Everybody's out here chasing SOTA, meanwhile I'm getting all my coding done with MiniMax M2.5 in multiple parallel sessions for $10/month and never running into limits.
Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
21–30 of 400 posts
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#22With them comparing to Opus 4.5, I find it hard to take some of these in good faith. Opus 4.7 is new, so I don't expect that, but Opus 4.6 has been out for quite some time.
If money is no object, then nothing else is worth considering if it isn't Codex 5.4/Opus 4.7/SOTA. But for many to most people, value Vs. relative quality are huge levers. Even many people on a Claude subscription aren't choosing or able to choose Opus 4.7 because of those cost/usage pressures. Often using Sonnet or an older opus, because of the value Vs. quality curve.
Also us weirdos with local model uses. But your point stands.
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#23With them comparing to Opus 4.5, I find it hard to take some of these in good faith. Opus 4.7 is new, so I don't expect that, but Opus 4.6 has been out for quite some time.
If money is no object, then nothing else is worth considering if it isn't Codex 5.4/Opus 4.7/SOTA. But for many to most people, value Vs. relative quality are huge levers. Even many people on a Claude subscription aren't choosing or able to choose Opus 4.7 because of those cost/usage pressures. Often using Sonnet or an older opus, because of the value Vs. quality curve.
Cost may or may not be a factor in my choice of model, but knowing the capabilities and knowing they will remain consistent, reliable, and available over time is always a dominant consideration. Lately, Anthropic in particular has not been great at that.
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#24Earlier quoted context omitted.
GLM 5.1 is pretty good, probably the best non-US agentic coding model currently available. But both GLM 5.0 and 5.1 have had issues with availability and performance that makes them frustrating to use. Recently GLM 5.1 was also outputting garbage thinking traces for me, but that appears to be fixed now.
Use them via DeepInfra instead of z.ai. No reliability issues. https://deepinfra.com/zai-org/GLM-5.1 Looks like fp4 quantization now though? Last week was showing fp8. Hm..
Deepinfra's implementation of it is not correct. Thinking is not preserved, and they're not responding to my submitted issue about it.
I also regularly experience Deepinfra slow to an absolute crawl - I've actually gotten more consistent performance from Z.ai.
I really liked Deepinfra but something doesn't seem right over there at the moment.
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#25[dead]
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#26I find it odd that none of OpenAI models was used in comparison, but used Z GLM 5.1. Is Z (GLM 5.1) really that good? It is crushing Opus 4.5 in these benchmarks, if that is true, I would have expected to read many articles on HN on how people flocked CC and Codex to use it.
In fact it is appreciated that Qwen is comparing to a peer. I myself and several eng I know are trying GLM. It's legit. Definitely not the same as Codex or Opus, but cheaper and "good enough". I basically ask GLM to solve a program, walk away 10-15 minutes, and the problem is solved.
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#27Earlier quoted context omitted.
If money is no object, then nothing else is worth considering if it isn't Codex 5.4/Opus 4.7/SOTA. But for many to most people, value Vs. relative quality are huge levers. Even many people on a Claude subscription aren't choosing or able to choose Opus 4.7 because of those cost/usage pressures. Often using Sonnet or an older opus, because of the value Vs. quality curve.
Also us weirdos with local model uses. But your point stands.
Unfortunately, like with the release of Qwen3.6-Plus, this model also isn’t released for local use. From the linked article: “Qwen3.6-Max-Preview is the hosted proprietary model available via Alibaba Cloud Model Studio”
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#28I find it odd that none of OpenAI models was used in comparison, but used Z GLM 5.1. Is Z (GLM 5.1) really that good? It is crushing Opus 4.5 in these benchmarks, if that is true, I would have expected to read many articles on HN on how people flocked CC and Codex to use it.
GLM-5 is good, like really good. Especially if you take pricing into consideration. I paid 7$ for 3 months. And I get more usage than CC.
They have difficulty supplying their users with capacity, but in an email they pointed out that they are aware of it. During peak hours, I experience degraded performance. But I am on their lowest tier subscription, so I understand if my demand is not prioritized during those hours.
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#29The way to develop in this space seems to be to give away free stuff, get your name out there, then make everything proprietary. I hope they still continue releasing open weights. The day no one releases open weights is a sad day for humanity. Normal people won’t own their own compute if that ever happens.
Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
#30Earlier quoted context omitted.
Also us weirdos with local model uses. But your point stands.
Unfortunately, like with the release of Qwen3.6-Plus, this model also isn’t released for local use. From the linked article: “Qwen3.6-Max-Preview is the hosted proprietary model available via Alibaba Cloud Model Studio”
The Max series was never available for local use, though. So this is expected.