Discussion on User Impressions of K3

AaronBergman18 · x · 2026-07-17

The author is asking the community about their actual experiences with k3.

They added that after recently evaluating numerous LLMs for a highly expensive task, they are increasingly convinced by the notion that "open-weight models have already saturated benchmark tests." In contrast, Sonnet 5 performs significantly better on such tasks than cheaper public models, though the author remains open to the possibility that "this time might be different."

Related event: Kimi K3 Coding Test Nears Frontier Models but Lacks Usability(3 posts)→

Original post →

More from Models

Models channel →