2026-09-28 · America/Los_Angeles · 社区动态 · #12

Qwen next 3.8 and 3.8 27b Vs Sonnet 5.5 low and Sonnet 5.5 medium.

Six months ago, a result like this was unthinkable. But now we can say it loud and clear: local models are at the cutting edge, and the gap of just a few months has been confirmed. Personally, I use Qwen-Next 3.8 for complex tasks; today, GPT-Sol-6-High was messing up a project, but Qwen-Next got it back on track. I consider it a reliable benchmark. What’s your take?

热度 47.2 / 100；排名与评分保留该期记录。