How much does Qwen3.6 Max Preview cost?

Qwen3.6 Max Preview costs $1.03 per million input tokens and $6.16 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.008 per message.

What benchmarks has Qwen3.6 Max Preview been tested on?

Qwen3.6 Max Preview has been evaluated on 13 benchmarks. Top scores: Chatbot Arena Elo — Coding: 1481.5, Chatbot Arena Elo — Overall: 1460.3, OTIS Mock AIME 2024-2025: 91.1.

Is Qwen3.6 Max Preview open source?

Yes, Qwen3.6 Max Preview is open source.

How does Qwen3.6 Max Preview compare to GPT-5.2?

Qwen3.6 Max Preview has an average score of 58.4 while GPT-5.2 scores 58.4. GPT-5.2 slightly outperforms Qwen3.6 Max Preview overall. Qwen3.6 Max Preview costs $1.03/1M input vs GPT-5.2 at $1.75/1M input. See full comparison →

Home/Models/Qwen3.6 Max Preview

Qwen3.6 Max Preview

Name: Qwen3.6 Max Preview · benchmarks, pricing and providers
Creator: BenchGecko

by Alibaba Qwen · Released Apr 2026

Open SourcePreview

58.4

avg score

Rank #99

Compare

Better than 68% of all models

Context

262K tokens (~131 books)

Input $/1M

$1.03

Output $/1M

$6.16

Type

text

License

Open Source

Benchmarks

13 tested

Data as of 2026-10-05

About

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...

Tested on 13 benchmarks · BenchGecko score 58.4. Top scores: Chatbot Arena Elo — Coding (1481.5%), Chatbot Arena Elo — Overall (1460.3%), OTIS Mock AIME 2024-2025 (91.1%).

Looking for similar performance at lower cost?
DeepSeek V4.1 Flash scores 58.7 (101% as good) at $0.15/1M input · 85% cheaper

Capabilities

coding

76.7

#10 globally

reasoning

55.6

#70 globally

math

46.2

#135 globally

knowledge

50.3

#127 globally

general

46.5

#44 globally

Benchmark Scores

Compare All

Tested on 13 benchmarks · Ranked across 6 categories

Score Distribution (all 312 models)

0255075100

▲ You are here

codingCompare coding →

SWE-Bench verified

Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.

76.7·

reasoningCompare reasoning →

SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

55.6·

mathCompare math →

OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

91.1·

FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

40.5·

FrontierMath-Tier-4-2025-07-01-Private

Hardest tier of FrontierMath. Problems at the frontier of human mathematical ability, many unsolved by most mathematicians.

6.9·

Quick compare:

vs GPT-5.2

vs GPT-4o (2024-05-13)

vs Kimi K2 Thinking

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Model Family · Alibaba Qwen Qwen 3.6

Qwen3.6 27BApr 2026

62.2

$0.32/M in262Kctx18 benchmarks

Qwen3.6 35B A3BApr 2026

42.6-19.6

$0.15/M in(-0.17)262Kctx23 benchmarks

Qwen3.6 FlashApr 2026

46.6+4.0

$0.19/M in(+0.04)1.0Mctx(+738K)19 benchmarks

Qwen3.6 Max PreviewApr 2026

58.4+11.8

$1.03/M in(+0.84)262Kctx(-738K)13 benchmarks

Qwen3.6 PlusApr 2026

62.8+4.4

$0.33/M in(-0.70)1.0Mctx(+738K)25 benchmarks

Qwen3.6 Plus (free)Apr 2026

$0.00/M in(-0.33)1.0Mctx

Qwen3.6 Plus Preview (free)Mar 2026

$0.00/M in1.0Mctx

See the full Qwen 3.6 family →

Recently Happened

Qwen3.6 Max Preview pricing dropped 20%

Apr 29, 2026

Qwen3.6 Max Preview added

Apr 27, 2026

Similar Models

Links

Info

Alibaba Qwen Pricing explorer Developers · API

Research

Documentation

Community

Source Code

BenchGecko API

qwen3-6-max-preview

Specifications

Typetext
Context262K tokens (~131 books)
ReleasedApr 2026
LicenseOpen Source
Statuspreview
Cost / Message~$0.008

Available On

Alibaba Qwen$1.03

Frequently Asked Questions

Qwen3.6 Max Preview is an open-source text AI model by Alibaba Qwen, released in April 2026. It has an average benchmark score of 58.4. Context window: 262K tokens.

Benchmarks

Chatbot Arena Elo — Coding Chatbot Arena Elo — Overall OTIS Mock AIME 2024-2025 GPQA diamond Dtbench

Alibaba Qwen · Provider Alibaba Qwen · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

Key facts · as of 2026-10-05

Qwen3.6 Max Preview by Alibaba Qwen. BenchGecko score 58.4, rank 99 of 312 scored models (normalized average of public benchmark scores).
List price $1.03 input · $6.16 output per 1M tokens (as of 2026-10-05).
Sold by 1 provider (as of 2026-10-05): Alibaba $1.03 in / $6.16 out.

How to cite · data as of 2026-10-05

Qwen3.6 Max Preview · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-6-max-preview

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP

Qwen3.6 Max Preview

Frequently Asked Questions

Related Models

Benchmarks

Related Pages

Key facts · as of 2026-10-05

How to cite · data as of 2026-10-05