Kimi K2.7 Code vs Mistral Large 3

Choose Kimi K2.7 Code if you want cheap, capable open-weight coding agents. Choose Mistral Large 3 if you want general-purpose open-weight agent work, especially in the EU.

In our editorial scoring, Kimi K2.7 Code leads in 4 of five dimensions (output quality, agentic ability, value for $ and reliability), while Mistral Large 3 leads in 1. On price, Kimi K2.7 Code runs about $1.35 per 1M tokens (blended) and is open-weight; Mistral Large 3 is about $0.80 and open-weight.

The model is half the story — the agent is the other half

The model picks the moves; the agent runs the loop, the tools, and the guardrails. Once you've chosen a model, see which agent gets the most out of it.