[HN Gopher] MiniMax M2.1: Built for Real-World Complex Tasks, Mu...
       ___________________________________________________________________
        
       MiniMax M2.1: Built for Real-World Complex Tasks, Multi-Language
       Programming
        
       Author : 110
       Score  : 205 points
       Date   : 2025-12-26 01:02 UTC (21 hours ago)
        
 (HTM) web link (www.minimaxi.com)
 (TXT) w3m dump (www.minimaxi.com)
        
       | p-e-w wrote:
       | 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.
        
         | bearjaws wrote:
         | Yeah I don't see anyway to download this, ollama has it as
         | cloud only.
        
         | viraptor wrote:
         | 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.
        
           | p-e-w wrote:
           | I don't get it. What's the holdup? Uploading a model to
           | Hugging Face isn't exactly difficult.
        
         | NitpickLawyer wrote:
         | Repo made public a few minutes ago:
         | 
         | https://huggingface.co/MiniMaxAI/MiniMax-M2.1
        
       | jdright wrote:
       | https://www.minimax.io/news/minimax-m21
        
       | jondwillis wrote:
       | > 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.
        
         | zaptrem wrote:
         | Not sure it's a cultural thing since most of the copy coming
         | out of DeepSeek has been pretty straightforward.
        
         | tw1984 wrote:
         | so when MiniMax released a pretty capable model, you choose to
         | ignore the model itself and just focus a single sentence they
         | wrote in the release note and started bad mouthing it.
         | 
         | is it a cultural thing?
        
           | simlevesque wrote:
           | If I use a software I need to trust it.
        
             | tw1984 wrote:
             | a model is not software, it is a bunch of weights.
             | 
             | you are more than welcomed to pick whatever model or
             | software you choose to trust, that is totally fine.
             | However, that is vastly different from bad mouthing a model
             | or software just because its release note contains a single
             | sentence you don't like.
        
               | LoganDark wrote:
               | The API is software. You don't get the weights.
        
               | logicprog wrote:
               | The weights are open.
        
               | homarp wrote:
               | here https://huggingface.co/MiniMaxAI/MiniMax-M2.1
               | 
               | GGUF https://huggingface.co/unsloth/MiniMax-M2.1-GGUF
        
           | pembrook wrote:
           | It's called bikeshedding and yes it's a cultural thing on HN.
           | [1]
           | 
           | Most people here are big company worker bees where they take
           | zero risks and do very little of substance.
           | 
           | In these organizations, it's common for large groups of
           | people to get together in "meetings" and endlessly nitpick
           | surface-level details of unimportant things while completely
           | missing the big picture because it's far too complex to allow
           | for easy opinions or smart-sounding critique.
           | 
           | [1] https://en.wikipedia.org/wiki/Law_of_triviality
        
           | jondwillis wrote:
           | It's the first thing in this press release. Start with
           | garbage? I'm going to assume it's all garbage.
        
       | monster_truck wrote:
       | 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.
        
         | viraptor wrote:
         | 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.
        
         | victorbjorklund wrote:
         | I'm sure you can find some COBOL code in many of the training
         | sets. Not sure I would build my next startup using COBOL.
        
       | tomcam wrote:
       | I still can't figure out what it does
        
         | prmph wrote:
         | You are not alone
        
         | esafak wrote:
         | It's an LLM for coding.
        
         | yinuoli wrote:
         | It's a neural network model, and it could generate text
         | following a given text.
        
         | tucnak wrote:
         | You should ask ChatGPT.
        
         | dist-epoch wrote:
         | Money, it does money
        
       | viraptor wrote:
       | I've played with this a bit and it's ok. I'd place it somewhere
       | around sonnet 4.5 level, probably below. But with this aggressive
       | pricing you can just run 3 copies to do the same thing, choose
       | the one that succeeded and still come out way ahead with the
       | cost. Not as great as following instructions as Claude models and
       | can get lost, but still "good enough".
       | 
       | I'm very happy with using it to just "do things". When doing in
       | depth debugging or a massive plan is needed, I'd go with
       | something better, but later going through the motions? It works.
        
