Kimi K2.7 Code, for me. It's the first model I've used that usually writes working code, somewhat rarely breaks stuff when adding or changing features, and usually fixes a bug correctly just by providing a traceback or description.

Kagi Assistant defaults to the last-used model unless you got there from a Quick Answer. Several times I forgot to change models, and interrupted K2.7 Code, but after a failing to notice the model a few times and getting usable results, I now usually just leave it alone. Unless I want a quicker answer and doubt a "Code" model will grok me.

Deepseek v4 Flash and OpenAi GPT 5.6 Luna are on their free plan, which is fab. I'm not sure more is needed, for web searching.

I find Kim best. I used 4.5, now 4.6 reasoning.