# TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models

arXiv: https://arxiv.org/abs/2511.08667 · HTML: https://mlsanity.com/paper/2511.08667/

## Key facts

- Cited by 132 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 218 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 30 of 42)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision](https://mlsanity.com/paper/2407.08608/) (2024)
- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data](https://mlsanity.com/paper/2003.06505/) (2020)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Think before you speak: Training Language Models With Pause Tokens](https://mlsanity.com/paper/2310.02226/) (2023)
- [TabArena: A Living Benchmark for Machine Learning on Tabular Data](https://mlsanity.com/paper/2506.16791/) (2025)
- [TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling](https://mlsanity.com/paper/2410.24210/) (2024)
- [Better by Default: Strong Pre-Tuned MLPs and Boosted Trees on Tabular Data](https://mlsanity.com/paper/2407.04491/) (2024)
- [LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence](https://mlsanity.com/paper/2509.03505/) (2025)
- [Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models](https://mlsanity.com/paper/2510.21204/) (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)
- [RealCause: Realistic Causal Inference Benchmarking](https://mlsanity.com/paper/2011.15007/) (2020)
- [Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data](https://mlsanity.com/paper/2507.03971/) (2025)
- [Turning Tabular Foundation Models into Graph Foundation Models](https://mlsanity.com/paper/2508.20906/) (2025)
- [Foundation Models for Causal Inference via Prior-Data Fitted Networks](https://mlsanity.com/paper/2506.10914/) (2025)
- [Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later](https://mlsanity.com/paper/2407.03257/) (2024)
- [TabPFGen -- Tabular Data Generation with TabPFN](https://mlsanity.com/paper/2406.05216/) (2024)
- [Exact Expressive Power of Transformers with Padding](https://mlsanity.com/paper/2505.18948/) (2025)
- [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)
- [TabPFN: One Model to Rule Them All?](https://mlsanity.com/paper/2505.20003/) (2025)
- [Detecting hidden confounding in observational data using multiple environments](https://mlsanity.com/paper/2205.13935/) (2022)
- [Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning](https://mlsanity.com/paper/2507.05526/) (2025)
- [TIME: TabPFN-Integrated Multimodal Engine for Robust Tabular-Image Learning](https://mlsanity.com/paper/2506.00813/) (2025)

## Built on by (most cited first, 30 of 132)

- [Beyond IID: How General Are Tabular Foundation Models, Really?](https://mlsanity.com/paper/2606.30410/) (2026)
- [PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models](https://mlsanity.com/paper/2602.04029/) (2026)
- [Relational In-Context Learning via Synthetic Pre-training with Structural Prior](https://mlsanity.com/paper/2603.03805/) (2026)
- [No Need to Train Your RDB Foundation Model](https://mlsanity.com/paper/2602.13697/) (2026)
- [Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models](https://mlsanity.com/paper/2605.06510/) (2026)
- [EXAONE Tabular 1.0 : Technical Report](https://mlsanity.com/paper/2608.25774/) (2026)
- [EveNet: A Foundation Model for Particle Collision Data Analysis](https://mlsanity.com/paper/2601.17126/) (2026)
- [Tabular Foundation Models are Strong Graph Anomaly Detectors](https://mlsanity.com/paper/2601.17301/) (2026)
- [Tabular Foundation Models Can Do Survival Analysis](https://mlsanity.com/paper/2601.22259/) (2026)
- [From Zero to Hero: Advancing Zero-Shot Foundation Models for Tabular Outlier Detection](https://mlsanity.com/paper/2602.03018/) (2026)
- [LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models](https://mlsanity.com/paper/2606.04485/) (2026)
- [Conditional Coverage Diagnostics for Conformal Prediction](https://mlsanity.com/paper/2512.11779/) (2025)
- [TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention](https://mlsanity.com/paper/2606.07345/) (2026)
- [V0: A Generalist Value Model for Any Policy at State Zero](https://mlsanity.com/paper/2602.03584/) (2026)
- [Use What You Know: Causal Foundation Models with Partial Graphs](https://mlsanity.com/paper/2602.14972/) (2026)
- [End-to-End Compression for Tabular Foundation Models](https://mlsanity.com/paper/2602.05649/) (2026)
- [Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks](https://mlsanity.com/paper/2603.29475/) (2026)
- [ScoringBench: A Benchmark for Evaluating Tabular Foundation Models with Proper Scoring Rules](https://mlsanity.com/paper/2603.29928/) (2026)
- [Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms](https://mlsanity.com/paper/2604.04868/) (2026)
- [Tabular foundation models for in-context prediction of molecular properties](https://mlsanity.com/paper/2604.16123/) (2026)
- [Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality](https://mlsanity.com/paper/2605.18971/) (2026)
- [TabDPT-Turbo: Efficient In-Context Learning for Tabular Prediction](https://mlsanity.com/paper/2608.01400/) (2026)
- [TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering](https://mlsanity.com/paper/2601.21656/) (2026)
- [Benchmarking Optimizers for MLPs in Tabular Deep Learning](https://mlsanity.com/paper/2604.15297/) (2026)
- [Interpretable Tabular Foundation Models via In-Context Kernel Regression](https://mlsanity.com/paper/2602.02162/) (2026)
- [STRABLE: Benchmarking Tabular Machine Learning with Strings](https://mlsanity.com/paper/2605.12292/) (2026)
- [Causal Foundation Models with Continuous Treatments](https://mlsanity.com/paper/2605.15133/) (2026)
- [SurvPFN: Towards Foundation Models for Survival Predictions](https://mlsanity.com/paper/2606.04564/) (2026)
- [Where Computation Lives Inside TabPFN: Causal Localisation of Attention Head Function](https://mlsanity.com/paper/2606.12917/) (2026)
- [RocketPFN: Accurate Time Series Classification via In-Context Learning](https://mlsanity.com/paper/2606.21786/) (2026)

## Abstract (arXiv)

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, built for datasets with up to 50,000 data points and 2,000 features, a 20x increase in data cells compared to TabPFNv2. TabPFN-2.5 is now the leading method for the industry standard benchmark TabArena (which contains datasets with up to 100,000 training data points), substantially outperforming tuned tree-based models and matching the accuracy of AutoGluon 1.4, a complex four-hour tuned ensemble that even includes the previous TabPFNv2. Remarkably, default TabPFN-2.5 has a 100% win rate against default XGBoost on small to medium-sized classification datasets (<=10,000 data points, 500 features) and a 87% win rate on larger datasets up to 100K samples and 2K features (85% for regression). 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 and methods already built on the TabPFN ecosystem.