Hacker News Reader

Interestingly, if you adjust the thinking effort, smaller model gets better? At least with the weights this comparison is using.

https://aibenchy.com/compare/qwen-qwen3-8-27b-high/qwen-qwen...

View on HN

Yeah, this was known since 3.8 27b was released, the high version reasons way too much, context gets polluted, so answers get worse, assuming it has to do a deterministic task, not a creative one.

Check other benchmark sites/videos too, they all said Qwen 3.8 27b is better on low than high.

Reply on news.ycombinator.com