What a coincidence! I just released OpenATP earlier today. OpenATP is an open-source Python package and CLI for agentic automated theorem provers. It includes support for Leanstral with Mistral’s Vibe harness. The previous production Leanstral model was deprecated on May 22nd. I will update the package to point to Leanstral 1.5 ASAP!
I would have preferred actual proof objects, as in Metamath's: separate the actual proof from the heuristics used to find it (also valuable, but a different thing).
Real talk, does anyone use anything from Mistral because it performs the best, by whatever secular metric of your choosing? Or is it only used "because EU"? Just focus on answering the question. I wonder if anyone has observed it perform better on any objective metric in any rigorous setting.
For writing and languange learning it's very decent, especially Mistral Large. The pricing is very good too. I really like the consistently low time to first token and good token per second. Claude, especially in the past, would be very inconsistent, often with outages. Mistral mostly just always works and is very fast.
Technical questions are unfortunately hit or miss. I'm lately pretty much always using a system prompt that emphasizes short answers [1], and Opus regularly one-shots it while Mistral needs a follow up. I use big-AGI as a model router [2] (dumb name, great software), which makes switching midway very easy though. For coding I'm still using Claude Code mostly out of inertia (although I really want to move to an OSS harness) and the one time I tried their `vibe` tool months ago it was a bit rough.
Mistral TTS with diarization is also great and cheap. That's the only thing for which I use their web UI.
[1] Give a short but helpful answer to the question the user asks. When helping with a computer-related task, unless the user asks, don't give any installation or setup instructions, but just get straight to the point. When the user asks a follow up question, give a more complete and longer answer while still not overexplaining. When the user prefaces the question with "short mode off" in any question, give a full and well considered reply.
I use their Voxtral Mini STT audio model to automatically transcribe my podcasts into markdown.
Out of all the STT models I've tried, it's both the best performing and one of the cheapest!
It's really accurate, feeding the episode notes and the podcast description ensures all names are properly spelled, and speaker diarization works really great.
(I just do a Gemini flash pass at the end to identify the speakers, so it shows the host name instead of "Speaker 1")
We are not Mistral's target audience. For instance I don't know if Leanstral performs the best as a "formal proof engineering model optimised for automated theorem proving and autoformalization" because I don't even know wth that is or who else does it.
Mistral themselves focus more on b2b; financial services, manufacturing, stuff like that, and they get some big clients that way.
Despite not being their target, I started using them because they have many open models. I continue using them because, yeah EU, but also because the community is great and the tool makes me think more than Claude does. Last, I stick with them because they are one of the few AI companies that are up-front about their environmental impact and are actually trying to minimize it while still providing a decent product.
If you can express a solution in Lean you can formally prove or disprove it. Formal verification is making a debut in traditional engineering toolkits.
I still prefer Mistral Nemo 12B for text summarisation tasks. It has a nice style. The Mistral Small 24B is also decent. I have a YouTube transcript summariser which I like these for.
However these days I usually have Qwen 3.6 27B already loaded so I mostly just use that instead.
I made a game (https://prose-or-con.com) where you pick whether writing is AI or human. Mistral is a bonkers weird writer. So weird I fell for it a couple of times because I thought, "No way a model writes this weird." Not, like, incorrect grammar or spelling or anything, just...off-kilter. Kinda sassy.
Yes, it's on the todo list, but I need more data. Only a half dozen people have played it and submitted a score. I'm storing the hashes of passages people got right and wrong so I can make exactly that chart at some point. I think both "the most human-like AI" and "the most AI-like human" are both interesting pieces of data, but I don't know either yet.
> 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.
I use it because EU and API pricing is decent to me. And support is awesome also. They reply the same day or at most the next day, and they follow the ticket great. It isn't that bad, but neither the best.
A few months ago, I had some data cleaning to do; their small model was surprisingly efficient and got the job done for 0.2x what I expected to run (Anthropic Sonnet / Haiku). Their TTS / STT is also roughly at the frontier, at least for French.
But I admit I only consider them because they're from France. Haven't seen a dimension where they're competitive for general users
OCR is off the charts good on every metric you can think of.
LLMs are a near-afterthought at this point if you don’t have data residency requirements. I love them and they’re slightly underrated, their models are consistently well-trained, open, but as you note, behind. There is no metric that will say they’re ahead in anything.
GitHub: https://github.com/henryrobbins/open-atp
Docs: https://open-atp.henryrobbins.com
Technical questions are unfortunately hit or miss. I'm lately pretty much always using a system prompt that emphasizes short answers [1], and Opus regularly one-shots it while Mistral needs a follow up. I use big-AGI as a model router [2] (dumb name, great software), which makes switching midway very easy though. For coding I'm still using Claude Code mostly out of inertia (although I really want to move to an OSS harness) and the one time I tried their `vibe` tool months ago it was a bit rough.
Mistral TTS with diarization is also great and cheap. That's the only thing for which I use their web UI.
[1] Give a short but helpful answer to the question the user asks. When helping with a computer-related task, unless the user asks, don't give any installation or setup instructions, but just get straight to the point. When the user asks a follow up question, give a more complete and longer answer while still not overexplaining. When the user prefaces the question with "short mode off" in any question, give a full and well considered reply.
[2] https://github.com/enricoros/big-AGI
Mistral themselves focus more on b2b; financial services, manufacturing, stuff like that, and they get some big clients that way.
Despite not being their target, I started using them because they have many open models. I continue using them because, yeah EU, but also because the community is great and the tool makes me think more than Claude does. Last, I stick with them because they are one of the few AI companies that are up-front about their environmental impact and are actually trying to minimize it while still providing a decent product.
If you can express a solution in Lean you can formally prove or disprove it. Formal verification is making a debut in traditional engineering toolkits.
I’ve also found it very good at pulling info from pdfs. Even a complicated festival with multiple venues and timetables.
However these days I usually have Qwen 3.6 27B already loaded so I mostly just use that instead.
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.
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.
But I admit I only consider them because they're from France. Haven't seen a dimension where they're competitive for general users
[1]: https://github.com/maxim/ringbinder
LLMs are a near-afterthought at this point if you don’t have data residency requirements. I love them and they’re slightly underrated, their models are consistently well-trained, open, but as you note, behind. There is no metric that will say they’re ahead in anything.