OmniTabBench: Mapping the Empirical Frontiers of GBDTs, Neural Networks, and Foundation Models for Tabular Data at Scale

TL;DR

OmniTabBench is the largest comprehensive benchmark for tabular data, evaluating diverse models across over 3000 datasets to understand their relative strengths and conditions favoring each.

Contribution

Introduces OmniTabBench, the largest tabular benchmark with 3030 datasets, and provides large-scale empirical evaluation and analysis of model performance conditions.

Findings

No single model family dominates across all datasets.

Dataset properties influence model performance and suitability.

Large-scale evaluation clarifies model strengths and weaknesses.

Abstract

While traditional tree-based ensemble methods have long dominated tabular tasks, deep neural networks and emerging foundation models have challenged this primacy, yet no consensus exists on a universally superior paradigm. Existing benchmarks typically contain fewer than 100 datasets, raising concerns about evaluation sufficiency and potential selection biases. To address these limitations, we introduce OmniTabBench, the largest tabular benchmark to date, comprising 3030 datasets spanning diverse tasks that are comprehensively collected from diverse sources and categorized by industry using large language models. We conduct an unprecedented large-scale empirical evaluation of state-of-the-art models from all model families on OmniTabBench, confirming the absence of a dominant winner. Furthermore, through a decoupled metafeature analysis, which examines individual properties such as dataset size, feature types, feature and target skewness/kurtosis, we elucidate conditions favoring specific model categories, providing clearer, more actionable guidance than prior compound-metric studies.