Project AURIONAI Use-Cases Research & Innovation
tabular

TabPFN-2.6

Prior Labs tabular foundation model; best TFM default on TabArena (rank 2).

Prior LabsPrior LabsGermanyTabPFNFamily
Prior Labs
Levelmodel
Classtabular
Parametersnot in the notes
Contextnot in the notes
Released24 Mar 2026
Opennessopen weights restricted
Runs onsingle datacentre GPU
Statusactive

Benchmark Results

maintainer-run
TabArena All Taskstabular
defaultmaintainer-run
1,626
8001,3001,800

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

rank 2 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

successor
TabPFN-2.6 to TabPFN-3: successor, medium confidenceTabPFN-3 to TabPFN-3.5: successor, high confidenceTabPFN v1 to TabPFN v2: successor, medium confidenceTabPFN v2 to TabPFN-2.6: successor, medium confidenceTabPFN v1TabPFN v1Prior Labs, 2022TabPFN v2TabPFN v2Prior Labs, 2025TabPFN-2.6TabPFN-2.6Prior Labs, Mar 2026TabPFN-3TabPFN-3Prior Labs, May 2026TabPFN-3.5TabPFN-3.5Prior Labs, Sep 2026
Prior LabsTabPFN-3 is a child (successor)medium confidencenotes
Prior LabsTabPFN v2 is the parent (successor)medium confidencenotes
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 5 models. Confidence and evidence are the notes' own.

R&D Topics

Tabular foundation modelsproduced by

Identity

Developer
Prior Labs
Family
TabPFN
Released
24 Mar 2026 sourcesregistry date
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
–
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
open weights restricted
Licence
tabpfn-2.6-license-v1.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
single datacentre GPU
Footprint
Median train about 5.5 s; tabpfn package Apache-2.0, 9.1.0 on 2 Oct 2026
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. TabArena All Tasks Benchmark Scores & AI Model Leaderboard | BenchmarkList benchmarklist.com https://benchmarklist.com/benchmarks/tabarena_all/
  2. The state of Tabular Foundation Models (2026) mindfulmodeler.substack.com https://mindfulmodeler.substack.com/p/the-state-of-tabular-foundation-models
  3. huggingface.co/api/models/Prior-Labs/tabpfn_2_6 https://huggingface.co/api/models/Prior-Labs/tabpfn_2_6
  4. pypi.org/pypi/tabpfn/json https://pypi.org/pypi/tabpfn/json

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "TabPFN-2.6", https://aurion.semai.id/models/prior-labs-tabpfn-2-6/, records of October 2026.