As mentioned at euler.stephan-brumme.com these tend to be harder, as they have their own judge system that actually runs programs, and therefore can test input multiple test cases against their reference implementation rather than just hard testing the result for a single input.
Goes only up to Project Euler problem 254 as of 2025, which had been published much much earlier, in 2009, so presumably they've stopped there.
Cool deeptech ones:
Boring ones:
International ones with a British presence:
ARC-AGI visualization by Ciro Santilli 37 Created 2025-10-14 Updated 2025-10-18
www.kaggle.com/code/allegich/arc-agi-2025-visualization-all-1000-120-tasks contains plots of all questions and answers. It is truly very convenient.
Sakana.AI by Ciro Santilli 37 Created 2025-10-14 Updated 2025-12-01
Their description is a bit of localization randomness:
We are building a world class AI research lab in Tokyo.
We want to develop AI solutions for Japan's needs, and democratize AI in Japan.
Video 1.
I Co-Invented the Transformer. Now I'm Replacing It.
Source. Interview with Sakana.AI co-founders Llion Jones and Luke Darlow by Machine Learning Street Talk published Nov 23, 2025.
LeanAgent by Ciro Santilli 37 2025-10-14
They do have a database system which is interesting.

Unlisted articles are being shown, click here to show only listed articles.