Abstract
The first tabular foundation model, TabPFN, and its successor TabPFNv2 have impacted tabular AI substantially, with dozens of methods building on it and hundreds of applications across different use cases.
This report introduces TabPFN-2.5, the next generation of our tabular foundation model, scaling to 20× data cells compared to TabPFNv2. On industry standard benchmarks with up to 50,000 data points and 2,000 features, TabPFN-2.5 substantially outperforms tuned tree-based models and matches the accuracy of AutoGluon 1.4, a complex four-hour tuned ensemble that even includes the previous TabPFNv2.
For production use cases, we introduce a new distillation engine that converts TabPFN-2.5 into a compact MLP or tree ensemble, preserving most of its accuracy while delivering orders-of-magnitude lower latency and plug-and-play deployment.This new release will immediately strengthen the performance of the many applications andmethods already built on the TabPFN ecosystem.
This new release will substantially strengthen the performance of the many applications and methods already built on TabPFN.
Introduction
Tabular data is ubiquitous, forming the backbone of decision-making in countless domains, from finance to healthcare. For decades, traditional tabular machine learning—built on gradient-boosted trees, random forests, and linear or additive models—has been the workhorse of applied data science. Yet these methods remain limited: they require extensive dataset-specific tuning, often provide uncalibrated or unreliable uncertainty estimates without significant modification, and lack the generalization and transferability of modern foundation models.
Tabular foundation models (TFMs) offer a new paradigm. They address these limitations by pretraining on large synthetic distributions of tabular tasks and performing inference via in-context learning instead of gradient descent. They are training-free predictors meta-trained to yield strong calibration, without the need for time-consuming and labor-intensive hyperparameter tuning necessary for gradient-boosted trees. Their strong generalization makes them particularly attractive for data-scarce domains.
Our initial release, TabPFNv1, served as a proof-of-concept that a transformer could learn a Bayesian-like inference algorithm, though it was limited to small (up to 1,000 samples), clean, numerical-only data. Our successor, TabPFNv2, scaled this idea into a practical model for datasets up to 10,000 samples. TabPFNv2 handles the messy and heterogeneous data seen in the real world—including categorical features, missing values & outliers.
What's New in TabPFN-2.5
State-of-the-Art Performance
In a forward pass, TabPFN-2.5 outperforms tuned tree-based models (like XGBoost and CatBoost) and matches the accuracy of AutoGluon 1.4 tuned for 4 hours—a complex ensemble that includes all previous methods, even TabPFNv2.
Improved Scalability
We scale the power of in-context learning to datasets of up to 50,000 samples (5× increase over TabPFNv2) and 2,000 features (4× increase), making TFMs viable for a much wider range of real-world problems.
Fast Inference
We've dramatically improved inference latency. Our proprietary distillation engine converts TabPFN-2.5 into a compact MLP or tree ensemble, preserving most of its accuracy while delivering orders-of-magnitude lower latency and plug-and-play deployment.