[adev_]

> Mistral because it performs the best, by whatever secular metric of your choosing?

I am. I use them primarily through their vibe CLI.

Reason is simple: They are cheaper (by almost one order of magnitude compared to Claude) and still do the job pretty well.

For small programming tasks, quick prototyping, refactoring or anything verbose and not requiring a context too large: I first go to Mistral and then eventually to Claude if I'm unsatisfied.

I also found out some of their models to be more responsive than OpenAI ones (which is not so surprising considering the size).

My tasks are mainly C++ and Python programming. People in other languages might not share my enthusiasm.

[jatora]

Your reason can't be cost because there are superior models that are cheaper than Mistral models, for coding. So i re-ask the question

[adev_]

> Your reason can't be cost because there are superior models that are cheaper than Mistral models

Nope. This is not my experience.

Public pricing in token/$ is only part of the equation.

Mistral tooling to consume significantly less tokens-per-given-task than the Anthropic ones.

My bills currently reflects that.

[tjwebbnorfolk]

I think other commenter is talking about smaller/cheaper models like Qwen that outperform mistral on just about every metric

[adev_]

I played with Qwen few months ago, I do prefer Mistral vibe for everyday usage (significantly faster if not self hosted).

[greenavocado]

Compare to Xiaomi MiMo-V2.5 you will be shocked