Life & fun · alternatives · 2026

24 alternatives to TabPFN v2 – A SOTA foundation model for small tabular data

I am excited to announce the release of TabPFN v2, a tabular foundation model that delivers state-of-the-art predictions on small datasets in just 2.8 seconds for classification and 4.8 seconds for regression compared to strong baselines tuned for 4 hours. Published in Nature, this model outperforms traditional methods on datasets with up to 10,000 samples and 500 features. The model is available under an open license: a derivative of the Apache 2 license with a single modification, adding an enhanced attribution requirement inspired by the Llama 3 license:…

TabPFN v2 is a tabular foundation model that makes predictions on small datasets in seconds rather than hours. It performs classification in 2.8 seconds and regression in 4.8 seconds, outperforming traditionally tuned… Below are 24 products that do a similar job, ranked by how close each is in meaning and then by launch-day votes. Prices are shown for the 1 we have checked on their own sites, 1 of them free or with a free tier.

1
TabPFN-2.5 – SOTA foundation model for tabular data▲73
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…
Nov 2025 · priorlabs.ai · its alternatives →
2
TabPFN-3.5, a Tabular Foundation Model for messy real-world tables▲10
Sep 2026 · priorlabs.ai · its alternatives →
3
Python SDK – forecasting with foundation time-series and tabular models▲43
We’ve built a Python SDK for running inference on foundation models designed for time-series and tabular data. They are new SOTA models for time-series and tabular tasks and work out of the box. They do not require model training or feature engineering. The link to the GitHub repository is: https://github.com/S-FM/faim-python-client
Dec 2025 · github.com · its alternatives →
4
Llama 3.2 Interpretability with Sparse Autoencoders▲579
I spent a lot of time and money on this rather big side project of mine that attempts to replicate the mechanistic interpretability research on proprietary LLMs that was quite popular this year and produced great research papers by Anthropic [1], OpenAI [2] and Deepmind [3]. I am quite proud of this project and since I consider myself the target audience for HackerNews did I think that maybe some of you would appreciate this open research replication as well. Happy to answer any questions or face any feedback. Cheers [1]…
2024 · github.com · its alternatives →
5
Mistral Small 3▲446
High performance in a 24b open-source model
2025 · mistral.ai · its alternatives →
6
DeepSeek-V4▲387
The open-source era of 1M context intelligence
Apr 2026 · huggingface.co · its alternatives →
7
PHBench▲398
Predict the next Series A from a ProductHunt launch
May 2026 · phbench.com · its alternatives →
8
Google EmbeddingGemma 2free▲318
An open, lightweight multimodal embedding model
17d ago · blog.google · its alternatives →
9
Fully client-side GPT2 prediction visualizer▲153
Hi HN! I've found this visualization tool immensely helpful over the years for getting an intuition for how an LLM "sees" some piece of text, and with a bit of elbow grease decided to move all compute to client side so I could make it publicly available. I've found it particularly useful for - Understanding exactly how repetition and patterns affect a small LM's ability to predict correctly - Understanding different tokenization patterns and how it affects model output - Getting a general sense of how "hard" different prediction tasks are for GPT-style models Known problems (that I probably…
2023 · perplexity.vercel.app · its alternatives →
10
Qwen-2.5-32B is now the best open source OCR model▲211
Last week was big for open source LLMs. We got: - Qwen 2.5 VL (72b and 32b) - Gemma-3 (27b) - DeepSeek-v3-0324 And a couple weeks ago we got the new mistral-ocr model. We updated our OCR benchmark to include the new models. We evaluated 1,000 documents for JSON extraction accuracy. Major takeaways: - Qwen 2.5 VL (72b and 32b) are by far the most impressive. Both landed right around 75% accuracy (equivalent to GPT-4o’s performance). Qwen 72b was only 0.4% above 32b. Within the margin of error. - Both Qwen models passed mistral-ocr (72.2%), which is specifically trained for OCR. - Gemma-3…
2025 · github.com · its alternatives →
11KG
Knowledge graph of restaurants and chefs, built using LLMs▲201
Hi HN! My latest side project is knowledge graph that maps the French culinary network using data extracted from restaurant reviews from LeFooding.com. The project uses LLMs to extract structured information from unstructured text. Some technical aspects you may be interested in: - Used structured generation to reliably parse unstructured text into a consistent schema - Tested multiple models (Mistral-7B-v0.3, Llama3.2-3B, gpt4o-mini) for information extraction - Created an interactive visualization using gephi-lite and Retina (WebGL) - Built (with Claude) a simple Flask web app to clean and…
2025 · theophilecantelob.re · its alternatives →
12BV
Benchmarking VLMs vs. Traditional OCR▲146
Vision models have been gaining popularity as a replacement for traditional OCR. Especially with Gemini 2.0 becoming cost competitive with the cloud platforms. We've been continuously evaluating different models since we released the Zerox package last year (https://github.com/getomni-ai/zerox). And we wanted to put some numbers behind it. So we’re open sourcing our internal OCR benchmark + evaluation datasets. Full writeup + data explorer here: https://getomni.ai/ocr-benchmark Github: https://github.com/getomni-ai/benchmark Huggingface:…
2025 · getomni.ai · its alternatives →
13
HuggingFace – Fast tokenization library for deep-learning NLP pipelines▲168
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production - huggingface/tokenizers
2020 · github.com · its alternatives →
14
Distilling DeepSeek into GPT-OSS doesn't transfer censorship. Try it▲170
