Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models739Deals30d256Policy30d64, 14 pendingSources1,010

Qwen3.6 Max Preview

AlibabaReleased Apr 20, 2026Deprecated

Score basis

Qwen3.6 Max Preview is strong in long context, capable in factuality and instruction following, and behind the leaders in reasoning and agentic tasks. Too few results yet to rate coding, safety, math, 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. Long Context−9.8%1 of 3
Capable2 capabilities
  1. Factuality−12.1%3 of 4
  2. Instruction Following−22.6%1 of 3
Limited2 capabilities
  1. Reasoning−25.0%4 of 6
  2. Agentic−33.8%1 of 7
Not rated5 capabilities

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

Price

$1.30input$7.80outputper million tokens

From Alibaba's own price page · 3 providers tracked · All prices

Costs more than 75% of 329 priced models · 3:1 input-to-output blend, log scale

Evidence

20results on20benchmarks

  • 5 independently verified
  • 15 aggregator

From 6 sources · latest Oct 7, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Qwen3.6 Max Preview benchmark results

20 results on 20 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

StrongFull long context ranking

9.8% behind the leader1 of 3 ranked benchmarks measured

Factuality

CapableFull factuality ranking

12.1% behind the leader3 of 4 ranked benchmarks measured

Instruction Following

CapableFull instruction following ranking

22.6% behind the leader1 of 3 ranked benchmarks measured

Reasoning

LimitedFull reasoning ranking

25.0% behind the leader4 of 6 ranked benchmarks measured

Agentic

LimitedFull agentic ranking

33.8% behind the leader1 of 7 ranked benchmarks measured

Coding

Not enough dataFull coding ranking

0 of 10 ranked benchmarks measured

More results

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

Show 1 more resultHide 1 result

Qwen3.6 Max Preview: common questions

Who makes Qwen3.6 Max Preview?

Qwen3.6 Max Preview is made by Alibaba.

When was Qwen3.6 Max Preview released?

Qwen3.6 Max Preview was released on Apr 20, 2026, according to Artificial Analysis.

What is Qwen3.6 Max Preview good at?

Qwen3.6 Max Preview is strong in long context, capable in factuality and instruction following, and behind the leaders in reasoning and agentic tasks. Too few results yet to rate coding, safety, math, multimodal tasks, or multilingual tasks.

How much does Qwen3.6 Max Preview cost?

Qwen3.6 Max Preview costs $1.30 per million input tokens and $7.80 per million output tokens, according to Alibaba's own price page. We track its price at 3 providers. At a mix of three input tokens to one output token, it costs more than 75% of the 329 priced models we track.

How many benchmarks has Qwen3.6 Max Preview been tested on?

We track 20 results for Qwen3.6 Max Preview on 20 benchmarks from 6 sources, 5 of them independently verified. The latest was recorded on Oct 7, 2026.

Which API features does Qwen3.6 Max Preview support?

OpenRouter lists tool calling, structured outputs, and reasoning for Qwen3.6 Max Preview.

About this record

Where Qwen3.6 Max Preview's numbers come from, and every name it appears under.

Tracked since
Apr 27, 2026
Newest source mention
May 21, 2026

Where the results come from

Verification: 20 scores · 5 independently verified · 15 aggregator-attributed. How these tiers are assigned

From 6 sources on 5 sites. Artificial Analysis supplies 15 of them; the 5 independently verified results come from 4 sites. Bars are coloured by trust tier.

  • artificialanalysis.ai15
  • epoch.ai2
  • datasets-server.huggingface.co1
  • lmarena.ai1
  • simple-bench.com1

Also known as

qwen 3.6 max (preview)qwen 3.6 max previewqwen3-6-max