MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

> MiniMax has been continuously transforming itself in a more AI-native way. The core driving forces of this process are models, Agent scaffolding, and organization. Throughout the exploration process, we have gained increasingly deeper understanding of these three aspects. Today we are releasing updates to the model component, namely MiniMax M2.1, hoping to help more enterprises and individuals find more AI-native ways of working (and living) sooner.

This compresses to: “We are updating our model, MiniMax, to 2.1. Agent harnesses exist and Agents are getting more capable.”

A good model and agent harness, pointed at the task of writing this post, might suggest less verbosity and complexity— it comes off as fake and hype-chasing to me, even if your model is actually good. I disengage there.

I saw yall give a lightning talk recently and it was similarly hype-y. Perhaps this is a translation or cultural thing.

Re: MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

#5

Post by monster_truck » Fri, Dec 26, 2025, 1:55 AM UTC

That they are still training models against Objective-C is all the proof you need that it will outlive Swift.

When is someone going to vibe code Objective-C 3.0? Borrowing all of the actual good things that have happened since 2.0 is closer than you'd think thanks to LLVM and friends.

Re: MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

#6

Post by bearjaws » Fri, Dec 26, 2025, 2:00 AM UTC

p-e-w wrote: post #2

One of the cited reviews goes: “We're excited for powerful open-source models like M2.1 […]” Yet as far as I can tell, this model isn’t open at all. Not even open weights, nevermind open source.

Yeah I don't see anyway to download this, ollama has it as cloud only.

Re: MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

#7

Post by tomcam » Fri, Dec 26, 2025, 2:06 AM UTC

I still can’t figure out what it does

Re: MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

#8

Post by prmph » Fri, Dec 26, 2025, 2:18 AM UTC

tomcam wrote: post #7

I still can’t figure out what it does

You are not alone

Re: MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

#9

Post by viraptor » Fri, Dec 26, 2025, 2:19 AM UTC

monster_truck wrote: post #5

That they are still training models against Objective-C is all the proof you need that it will outlive Swift. When is someone going to vibe code Objective-C 3.0? Borrowing all of the actual good things that have happened since 2.0 is closer than you'd think thanks to LLVM and friends.

Why would they not? Existing objective-c apps will still need updates and various work. Models are still trained on assembler for architectures that don't meaningfully exist today as well.

Re: MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language Programming

#10

Post by viraptor » Fri, Dec 26, 2025, 2:20 AM UTC

p-e-w wrote: post #2

One of the cited reviews goes: “We're excited for powerful open-source models like M2.1 […]” Yet as far as I can tell, this model isn’t open at all. Not even open weights, nevermind open source.

It's scheduled for release. They jumped the gun with the news. But at far as we know, it's still coming out, just like M2.