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

Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

qwen.ai

Post reply on HN
Print view View original

201–210 of 400 posts

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#201

Post by ezekiel68 »

alex7o wrote: post #71

Ok I find it funny that people compare models and are like, opus 4.7 is SOTA and is much better etc, but I have used glm 5.1 (I assume this comes form them training on both opus and codex) for things opus couldn't do and have seen it make better code, haven't tried the qwen max series but I have seen the local 122b model do smarter more correct things based on docs than opus so yes benchmarks are one thing but realit…

Qwen3-Coder produced much better rust code (that utilized rust's x86-64 vectorized extensions) a few months ago than Claude Opus or Google Gemini could. I was calling it from harnesses such as the Zed editor and trae CLI.

I was very impressed.

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#202

Post by slopinthebag »

Kerrick wrote: post #197
Tepix wrote: post #148

Earlier quoted context omitted.

Are you talking about GLM 5.1, DeepSeek V3.2 or Kimi K2.6 (released one hour ago!)? Oh wait, it doesn't apply to those…

Z.ai's Coding Plan with GLM 5.1 (Max) did more than double in price. It was $80 two weeks ago, and now it's $160.

Coding plans are subsidised crap anyways, the real price win is the API pricing which is not.

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#203

Post by ecocentrik »

jxmesth wrote: post #196
ecocentrik wrote: post #188

Earlier quoted context omitted.

When was the last time you used Qwen models? Their 3.5 and 3.6 models are excellent with tool calling.

I gave it a try a few weeks ago tbh, I'll give it another shot tho. I mainly use their Web chats since that's easier to use and previously, qwen, deepseek, kimi, all were unable to output proper docx files or use skills.

Try loading the models up in a coding harness like Claude Code. There's a few docx skills listed on Vercel's skill index.

https://skills.sh/tfriedel/claude-office-skills/docx

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#204

Post by bensyverson »

ecshafer wrote: post #162
bensyverson wrote: post #120

Earlier quoted context omitted.

Allow me to introduce you to Buddhism

Elaborate. Buddhism is going to have the same epistemological issues as anything, since its a human consciousness issue.

> since its a human consciousness issue

I'd encourage you to check it out for yourself. It's certainly possible to be a dogmatic Buddhist, but one of the foundational beliefs of Buddhism is that the type of dogmatic attachment you're describing is avoidable. It's not easy, but that's why you meditate.

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#205

Post by dd8601fn »

seplite wrote: post #27
dd8601fn wrote: post #22

Earlier 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”

Sure, not plus or max. I just use their lesser moe ones locally (that would never come close to massive sota models) all the time.

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#206

Post by sirnicolaz »

alex7o wrote: post #71

Ok I find it funny that people compare models and are like, opus 4.7 is SOTA and is much better etc, but I have used glm 5.1 (I assume this comes form them training on both opus and codex) for things opus couldn't do and have seen it make better code, haven't tried the qwen max series but I have seen the local 122b model do smarter more correct things based on docs than opus so yes benchmarks are one thing but realit…

Consider that SWE benchmarking is mainly done with python code. It tells something

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#207

Post by bensyverson »

svnt wrote: post #166
bensyverson wrote: post #149

Earlier quoted context omitted.

Zen

The Western Zen? In my experience it is downgraded from being a religion to being a system of practice which relieves it of the broader Mahayana cosmology. But I would suggest the dogma is less obvious but still there, often just somewhere else, such as in its own limitations, or in a philosophical container at a higher level such as scientism.

All Zen is about releasing those attachments. Granted it's pretty hard, because if you succeed, you're enlightened.

East, West, Religion, Practice… From a Zen perspective, you're just troubling your mind with binaries and conflict.

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#208

Post by ezekiel68 »

jdw64 wrote: post #129

https://www.alibabacloud.com/help/en/model-studio/context-ca... I’ve also been testing models like Opus, Codex, and Qwen, and Qwen is strong in many coding tasks. However, my main concern is how it behaves in long-running sessions. While Qwen advertises large context windows, in practice the effectiveness of long-context usage seems to depend heavily on its context caching behavior. According to the official document…

TBF, it's certainly best practice, advised by the model providers themselves, to cut sessions short and start new ones.

Anthropic's "Best Practices" doc[0] for Claude Code states, "A clean session with a better prompt almost always outperforms a long session with accumulated corrections."

[0] https://code.claude.com/docs/en/best-practices

Re: Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving

#210

Post by sscaryterry »

jxmesth wrote: post #182
alex7o wrote: post #71

Ok I find it funny that people compare models and are like, opus 4.7 is SOTA and is much better etc, but I have used glm 5.1 (I assume this comes form them training on both opus and codex) for things opus couldn't do and have seen it make better code, haven't tried the qwen max series but I have seen the local 122b model do smarter more correct things based on docs than opus so yes benchmarks are one thing but realit…

The only reason I'm stuck with Claude and Chatgpt is because of their tool calling. They do have some pretty useful features like skills etc. I've tried using qwen and deepseek but they can't even output documents. How are you guys handling documents and excels with these tools? I'd love to switch tbh.

You can use GLM-5.1 with claude code directly, I use ccs, GLM-5.1 setup as plan, but goes via API key.
Post reply on HN