       | mr_o47 wrote:
       | I won't say it's same on the level of claude models but it's
       | definitely good at coming up with frontend designs
        
       | esafak wrote:
       | > It exhibits consistent and stable results in tools such as
       | Claude Code, Droid (Factory AI), Cline, Kilo Code, Roo Code, and
       | BlackBox, while providing reliable support for Context Management
       | mechanisms including Skill.md, Claude.md/agent.md/cursorrule, and
       | Slash Commands.
       | 
       | One of the demos shows them using Claude Code, which is
       | interesting. And the next sections are titled 'Digital Employee'
       | and 'End-to-End Office Automation'. Their ambitions obviously go
       | beyond coding. A sign of things to come...
        
         | jimmydoe wrote:
         | they are going IPO in HKEX in a few weeks. some hype up are
         | necessary, not too far fetched imo, pretty much same as
         | anthropic playbook.
        
           | tw1984 wrote:
           | anthropic playbook does include the false claim publicly made
           | by its CEO that "in six months AI would be writing 90 percent
           | of code". he made that claim 10 months ago. it is a criminal
           | offence for intentionally misleading investors in many
           | countries.
           | 
           | MiniMax is like 100x more honest.
        
             | fluoridation wrote:
             | Does it come as misleading if you honestly believe what
             | you're saying but are simply mistaken?
        
             | sumedh wrote:
             | > in six months AI would be writing 90 percent of code
             | 
             | Are you still writing code by hand?
        
         | atombender wrote:
         | Claude doesn't officially support using other, non-Anthropic
         | models, right? So did they patch the code or fake the Claude
         | API, or some other hack to get around that?
        
           | homarp wrote:
           | you have a few 'claude' proxies on github
           | 
           | llama.cpp recently added Anthropic API support
           | https://github.com/ggml-org/llama.cpp/pull/17570
        
       | Invictus0 wrote:
       | How is everyone monitoring the skill/utility of all these
       | different models? I am overwhelmed by how many they are, and the
       | challenge of monitoring their capability across so many different
       | modalities.
        
         | redman25 wrote:
         | https://www.swebench.com
         | 
         | https://swe-rebench.com
         | 
         | https://livebench.ai/#/
         | 
         | https://eqbench.com/#
         | 
         | https://contextarena.ai/?needles=8
         | 
         | https://metr.org/blog/2025-03-19-measuring-ai-ability-to-com...
         | 
         | https://artificialanalysis.ai/leaderboards/models
         | 
         | https://gorilla.cs.berkeley.edu/leaderboard.html
         | 
         | https://github.com/lechmazur/confabulations
         | 
         | https://dubesor.de/benchtable
         | 
         | https://help.kagi.com/kagi/ai/llm-benchmark.html
         | 
         | https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard
        
           | Alifatisk wrote:
           | I'd stick to artificial analysis
        
             | pylotlight wrote:
             | That has many of its own problems as well.
        
         | spoaceman7777 wrote:
         | This is the best summary, in my opinion. You can also see the
         | individual scores on the benchmarks they use to compute their
         | overall scores.
         | 
         | It's nice and simple in the overview mode though. Breaks it
         | down into an intelligence ranking, a coding ranking, and an
         | agentic ranking.
         | 
         | https://artificialanalysis.ai/
        
       | gcanyon wrote:
       | Would it kill them to use the words "AI coding agent" somewhere
       | prominent?
       | 
       | "MiniMax M2.1: Significantly Enhanced Multi-Language Programming,
       | Built for Real-World Complex Tasks" could be an IDE, a UI
       | framework, a performance library, or, or...
        
         | spoaceman7777 wrote:
         | It's not an AI coding agent. It's an LLM that can be used for
         | whatever you'd like, including powering coding agents.
        
           | gcanyon wrote:
           | HA! I _almost_ added a disclaimer to the original message
           | that I wasn 't certain in my identification, hence the
           | request/complaint that they didn't make it clear. But I
           | figured the message would be more effective if I "confidently
           | got it wrong" rather than asking, so I went with it.
        
