Contamination MapTabular / Model
TabPFN-2.5
- Organisation
- Prior Labs
- Family
- TabPFN · version 2.5
- Released
- 2025-11-11 (arXiv v1 submission date of the technical report https://arxiv.org/abs/2511.08667 (HF repo Prior-Labs/tabpfn_2_5 created 2025-11-03))
- Checkpoints
- Prior-Labs/tabpfn_2_5: tabpfn-v2.5-classifier-v2.5_default-2.ckpt, tabpfn-v2.5-classifier-v2.5_large-features-L.ckpt, tabpfn-v2.5-classifier-v2.5_large-features-XL.ckpt, tabpfn-v2.5-classifier-v2.5_large-samples.ckpt, tabpfn-v2.5-classifier-v2.5_variant.ckpt, tabpfn-v2.5-regressor-v2.5_default.ckpt, tabpfn-v2.5-regressor-v2.5_low-skew.ckpt, tabpfn-v2.5-regressor-v2.5_quantiles.ckpt, tabpfn-v2.5-regressor-v2.5_small-samples.ckpt, tabpfn-v2.5-regressor-v2.5_variant.ckpt
- Weights
- Open · tabpfn-2.5-license-v1.1 (non-commercial)
- Links
- PaperModel cardCode
Training data disclosure: Full list
Level determined for 100% of benchmark cells.
- TestTest data seen0
- SeenSeen, split unclear0
- TrainTraining data seen0
- Related data seen0
- NoNot seen51
- ?Unknown0
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Other declared training data
-
TabPFN-2.5 synthetic prior · split: unknown
Evidence
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
arxiv.org · paper · Section 3, Data · retrieved 2026-10-15
Benchmark cells
TabArena
Not seen airfoil_self_noise · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Amazon_employee_access · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen anneal · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Another-Dataset-on-used-Fiat-500 · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen APSFailure · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen bank-marketing · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Bank_Customer_Churn · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Bioresponse · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen blood-transfusion-service-center · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen churn · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen coil2000_insurance_policies · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen concrete_compressive_strength · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen credit-g · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen credit_card_clients_default · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen customer_satisfaction_in_airline · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen diabetes · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Diabetes130US · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen diamonds · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen E-CommereShippingData · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Fitness_Club · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Food_Delivery_Time · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen GiveMeSomeCredit · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen hazelnut-spread-contaminant-detection · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen healthcare_insurance_expenses · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen heloc · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen hiva_agnostic · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen houses · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen HR_Analytics_Job_Change_of_Data_Scientists · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen in_vehicle_coupon_recommendation · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Is-this-a-good-customer · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen kddcup09_appetency · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen Marketing_Campaign · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen maternal_health_risk · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen miami_housing · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen MIC · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen NATICUSdroid · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen online_shoppers_intention · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen physiochemical_protein · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen polish_companies_bankruptcy · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen qsar-biodeg · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen QSAR-TID-11 · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen QSAR_fish_toxicity · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen SDSS17 · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen seismic-bumps · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen splice · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen students_dropout_and_academic_success · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen superconductivity · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen taiwanese_bankruptcy_prediction · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen website_phishing · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen wine_quality · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Not seen jm1 · absent from the complete list of training data
Evidence (2)
“Like the original TabPFNv2, TabPFN-2.5 is trained purely on synthetically generated data.”
“TabPFN-2.5: trained purely on synthetic tabular tasks”
Notes
Synthetic-only checkpoints of the 2.5 release (those without the real-data mark on the model card). The default classification checkpoint tabpfn-v2.5-classifier-v2.5_default.ckpt is the real-data fine-tuned one (see real-tabpfn-2-5); the default regression checkpoint is synthetic-only per the card: 'default regression checkpoint, trained on synthetic data only.'
Sources
- TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models (arXiv v2) · paper · retrieved 2026-10-15
- Prior-Labs/tabpfn_2_5 model card · model card · retrieved 2026-10-15