Tried these with some local models and these are the ones that generated the program one shot, a few of them also generated the results correctly one shot.

llama3.1-70b, llama3.1-405b, deepseekcoder2.5, gemma-27b, mistral-large, qwen2.5-72b. https://gist.github.com/segmond/8992a8ec5976ff6533d797caafe1...

I like how the solution sort of varies across most, tho mistral and qwen look really similar.