TabPFN-2.5
SOTA foundation model for tabular data
Details
- External ID
- 45838540
- Source
- HN
- Company
- —
- Product
- TabPFN-2.5
- Website domain
- priorlabs.ai
- Launched
- Nov. 6, 2025
- Cohort
- —
- Upvotes
- 73
- Upvotes percentile
- 0.8777292576419214
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
I am excited to announce the release of TabPFN-2.5, our tabular foundation model that now scales to datasets of up to 50,000 samples and 2,000 features - a 5x increase from TabPFN v2, published in the Nature journal earlier this year. TabPFN-2.5 delivers state-of-the-art predictions in one forward pass without hyperparameter tuning across classification and regression tasks.What’s new in 2.5: TabPFN-2.5 maintains the core approach of v2 - a pretrained transformer trained on more than hundred million synthetic datasets to perform in-context learning and output a predictive distribution for the test data. It natively supports missing values, cateogrical features, text and numerical features is robust to outliers and uninformative features.The major improvements:- 5x scale increase: Now handles 50,000 samples × 2,000 features (up from 10,000 × 500 in v2)- SOTA performance: TabPFN-2.5 outperforms tuned tree-based methods and matches the performance of a complex ensemble (AutoGluon 1.4), that itself includes TabPFN v2, tuned for 4 hours. Tuning the model improves performance, outperforming AutoGluon 1.4 for regression tasks.- Rebuilt API: New REST interface along with Python SDK with dedicated fit & predict endpoints, making deployment and integration more developer-friendly- A distillation engine that converts TabPFN-2.5 into a compact MLP or tree ensemble while preserving accuracy and offer low latency inference.There are still some limitations. The model is designed for datasets up to 50K samples. It can handle larger datasets but that hasn’t been our focus with TabPFN-2.5. The distillation engine is not yet available through the API but only through licenses (though we do show the performance in the model report).We’re actively working on removing these limitations and intend to release newer models focused on context reasoning, causal inference, graph networks, larger data and time-series. TabPFN-2.5 is available via API and a package on Hugging Face. Would love for you to try it and give us your feedback!Model report: https://priorlabs.ai/technical-reports/tabpfn-2-5-model-repo...Package: https://github.com/PriorLabs/TabPFNClient: https://github.com/PriorLabs/tabpfn-clientDocs: https://docs.priorlabs.ai/quickstart
Enrichment
- Theme
- specialized AI models and agent reasoning tools
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Commercial product
- Normalized one-liner
- foundation model for tabular data
- Manually corrected
- False
Could you build this?
No TabPFN is a cutting-edge machine learning research breakthrough published in Nature that performs Prior-Data Fitted Network inference for tabular data, requiring advanced ML theory and massive synthetic data pretraining.
What it would actually take: Building TabPFN-2.5 requires training large Transformer-based architectures on synthetically generated structural datasets simulating millions of probabilistic causal mechanisms. The stack relies on PyTorch/JAX with massive distributed GPU compute clusters to approximate Bayesian inference in a single forward pass. Developing this demands deep expertise in Bayesian statistics, meta-learning, and foundational ML architecture design.
Discussion
13 comments analyzed.
Competitors mentioned: AutoGluon, XGBoost, CatBoost
Concerns raised: Text feature handling differs between local and API versions, Loading entire tables into context for large datasets, Need for custom benchmarks beyond current datasets
Feature requests: Better handling of real-world feature relationships/connections, Further reduction in manual feature engineering requirements
Competitors
Other products that read as similar to this one — 77 launches clear the similarity bar, closest 8 shown.
Attention rank: #16 of 78 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Looks like the first mover among its competitors.
- TabPFN Scaling Mode · hn · 2025-12-03 · 5 upvotes · similarity 0.71
- TabPFN MCP, gives LLMs tools for predictions on tabular data (beta) · hn · 2026-02-05 · 11 upvotes · similarity 0.55
- Python SDK · hn · 2025-12-18 · 43 upvotes · similarity 0.52
- causilo · github · 2026-09-13 · 64 upvotes · similarity 0.52
- TabPFN-3.5, a Tabular Foundation Model for messy real-world tables · hn · 2026-09-15 · 10 upvotes · similarity 0.47
- Strand AI - The Data Layer for Biology. · yc · 2026-02-25 · 605 upvotes · similarity 0.42
- resnet152v2-skin-cancer-ham10000 · github · 2026-09-27 · 17 upvotes · similarity 0.42
- Autofit2 · hn · 2026-06-25 · 28 upvotes · similarity 0.42
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.