# TabPFN-3: Technical Report

arXiv: https://arxiv.org/abs/2605.13986 · HTML: https://mlsanity.com/paper/2605.13986/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 276 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 30 of 69)

- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [Chronos-2: From Univariate to Universal Forecasting](https://mlsanity.com/paper/2510.15821/) (2025)
- [TabArena: A Living Benchmark for Machine Learning on Tabular Data](https://mlsanity.com/paper/2506.16791/) (2025)
- [TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning](https://mlsanity.com/paper/2505.23719/) (2025)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025)
- [CARTE: Pretraining and Transfer for Tabular Learning](https://mlsanity.com/paper/2402.16785/) (2024)
- [fev-bench: A Realistic Benchmark for Time Series Forecasting](https://mlsanity.com/paper/2509.26468/) (2025)
- [Do-PFN: In-Context Learning for Causal Effect Estimation](https://mlsanity.com/paper/2506.06039/) (2025)
- [CausalPFN: Amortized Causal Effect Estimation via In-Context Learning](https://mlsanity.com/paper/2506.07918/) (2025)
- [RelGNN: Composite Message Passing for Relational Deep Learning](https://mlsanity.com/paper/2502.06784/) (2025)
- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [RealCause: Realistic Causal Inference Benchmarking](https://mlsanity.com/paper/2011.15007/) (2020)
- [Scalable-Softmax Is Superior for Attention](https://mlsanity.com/paper/2501.19399/) (2025)
- [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025)
- [Turning Tabular Foundation Models into Graph Foundation Models](https://mlsanity.com/paper/2508.20906/) (2025)
- [Relational Graph Transformer](https://mlsanity.com/paper/2505.10960/) (2025)
- [Foundation Models for Causal Inference via Prior-Data Fitted Networks](https://mlsanity.com/paper/2506.10914/) (2025)
- [TabPFGen -- Tabular Data Generation with TabPFN](https://mlsanity.com/paper/2406.05216/) (2024)
- [Benchmarking Multimodal AutoML for Tabular Data with Text Fields](https://mlsanity.com/paper/2111.02705/) (2021)
- [KumoRFM-2: Scaling Foundation Models for Relational Learning](https://mlsanity.com/paper/2604.12596/) (2026)
- [xRFM: Accurate, scalable, and interpretable feature learning models for tabular data](https://mlsanity.com/paper/2508.10053/) (2025)
- [Bringing Graphs to the Table: Zero-shot Node Classification via Tabular Foundation Models](https://mlsanity.com/paper/2509.07143/) (2025)
- [TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts](https://mlsanity.com/paper/2510.06162/) (2025)
- [Dynamic Structural Causal Models](https://mlsanity.com/paper/2406.01161/) (2024)
- [TIME: TabPFN-Integrated Multimodal Engine for Robust Tabular-Image Learning](https://mlsanity.com/paper/2506.00813/) (2025)
- [Vectorizing string entries for data processing on tables: when are larger language models better?](https://mlsanity.com/paper/2312.09634/) (2023)
- [Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?](https://mlsanity.com/paper/2512.08798/) (2025)

## Built on by (most cited first, 17 of 17)

- [Trio: Learning Time-Series Forecasting with Temporal-Spatial-Sample Attention and Structural Causal Priors](https://mlsanity.com/paper/2606.07291/) (2026)
- [All Explanations are Wrong, But Many Are Useful: Exploring the Rashomon Explanation Set with Large Language Models](https://mlsanity.com/paper/2607.09502/) (2026)
- [Architecture Alignment With Sparse Priors in Tabular Foundation Models](https://mlsanity.com/paper/2609.36883/) (2026)
- [Closing the Context Gap: Activation Alignment for Tabular In-Context Learning](https://mlsanity.com/paper/2610.06679/) (2026)
- [Adapting prior-data fitted networks for tabular anomaly detection](https://mlsanity.com/paper/2610.06693/) (2026)
- [To Learn is to Wander: Learning Across Graphs and Tasks with Random Walks](https://mlsanity.com/paper/2610.06694/) (2026)
- [Few-Shot Bioactivity Prediction with Meta-Learning under Assay Heterogeneity](https://mlsanity.com/paper/2610.07079/) (2026)
- [TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context Diversity](https://mlsanity.com/paper/2610.07559/) (2026)
- [TICDA: Tabular In-Context Data Attribution](https://mlsanity.com/paper/2610.07996/) (2026)
- [ProximalFM: Amortized Proximal Causal Inference under Hidden Confounding](https://mlsanity.com/paper/2610.08078/) (2026)
- [The Standardization Trap: Certifying Joint Label Processing in Tabular Foundation Models](https://mlsanity.com/paper/2610.08314/) (2026)
- [How High Is 0.6? Floors, Ceilings, and Headroom in Interpretability Probing](https://mlsanity.com/paper/2610.08544/) (2026)
- [GeneICL: A Tabular Foundation Model for Bulk Transcriptomics](https://mlsanity.com/paper/2610.08694/) (2026)
- [Efficient Provably Private Classification with a Tabular Foundation Model](https://mlsanity.com/paper/2610.10068/) (2026)
- [Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and Jev](https://mlsanity.com/paper/2610.10321/) (2026)
- [MotherTree: Meta-learning on synthetic data improves decision tree training](https://mlsanity.com/paper/2610.10832/) (2026)
- [Test-Time Compute for Tabular Foundation Models: Mechanisms, Gains, and Limits](https://mlsanity.com/paper/2610.12005/) (2026)

## Abstract (arXiv)

Tabular data underpins most high-value prediction problems in science and industry, and TabPFN has driven the foundation model revolution for this modality. Designed with feedback from our users, TabPFN-3 builds on this foundation to scale state-of-the-art performance to datasets with 1M training rows and substantially reduce training and inference time. Pretrained exclusively on synthetic data from our prior, TabPFN-3 dramatically pushes the frontier of tabular prediction and brings substantial gains on time series, relational, and tabular-text data. On the standard tabular benchmark TabArena, a forward pass of TabPFN-3 outperforms all other models, including tuned and ensembled baselines, by a significant margin, and pareto-dominates the speed/performance frontier. On more diverse datasets, TabPFN-3 ranks first on datasets with many classes, and beats 8-hour-tuned gradient-boosted-tree baselines on datasets up to 1M training rows and 200 features. TabPFN-3 introduces test-time compute scaling to tabular foundation models. Our API offering TabPFN-3-Plus (Thinking) exploits this to beat all non-TabPFN models by over 200 Elo on TabArena, rising to 420 Elo on the largest data subset, and outperforms AutoGluon 1.5 extreme while being 10x faster, without using LLMs, real data, internet search or any other model besides TabPFN. TabPFN-3 extends the capabilities of our models, enabling SOTA prediction on relational data (new SOTA foundation model on RelBenchV1) and tabular-text data (SOTA on TabSTAR via TabPFN-3-Plus); and improves existing integrations: a specialized checkpoint, TabPFN-TS-3, ranks 2nd on the time-series benchmark fev-bench, and SHAP-value computation is up to 120x faster. TabPFN-3 achieves this performance while being up to 20x faster than TabPFN-2.5. In addition, a reduced KV cache and row-chunking scale to 1M rows on one H100 with fast inference speed.