             | martin-t wrote:
             | Some sad irony: just like saying the wrong thing is more
             | likely to get you a reply, using a poor title gets them
             | more engagement.
        
               | gcanyon wrote:
               | Maybe :-(
        
           | pdyc wrote:
           | That reinforces OP's point that it isn't clear from their
           | wording. I initially thought it was a speech model, then I
           | saw Python, etc., and it took me a bit more reading to
           | understand what it actually is
        
         | tw1984 wrote:
         | its main Chinese competitor GLM is like making 50 cents USD
         | each in the past 6 months from its 40 million "developer
         | users", calling your flagship model "AI coding agent" is like
         | telling investors "we are doing this for fun, not for money".
        
       | boredemployee wrote:
       | Internal Server Error
        
       | sosodev wrote:
       | I've spent a little bit of time testing Minimax M2. It's quite
       | good given the small size but it did make some odd mistakes and
       | struggle with precise instructions.
        
         | viraptor wrote:
         | This is an announcement for M2.1 not M2. It got a decent bump
         | in agent capabilities.
        
       | integricho wrote:
       | Their site crashes my phone browser while scrolling. Is that the
       | expected quality of output of their product?
        
         | Tepix wrote:
         | Should a website be able to crash a browser?
        
         | jedisct1 wrote:
         | If a website can crash your browser, the problem is your
         | browser...
        
       | kachapopopow wrote:
       | I think people should stop comparing to sonnet, but to opus
       | instead since it's so far ahead on producing code I would
       | actually want to use (gemini 3 pro tends to be lacking in
       | generalization and wants things to be using it's own style rather
       | than adapting).
       | 
       | Whatever benchmark opus is ahead in should be treated as a very
       | important metric of proper generalization in models.
        
         | azuanrb wrote:
         | I generally prefer Sonnet as comparison too. Opus, as good as
         | it is, is just too expensive. The "best" model is the one I can
         | use, not the one I can't afford.
         | 
         | These days, by default I just use Sonnet/Haiku. In most cases
         | it's more than good enough for me. It's plenty with $20 plan.
         | 
         | With MiniMax, or GLM-4.7, some people like me are just looking
         | for Sonnet level capability at much cheaper price.
        
           | baq wrote:
           | are you counting price per token or price per successful
           | task? I'm pretty sure opus 4.5 is cheaper per task than
           | sonnet in some use cases.
        
             | azuanrb wrote:
             | Per successful tasks. The result are mixed. Like you
             | mentioned, it can be cheaper but only in some use cases.
             | I'm only on the $20 plan. If I use Opus and it's not as
             | efficient for my current tasks, I'll burn through my limit
             | pretty fast. Ended up can't use any anymore for the next
             | few hours.
             | 
             | Whereas with Sonnet/Haiku, I'm much more guaranteed to have
             | 100% AI assistance throughout my coding session. This
             | matters more to me right now. Just a tradeoff I'm willing
             | to make.
        
           | mjburgess wrote:
           | Are you using GLM-4.7? I've just spent a fortune on Opus, and
           | I heard GLM was close -- but after integrating it into
           | cursor, it seems to spin forever, loose tool use, and
           | generates partial? plans. I did look into using it with the
           | claude cli tool, so it could be cursor specific -- but I
           | havent had the best experience despite going for the pro plan
           | with them. Any advise on how you're using GLM effectively? If
           | at all
           | 
           | At the moment Opus is the only model i can trust even when it
           | generates "refactoring work", it can do the refactoring.
        
             | azuanrb wrote:
             | I'm on the Lite plan. For coding, I still prefer Claude
             | because the models are simply better. I mainly use CLI
             | tools like Claude Code and OpenCode.
             | 
             | I'm also managing a few projects and teams. One way I'm
             | getting value from my GLM subscription is by building a
             | daily GitHub PR summary bot using a GitHub Action. It's
             | good enough for me to keep up with the team and to monitor
             | higher-risk PRs.
             | 
             | Right now I'm using GLM more as an agent/API rather than as
             | a coding tool. Claude works best for agentic coding for me.
             | 
             | I'm on Claude $20 plan and I usually start with Haiku, then
             | I switch to Sonnet or Opus for harder or longer tasks.
        
