TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14(efraingaray.com)
21 points by EfrainGaray | 9 comments
Blog post benchmarking TabPFN and TabICL foundation models against tuned XGBoost on fourteen tabular datasets, finding the no-training models won all fourteen.


![Screenshot of dl.acm.org: What does it mean to be a programming language, anyhow? (2021) [pdf]](https://hn.urlbox.com/shots/renders/2024/8/22/5e6ca00a-2d05-48fc-973e-4a9327eeac8c.jpg)



![Screenshot of rodrigo-bruno.github.io: A Performance Comparison of Modern Garbage Collectors (2021) [pdf]](https://hn.urlbox.com/shots/renders/2024/10/30/bec3db13-8dd2-4974-9311-db63b4a4b730.jpg)