Qwen3.8 Max

0–100 · higher means more positive community experience, not benchmark performance.

Updated 2026-09-05 14:21 UTC · 2026-08-29 – 2026-09-05 UTC

Community score44.8/10015 comments in 7 days

Community reviews

Selected comments from the last 7 days. The balance of excerpts does not represent the share of positive reviews.

5 selected excerpts

NegativeGeneral text2026-09-04

“Not as good as GLM5.3”

ZhihuzhMachine translated

Show original

不如GLM5.3

NegativeReasoning2026-09-03

“3.8max is like a poor man's version of Kimi k3, planning and knowledge base are acceptable, but execution ability is very mediocre”

ZhihuzhMachine translated

Show original

3.8max像个乞丐版的kimi k3，规划和知识量可以，执行能力很一般

NegativeGeneral text2026-09-03

“Only kept qwen3.8-Max, and it's still limited”

V2EXzhMachine translated

Show original

只留了 qwen3.8-Max ，还限量

NeutralReasoning2026-09-03

“Qwen3.8max still does a bit of score-chasing, but much less than in the Lin p10 period”

ZhihuzhMachine translated

Show original

Qwen3.8max确实还有点刷，但比林p10时期已经收敛太多了

PositiveGeneral text2026-09-02

“After this round of upgrades, Qwen 3.8 Max already has GPT-5.6 Sol-level capabilities”

ZhihuzhMachine translated

Show original

经过这波升级 Qwen 3.8 Max 已经有了 GPT-5.6 Sol 级的能力