Qwen3.6-27B and Qwen3.8-27B are great. They are fast and quite accurate for not having to spend too much time thinking or searching, as other models with comparable scores have to.

But Qwen3.8-Flash-Next, which tops a lot of benchmarks in its category, is the most obvious Claude distill ever, and although I don't particularly care about how models get trained, I hate the way it sounds and interacts with me.

• Three warts I'd still fix
• Statements are down to the two things code can't say
• The bug is fixed at the substrate that caused it
• Genuinely good now
• Also worth a conscious nod
• Say the word on 1 and/or 3 and I'll do them

Not to mention Claude's over-the-top comments and git commit messages that make you want to scream.

I wish Alibaba would go back to adopting its own style. Qwen3.6-27B and Qwen3.8-27B sound much better.

Are there any open models that can actually compete with proprietary ones like GPT 5.5 Extended Thinking or Claude Opus 4.7? I am getting really good results with those in their chat interfaces for coding tasks. They sometimes spend 30-45 minutes working on my task and have an internal container they are doing tool calls on, like cloning a repository and compiling their code, and can find online documentation. Their answers are very good and usually correct for very complex tasks requiring specific protocols.

So I would like to know how well we can replicate this using open models since I want more control over how it runs, and privacy. Do any of you hook in agentic capabilities into your local models? How do you do it, and which models give you good results?

Pretend I have unlimited resources (local llama.cpp, sufficient fast storage/memory, and unlimited time to wait for a good response).