QwenSWEBench

Qwen in-house software-engineering benchmark run in Claude Code (avg@3, 8-hour limit). Task and scoring details unpublished.

Lab-created in-house eval (Alibaba Qwen).

Made by Alibaba Qwen Fixing real repositories Tasks kept private Last in a launch post Aug 2026 Last model added Aug 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
Answers: Code A program or patch run against tests.

Models scored in lab cards

Launch posts list it, from 1 lab

Qwen 3.8 Max leads with 80.7%

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

#	Model	Score	Setting	Date	Source
1	Qwen 3.8 Max	80.7%		Aug 2026	Model card
2	Qwen 3.8 27B	79%		Aug 2026	Model card

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Qwen

Date	Launch post	Score	As the post writes it
14 Aug 2026	Qwen 3.8 27B	79	Software engineering QwenSWEBench (avg@3)
3 Aug 2026	Qwen 3.8 Max	80.7	QwenSWEBench