arXiv)

Deeply phenotyped cohorts combine clinical, imaging, molecular, and wearable observations across timescales from seconds to years, but heterogeneous analyses are not directly comparable. We present PhenoBench, an executable benchmark that turns deep-phenotyping measurements into explicit questions and controlled comparisons of information sources and predictive models. It is built around the Human Phenotype Project, with more than 13,000 participants at the initial visit. Each question fixes the target, population, timing, and allowed information; its evaluation contract specifies the split, metric, baseline, and claim boundary. PhenoBench defines 90 clinically grounded tasks across 15 domains and 26 input modalities. Across 160 matched regression comparisons spanning 52 tasks, six pretrained tabular models ranked above the evaluated task-specific baselines, including XGBoost and CatBoost, under a fixed single-estimator protocol with bounded tuning. Giving each task equal weight, their mean advantage over ridge was 0.0103 R2 (95% task-bootstrap interval, 0.0071-0.0136). We also evaluated 14 language models, collectively covering 40 tasks spanning phenotype recovery, classification, follow-up forecasting, and participant ordering. Without cohort-specific fitting, language models made informative predictions on some tasks but showed task-specific capability gaps, shared failures of scale, and rarely surpassed task-specific ridge or logistic regression models fitted on the same input fields. PhenoBench provides a versioned, auditable evaluation system where new questions, measurements, and models can be added without redefining existing comparisons.