             | sumedh wrote:
             | > I did look into using it with the claude cli tool, so it
             | could be cursor specific
             | 
             | Claude Code with GLM seems ok to me, I just it use it as a
             | backup LLM if in case I hit usage limits but for some light
             | refactoring it did the job well.
             | 
             | Are you also facing issues with Claude Code and GLM?
        
           | andai wrote:
           | Opus is 3x cheaper now.
           | 
           | I think it's still not on the $20 plan tho which is sad.
        
             | WiSaGaN wrote:
             | It is now. But the limit on $20 plan is quite low and easy
             | to use up.
        
             | azuanrb wrote:
             | Available since few weeks ago.
             | 
             | > Claude Opus 4.5, our frontier coding model, is now
             | available in Claude Code for Pro users. Pro users can
             | select Opus 4.5 using the /model command in their terminal.
             | 
             | Opus 4.5 will consume rate limits faster than Sonnet 4.5.
             | We recommend using Opus for your most complex tasks and
             | using Sonnet for simpler tasks.
        
             | sheepscreek wrote:
             | Use Claude Opus in Antigravity. Google is very generous
             | with the limits. The best part is, if you hit your limit,
             | you can switch to Gemini Pro High.
             | 
             | I think Google is able to do this because they host Claude
             | on their own TPUs in their datacentres (probably for Vertex
             | AI customers). So they can undercut just about anyone
             | include Anthropic on costs!
             | 
             | No matter which model you start with, having the other
             | frontier model as a backup is fantastic. Essentially you're
             | getting 2x the limit.
        
       | Tepix wrote:
       | The weights got released on huggingface now.
       | 
       | https://huggingface.co/MiniMaxAI/MiniMax-M2.1
        
       | stpedgwdgfhgdd wrote:
       | Internal Server Error
        
         | 01-_- wrote:
         | me too
        
       | gempir wrote:
       | Very anecdotal but for me this model has very weak prompt
       | adherence. I compared it a tiny bit to gemini flash 3.0 and
       | simple things like "don't use markdown tables in output" was very
       | hard to get with m2.1
       | 
       | Took me like 5 prompt iterations until it finally listened.
       | 
       | But it's very good, better than flash 3.0 in terms of code output
       | and reasoning while being cheaper.
        
       | m00dy wrote:
       | I used gemini-3-pro-preview on Deepwalker [0]. It was good, then
       | switched to gemini-3-flash, It's ok. It gets the job done.
       | Looking for some alternatives such as GLM and Minimax. Very
       | curious about their agentic performance. Like long running tasks
       | with reasoning.
       | 
       | [0]: https://deepwalker.xyz
        
       | p5v wrote:
       | Has anyone used this in earnest with something like OpenCode?
       | Over the past few months I've tested a dozen models that were
       | claimed to be nearly as good Claude Code or Codex, but the
       | overall experience when using them with OpenCode was close to
       | abysmal. Not even a single one was able to do a decent code
       | editing job on a real-world codebase.
        
         | t1amat wrote:
         | With M2, yes - I've used it in Claude Code (e.g. native tool
         | calling), Roo/Cline (e.g. custom tool parsing), etc. It's quite
         | good and for some time the best model to self-host. At 4bit it
         | can fit on 2x RTX 6000 Pro (e.g. ~200GB VRAM) with about 400k
         | context at fp8 kv cache. It's very fast due to low active
         | params, stable at long context, quite capable in any agent
         | harness (its training specialty). M2.1 should be a good bump
         | beyond M2, which was undertrained relative to even much smaller
         | models.
        
       | sillyboi wrote:
       | Internal server error..
        
       | erdemo wrote:
       | The intro video is so cringe as their AI agent name.
        
       ___________________________________________________________________
       (page generated 2025-12-26 23:01 UTC)