Alibaba

Qwen3.7 Max

Benchmarks, price, context and versions

Also searched as

Qwen3.7-Max, qwen3.7 max huggingface, qwen3.7 max parameters, qwen3.7 max size

Direct answer: Qwen3.7 Max is a model from Alibaba. 90.9% on GPQA Diamond, per Epoch AI. On OpenRouter, US$ 1.48 per 1 million input tokens and US$ 4.42 per 1 million output tokens.

✓ Good for

  • technical reasoning on science topics (#37 of 198 on GPQA Diamond)
  • calculation and problems with an exact answer (#43 of 186 on OTIS Mock AIME)
  • fixing bugs in real code (#7 of 32 on SWE-bench Verified)
  • technical reasoning as the model appears through the API (#31 of 135 on GPQA Diamond (OpenRouter))
  • very long documents or code (a window of 1 million tokens or more, according to OpenRouter)

✕ Not the best for

  • agents that follow rules and use tools (#79 of 131 on τ-bench Verified (airline))

This block follows a rule of this section, using source data: if the model is in the top 25% of the metric, the item goes under "Good for"; if it is in the bottom half, it goes under "Not the best for". The middle band appears in neither. Price and context use OpenRouter; scores use Epoch AI or OpenRouter Benchmarks, in the latest version we checked.

Benchmarks

GPQA Diamond

?what it is
90.9%

highest score on this metric 96.4%

37º / 198 · Epoch AI, latest version we checked

OTIS Mock AIME

?
95.6%

highest score on this metric 100%

43º / 186 · Epoch AI, latest version we checked

FrontierMath (tiers 1 to 3)

?
64.6%

highest score on this metric 95.1%

39º / 86 · Epoch AI, latest version we checked

SimpleQA Verified

?
55.8%

highest score on this metric 94%

24º / 87 · Epoch AI, latest version we checked

SWE-bench Verified

?
77.3%

highest score on this metric 83.5%

7º / 32 · Epoch AI, latest version we checked

GPQA Diamond (OpenRouter)

?
90.9%

highest score on this metric 96.5%

31º / 135 · OpenRouter Benchmarks, latest version we checked

τ-bench Verified (airline)

?
72%

highest score on this metric 82%

79º / 131 · OpenRouter Benchmarks, latest version we checked

Key specs

Origin
China
Family
Qwen Max provisional data
Weights?
closed
License
no data
Input US$/1M?
US$ 1.48
Output US$/1M
US$ 4.42
Context?
1,000,000 tokens
Parameters
no data
Input
text
OpenRouter usage?
no data
Downloads (30 days)?
no data
Use cases provisional data
Text Agents Code
Dates in sources
  • 2026, published, per Epoch AI
  • 2026, listed on OpenRouter

Version history

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch.

FAQ

How much does Qwen3.7 Max cost?

On OpenRouter, US$ 1.48 per 1 million input tokens and US$ 4.42 per 1 million output tokens.

Is Qwen3.7 Max open source?

No. It is available through API only.

What is Qwen3.7 Max's GPQA Diamond score?

90.9% on GPQA Diamond, per Epoch AI.

What is Qwen3.7 Max?

Qwen3.7 Max is a model from Alibaba, with closed weights, used for text, agents, code.

What is the context window of Qwen3.7 Max?

1,000,000 tokens, per OpenRouter.

Is Qwen3.7 Max good for coding?

It scores 77.3% on SWE-bench Verified, per Epoch AI.

Who made Qwen3.7 Max?

It was made by Alibaba, a lab from China.

provisional data Questions ordered by what shows up in public Google search suggestions (no volume). Answers use source data only.

Models from Alibaba

See lab

Sources

  • Epoch AI, CC BY 4.0, latest version we checked.
  • OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
  • OpenRouter Benchmarks, CC BY 4.0, latest version we checked.

Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.