Project AURIONAI Use-Cases Research & Innovation
tabularfamily

TabPFN

Prior Labs tabular foundation model family.

Prior LabsPrior LabsGermanyELLIS TübingenELLIS Tübingen
Prior Labs
Levelfamily
Classtabular
Parametersnot in the notes
Contextnot in the notes
Released8 Jan 2025
Opennessunknown
Runs onnot in the notes
Statusactive

Benchmark Results

maintainer-run
TabArena All Taskstabular
TabPFN-2.6defaultmaintainer-run
1,626
rank 2 of 59, All Tasks, no imputation, snapshot 2026-05-06, 59 entries6 May 2026 benchmarklist.com, benchmarklist.com
RealTabPFN-2.5tuned + ensembledmaintainer-run
1,604
8001,3001,800

Score in Elo; the axis starts at 800, as Elo has no zero. Higher is better.

rank 3 of 59, All Tasks, no imputation, snapshot 2026-05-06, 59 entries6 May 2026 benchmarklist.com, benchmarklist.com
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).

Lineage

202520262027RealTabPFN-2.5RealTabPFN-2.5, Nov 2025TabPFN-2.6TabPFN-2.6, Mar 2026TabPFN-3TabPFN-3, May 2026TabPFN-3.5TabPFN-3.5, Sep 2026

2 members have no release date in the notes, so they are not on this timeline.

Prior LabsTabPFN-3.5 belongs to this familytabularSep 2026
Prior LabsTabPFN-3 belongs to this familytabularMay 2026
Prior LabsTabPFN-2.6 belongs to this familytabular24 Mar 2026
Prior LabsRealTabPFN-2.5 belongs to this familytabularNov 2025
Prior LabsTabPFN v2 belongs to this familytabular2025
Prior LabsTabPFN v1 belongs to this familytabular2022
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Data curation and synthetic dataproduced byTabular foundation modelsexemplar

Identity

Developer
Prior Labs, ELLIS Tübingen
Family
not in the notes
Released
8 Jan 2025 sourcesnotes
Weights published
–
Record checked
10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer In-context transformer (PFN)
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Note
Pretrained about 2 weeks on 8 GPUs on about 130M synthetic datasets; up to 10,000 samples and 500 features.
Context length
not in the notes
Input
table
Output
table
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
unknown
Licence
not in the notes sources
Access routes
not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Industry Use Cases

No industry use case links this model.

Sources

  1. The state of Tabular Foundation Models (2026) mindfulmodeler.substack.com https://mindfulmodeler.substack.com/p/the-state-of-tabular-foundation-models
  2. docs.priorlabs.ai/changelog.md https://docs.priorlabs.ai/changelog.md
  3. Client Challenge nature.com https://www.nature.com/articles/s41586-024-08328-6

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "TabPFN", https://aurion.semai.id/models/prior-labs-tabpfn/, records of October 2026.