Alibaba

Qwen3.6 Max

Name: Alibaba Qwen3.6 Max
Author: Alibaba

Compare

2026-04-27

Compare

Qwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total parameters. It is optimized for agentic coding, tool use, and complex reasoning tasks.

Reasoning|Proprietary Model

Knowledge Cutoff

Unknown

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory

262KIN66KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words

$1.04IN$6.24OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

Calculate Cost

Source:Official Docs

AI Performance Evaluation

Arena Overall Score

1457

±9

As of 2026-05-01

Overall Rank

No.31

3,943 Votes

Arena by Ability

Hard Prompts

1478±12No.33

Expert Knowledge

1485±29No.30

Instruction Following

1449±16No.32

Conversation Memory

1469±24No.31

Creative

1432±25No.32

Coding

1498±18No.41

Math

1488±32No.9

Arena by Occupation

Creative Writing

1453±20No.20

Social Sciences

1494±22No.9

Media

1432±22No.32

Business

1448±21No.39

Healthcare

1486±35No.23

Legal

1462±35No.36

Software

1489±14No.40

Mathematics

1511±35No.7

Source:Arena Intelligence

Overall

AA Intelligence Index

52%↑13%

Reasoning & Math

GPQA Diamond

89%↑7%

HLE

29%↑10%

Coding

AA Coding Index

45%↑8%

TAU2

96%↑17%

TerminalBench

44%↑10%

SciCode

47%↑4%

Language & Instructions

IFBench

77%↑18%

AA-LCR

70%↑7%

Output Speed

Standard Mode

35tok/s↓41

First Output 59.66s

Source:Artificial Analysis

Alibaba