TabPFN
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
Why people recommend it
“Non-LLM transformers beat tree boosting - TabPFN, TabFM”
“there is TabPFN [1] which also has time series capabilities.”
Show 1 more
“Looks really cool.”
Caveats and dissent
No one in these comments warned against it.
From the makers not counted in the ranking
“TabPFN v2 was published in Nature and set a new state of the art”
“TabPFN v2 was published in Nature and set a new state of the art”
“TabPFN v2 was published in Nature and set a new state of the art”
“We started with TabPFN. v2 was published in Nature and set a new state of the art on tabular benchmarks”
“We built TabPFN, the first foundation model that actually understands tabular data”
Threads where it came up
- Why Large Language Models Fail at Tabular Prediction 2 mentions
- Ask HN: Who is hiring? (October 2026) 1 mention
- Ask HN: Who is hiring? (September 2026) 1 mention
- Ask HN: Who is hiring? (August 2026) 1 mention
- Ask HN: Who is hiring? (July 2026) 1 mention
- Ask HN: Who is hiring? (June 2026) 1 mention
Data: tabpfn.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 4
“The inference time is still much worse than any of the more traditional models”
“Non-LLM transformers beat tree boosting - TabPFN, TabFM”
“there is TabPFN [1] which also has time series capabilities.”
“Looks really cool.”