Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d266Policy30d65, 14 pendingSources1,013

Qwen3 Max (Reasoning)

AlibabaReleased Nov 3, 2025Deprecated

Score basis

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

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.

Capable2 capabilities
  1. Long Context−17.1%2 of 3
  2. Instruction Following−22.3%2 of 3
Limited2 capabilities
  1. Reasoning−30.2%3 of 6
  2. Coding−32.9%4 of 10
Not rated6 capabilities

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

Price

$1.20input$6.00outputper million tokens

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

Costs more than 74% of 331 priced models · 3:1 input-to-output blend, log scale

Evidence

39results on36benchmarks

  • 11 aggregator
  • 28 vendor-reported

From 2 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputs

As listed by OpenRouter

Research

1313 papers reference Qwen3 Max (Reasoning)

Qwen3 Max (Reasoning) benchmark results

39 results on 36 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

CapableFull long context ranking

17.1% behind the leader2 of 3 ranked benchmarks measured

Show 1 more long context resultHide 1 long context result

Instruction Following

CapableFull instruction following ranking

22.3% behind the leader2 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

Reasoning

LimitedFull reasoning ranking

30.2% behind the leader3 of 6 ranked benchmarks measured

Show 1 more reasoning resultHide 1 reasoning result

Coding

LimitedFull coding ranking

32.9% behind the leader4 of 10 ranked benchmarks measured

Agentic

Not enough dataFull agentic ranking

0 of 7 ranked benchmarks measured

Math

Not enough dataFull math ranking

0 of 5 ranked benchmarks measured

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

More results

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

Show 14 more resultsHide 14 results

Qwen3 Max (Reasoning): common questions

Who makes Qwen3 Max (Reasoning)?

Qwen3 Max (Reasoning) is made by Alibaba.

When was Qwen3 Max (Reasoning) released?

Qwen3 Max (Reasoning) was released on Nov 3, 2025, according to Artificial Analysis.

What is Qwen3 Max (Reasoning) good at?

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

How much does Qwen3 Max (Reasoning) cost?

Qwen3 Max (Reasoning) costs $1.20 per million input tokens and $6.00 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 74% of the 331 priced models we track.

How many benchmarks has Qwen3 Max (Reasoning) been tested on?

We track 39 results for Qwen3 Max (Reasoning) on 36 benchmarks from 2 sources. The latest was recorded on Oct 8, 2026.

Which API features does Qwen3 Max (Reasoning) support?

OpenRouter lists tool calling and structured outputs for Qwen3 Max (Reasoning).

About this record

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

Tracked since
Apr 27, 2026
Newest source mention
Jul 20, 2026

Where the results come from

Verification: 39 scores · 0 independently verified · 11 aggregator-attributed · 28 vendor-reported. How these tiers are assigned

From 2 sources on 2 sites. api.llm-stats.com supplies 28 of them. Bars are coloured by trust tier.

  • api.llm-stats.com28
  • artificialanalysis.ai11

Also known as

qwen3-max-previewqwen3 max thinkingQwen3 MaxQwen3qwen 3Qwen3 Max (Preview)qwen3-max-thinking-previewqwen3 max thinking (preview)