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.
I did notice the same. Both Sol and Claude prefer pushing that typical corpo business/product talk that makes me go crazy.
More specifically it keeps talking like that one colleague who speaks fluent corpo BS and manages to amaze non-tech people by verbose statements that ultimately say nothing or are super vague on details.