Skip to content
Back to the index
22FrontierProvisional score

Qwen 3.7-Max

Qwen 3.7-Max

The stable closed Qwen: strong, multilingual, and a generation more settled than the preview above it.

Updated

Qwen 3.7-Max preview

The read

3.7-Max is the production flagship of the closed Qwen line and the one to build against if you want Alibaba's quality without preview-grade churn. It reasons close to the frontier, takes a very long context, and is one of the few models here genuinely strong in Chinese, English and a long tail of other languages at once. Closed weights, and priced accordingly against its open siblings.

Where it shines

  • Genuinely strong across Chinese, English and a long tail of languages
  • Settled production behaviour rather than a moving preview
  • Long context at a mid-tier price

Worth knowing first

  • Closed weights, so none of the open Qwen advantages apply
  • Costs many times more than the open Qwen releases that trail it narrowly

Index score

81.0

Provisional. This score is read from the product's public capability, not from the one-prompt rebuild the fully reviewed entries went through, so treat it as a placing rather than a verdict.

Craft84
Speed78
Control76
Value78
Rank
22 of 53
Builds
LLMs
Category
Frontier
Output
Text, code and images in, text out
Pricing
Paid only
Best for
Production multilingual work that needs a settled API

Scores are our own editorial judgement, weighted craft 55, speed 10, control 15 and value 20.