Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d263Policy30d65, 14 pendingSources1,013

Qwen3.7 Max

AlibabaReleased May 19, 2026Current

Score basis

Qwen3.7 Max is strong in factuality; capable in instruction following, long context, reasoning, and coding; and behind the leaders in agentic tasks and math. Too few results yet to rate safety, multimodal tasks, or multilingual tasks.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Strong1 capability
  1. Factuality−8.8%3 of 4
Capable4 capabilities
  1. Instruction Following−12.1%2 of 3
  2. Long Context−13.2%1 of 3
  3. Reasoning−17.2%5 of 6
  4. Coding−19.5%10 of 10
Limited2 capabilities
  1. Agentic−34.9%5 of 7
  2. Math−35.5%3 of 5
Not rated3 capabilities

Too few results yet to rate Safety, Multimodal or Multilingual.

Price

$2.50input$7.50outputper million tokens

From Alibaba's own price page · 4 providers tracked · All prices

Costs more than 82% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

86results on70benchmarks

  • 13 independently verified
  • 19 aggregator
  • 41 vendor-reported
  • 13 cross-referenced

From 11 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

6 papers reference Qwen3.7 Max

Qwen3.7 Max benchmark results

86 results on 70 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Factuality

StrongFull factuality ranking

8.8% behind the leader3 of 4 ranked benchmarks measured

Instruction Following

CapableFull instruction following ranking

12.1% behind the leader2 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

Long Context

CapableFull long context ranking

13.2% behind the leader1 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Reasoning

CapableFull reasoning ranking

17.2% behind the leader5 of 6 ranked benchmarks measured

Show 6 more reasoning resultsHide 6 reasoning results

Coding

CapableFull coding ranking

19.5% behind the leader10 of 10 ranked benchmarks measured

Show 4 more coding resultsHide 4 coding results

Agentic

LimitedFull agentic ranking

34.9% behind the leader5 of 7 ranked benchmarks measured

Show 2 more agentic resultsHide 2 agentic results

Math

LimitedFull math ranking

35.5% behind the leader3 of 5 ranked benchmarks measured

Show 5 more math resultsHide 5 math results

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 33 more resultsHide 33 results

Qwen3.7 Max: common questions

Who makes Qwen3.7 Max?

Qwen3.7 Max is made by Alibaba.

When was Qwen3.7 Max released?

Qwen3.7 Max was released on May 19, 2026, according to Artificial Analysis.

What is Qwen3.7 Max good at?

Qwen3.7 Max is strong in factuality; capable in instruction following, long context, reasoning, and coding; and behind the leaders in agentic tasks and math. Too few results yet to rate safety, multimodal tasks, or multilingual tasks.

How much does Qwen3.7 Max cost?

Qwen3.7 Max costs $2.50 per million input tokens and $7.50 per million output tokens, according to Alibaba's own price page. We track its price at 4 providers. At a mix of three input tokens to one output token, it costs more than 82% of the 331 priced models we track.

How many benchmarks has Qwen3.7 Max been tested on?

We track 86 results for Qwen3.7 Max on 70 benchmarks from 11 sources, 13 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does Qwen3.7 Max support?

OpenRouter lists tool calling, structured outputs, and reasoning for Qwen3.7 Max.

About this record

Where Qwen3.7 Max's numbers come from, and every name it appears under.

Tracked since
May 20, 2026
Newest source mention
Aug 31, 2026

Where the results come from

Verification: 86 scores · 13 independently verified · 19 aggregator-attributed · 13 vendor cross-reference · 41 vendor-reported. How these tiers are assigned

From 11 sources on 8 sites. api.llm-stats.com supplies 28 of them; the 13 independently verified results come from 5 sites. Bars are coloured by trust tier.

  • api.llm-stats.com28
  • huggingface.co26
  • artificialanalysis.ai19
  • livebench.ai7
  • epoch.ai3
  • datasets-server.huggingface.co1
  • lmarena.ai1
  • simple-bench.com1

Also known as

qwen 3.7 maxqwen3-7-maxqwen3.7-max-20260517qwen3.7-max-previewquen 3.7 max