We recently used DeepSeek V4 Flash as a teacher for finance tasks with GPT-OSS-120B. Distillation works well on this problem. At a constrained 8k token budget, our self-distilled 120B scores 83.61% on FinanceReasoning, above Kimi K3 (81.93%) and Inkling (65.13%). We released the 20B open weights. With V4 as the teacher though, we realized it would be timely to measure if the censorship characteristic of it transferred to the distilled version of the base model. tl;dr it didn't, the teacher answered politically sensitive questions 7 SDs differently than expected, but the distilled model's…
Jul 2026 · ctgt.ai · its alternatives →
15
DeepSeek-V3.2-Exp▲155
Long-context efficiency with DeepSeek Sparse Attention
2025 · huggingface.co · its alternatives →
16AT
A tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)▲55
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
2025 · llmapitest.com · its alternatives →
17
I implemented a neural network in SQL▲121
Two weeks ago I was on my babymoon in Corfu, Greece. While in transit, I was overseeing a GSoC intern submit an important feature to my array database library, Xarray-SQL. He added `to_dataset()`, which completed the roundtrip between thinking of array data in a tabular model simultaneously as gridded rasters (the premise of the project is that every Nd array can be mapped to 2d, where orthogonal dims of the Nd array are just primary keys of a tabular representation). We discussed in chat, now that this feature existed, what demos could we make that would prove this data model works? With…
Jul 2026 · github.com · its alternatives →
18
Fine-grained stylistic control of LLMs using model arithmetic▲85
We developed a new framework that enables flexible control of generated text in language models. By combining several models and/or system prompts in one mathematical formula, it lets you tweak your style and combine model outputs with ease. A handy tool for those working with LLMs, looking for more fine-grained control of stylistic output. More details in our paper: https://arxiv.org/abs/2311.14479. Feedback and potential applications are welcome.
2023 · github.com · its alternatives →
19UD
Unify – Dynamic LLM Benchmarks and SSO for Multi-Vendor Deployment▲91
Hey HN! I’m the founder of Unify, and we’ve just released our Model Hub, which provides a collection of LLM endpoints with live runtime benchmarks all plotted across time: https://unify.ai/hub A key finding is that static tabular runtime benchmarks for LLMs simply do not work. It’s necessary to take a time-series perspective, and plot the variations through time. We currently have 21 models provided by: Anyscale, Perplexity AI, Replicate, Together AI, OctoAI, Mistral AI and OpenAI, with more on the roadmap. We test across different regions (Asia, US, Europe), with varied…
2024 · its alternatives →
20
Desbordante 2.0 – A high-performance data profiler▲67
Hi! We are excited to announce the second release of Desbordante — an open-source, high-performance data profiler that is capable of discovering and validating many different patterns in data using various algorithms. Unlike existing data profilers, Desbordante focuses on discovering complex patterns in data, which are notoriously hard to extract. Since its inception in 2019, it has become the fastest open-source tool for these tasks. It also offers an array of patterns which have no alternative implementations. With this release, Desbordante now supports 17 types of patterns, such as:…
2024 · github.com · its alternatives →
21
finetune LLMs via the Finetuning Hub▲80
Hi HN community, I have been working on benchmarking publicly available LLMs these past couple of weeks. More precisely, I am interested on the finetuning piece since a lot of businesses are starting to entertain the idea of self-hosting LLMs trained on their proprietary data rather than relying on third party APIs. To this point, I am tracking the following 4 pillars of evaluation that businesses are typically look into: - Performance - Time to train an LLM - Cost to train an LLM - Inference (throughput / latency / cost per token) For each LLM, my aim is to benchmark them for…
2023 · github.com · its alternatives →
22
Smolmodels – open-source tool to build ML models using natural language▲37
Hi HN - Marcello and Vaibhav here. We built smolmodels to experiment with using LLMs for ML development. It's a fully open-source library that generates complete model training and inference code from natural language descriptions. It combines graph search with LLM code generation to find a model that gives as good predictions as possible. The core idea is that LLMs are overkill for a lot of predictive tasks. Smolmodels automates the trial-and-error process of finding the right model architecture and training approach, letting you build small, specialised models. You can either provide your…
2025 · github.com · its alternatives →
23
Open-source model and scorecard for measuring hallucinations in LLMs▲65
Hi all! This morning, we released a new Apache 2.0 licensed model on HuggingFace for detecting hallucinations in retrieval augmented generation (RAG) systems. What we've found is that even when given a "simple" instruction like "summarize the following news article," every LLM that's available hallucinates to some extent, making up details that never existed in the source article -- and some of them quite a bit. As a RAG provider and proponents of ethical AI, we want to see LLMs get better at this. We've published an open source model, a blog more thoroughly describing our methodology (and…
2023 · vectara.com · its alternatives →
24
TuneTrain.ai▲79
Do you know that Small Language Models (SLM) can outperform LLMs if trained (fine-tuned) on domain specific datasets, like your companies knowledge base? The issue: fine-tuning a SLM usually requires a dataset of 10k - 100k records, which is huge. I created a platform for applying "human in the loop" augmentation techniques on your small dataset, so that you can start with maybe 100 records and build-up quickly huge datasets and launch a training without prior knowledge. I implemented 2 techniques, based on LLM distillation, however: more to come. HN, what Do you think? Do you see value in…
2025 · tunetrain.ai · its alternatives →

Also compare

Ranked by how close each launch is in meaning, then by votes. Prices were read from each product’s own site when checked and can change. Refine with your own description →