TabPFN-3: Technical Report
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913170397855744 |
|---|---|
| author | Grinsztajn, Léo Flöge, Klemens Key, Oscar Birkel, Felix Jund, Philipp Roof, Brendan Manium, Mihir Hoo, Shi Bin Bühler, Magnus Garg, Anurag Safaric, Dominik Robertson, Jake Jäger, Benjamin Alessi, Simone Hayler, Adrian Moroshan, Vladyslav Purucker, Lennart Singer, Philipp Arazi, Alan Siems, Julien Metzen, Jan Hendrik Grab, Georg Erickson, Nick Guo, Siyuan Kalfon, Eliott Bing, Simon Salinas, David Cornu, Clara Wehrhahn, Lilly Charlotte Kriuchkova, Diana Kaya, Kursat Sidhoum, Lydia Salmon, Marie Chen, Jerry Hulsebos, Madelon LeCun, Yann Müller, Samuel Schölkopf, Bernhard Gambhir, Sauraj Hollmann, Noah Hutter, Frank |
| author_facet | Grinsztajn, Léo Flöge, Klemens Key, Oscar Birkel, Felix Jund, Philipp Roof, Brendan Manium, Mihir Hoo, Shi Bin Bühler, Magnus Garg, Anurag Safaric, Dominik Robertson, Jake Jäger, Benjamin Alessi, Simone Hayler, Adrian Moroshan, Vladyslav Purucker, Lennart Singer, Philipp Arazi, Alan Siems, Julien Metzen, Jan Hendrik Grab, Georg Erickson, Nick Guo, Siyuan Kalfon, Eliott Bing, Simon Salinas, David Cornu, Clara Wehrhahn, Lilly Charlotte Kriuchkova, Diana Kaya, Kursat Sidhoum, Lydia Salmon, Marie Chen, Jerry Hulsebos, Madelon LeCun, Yann Müller, Samuel Schölkopf, Bernhard Gambhir, Sauraj Hollmann, Noah Hutter, Frank |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13986 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TabPFN-3: Technical Report Grinsztajn, Léo Flöge, Klemens Key, Oscar Birkel, Felix Jund, Philipp Roof, Brendan Manium, Mihir Hoo, Shi Bin Bühler, Magnus Garg, Anurag Safaric, Dominik Robertson, Jake Jäger, Benjamin Alessi, Simone Hayler, Adrian Moroshan, Vladyslav Purucker, Lennart Singer, Philipp Arazi, Alan Siems, Julien Metzen, Jan Hendrik Grab, Georg Erickson, Nick Guo, Siyuan Kalfon, Eliott Bing, Simon Salinas, David Cornu, Clara Wehrhahn, Lilly Charlotte Kriuchkova, Diana Kaya, Kursat Sidhoum, Lydia Salmon, Marie Chen, Jerry Hulsebos, Madelon LeCun, Yann Müller, Samuel Schölkopf, Bernhard Gambhir, Sauraj Hollmann, Noah Hutter, Frank Machine Learning 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. |
| title | TabPFN-3: Technical Report |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2605.13986 |