Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

minimaxi.com

Post reply on HN
Print view View original

61–70 of 86 posts

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

#61

Post by azuanrb »

baq wrote: post #53
azuanrb wrote: post #51

Earlier quoted context omitted.

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.

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.

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.

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

#62

Post by WiSaGaN »

andai wrote: post #60
azuanrb wrote: post #51

Earlier quoted context omitted.

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.

Opus is 3x cheaper now. I think it's still not on the $20 plan tho which is sad.

It is now. But the limit on $20 plan is quite low and easy to use up.

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

#63

Post by azuanrb »

andai wrote: post #60
azuanrb wrote: post #51

Earlier quoted context omitted.

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.

Opus is 3x cheaper now. I think it's still not on the $20 plan tho which is sad.

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.

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

#64

Post by m00dy »

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

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

#65

Post by sumedh »

mjburgess wrote: post #54
azuanrb wrote: post #51

Earlier quoted context omitted.

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.

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 A…

> 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?

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

#66

Post by sumedh »

tw1984 wrote: post #31
jimmydoe wrote: post #22

Earlier quoted context omitted.

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.

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.

> in six months AI would be writing 90 percent of code

Are you still writing code by hand?

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

#67

Post by pylotlight »

Alifatisk wrote: post #52
redman25 wrote: post #25

Earlier quoted context omitted.

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 http…

I’d stick to artificial analysis

That has many of its own problems as well.

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

#68

Post by p5v »

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.

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

#69

Post by gcanyon »

martin-t wrote: post #47
gcanyon wrote: post #34

Earlier quoted context omitted.

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.

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.

Maybe :-(

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

#70

Post by t1amat »

p5v wrote: post #68

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.

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.
Post reply on HN