NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Qwen3.6 27B
Alibaba Qwen logo

Qwen3.6 27B

by Alibaba Qwen · Released Apr 2026

Open SourceMultimodal
62.2
avg score
Rank #74
Compare
Better than 76% of all models
Context
262K tokens (~131 books)
Input $/1M
$0.32
Output $/1M
$2.70
Type
multimodal
License
Open Source
Benchmarks
18 tested
Data as of
About

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image, and video inputs...

Tested on 18 benchmarks · BenchGecko score 62.2. Top scores: OTIS Mock AIME 2024-2025 (91.1%), GPQA diamond (81.1%), LiveBench — Mathematics (79.9%).

Capabilities
coding
60.9
#43 globally
reasoning
70.4
#42 globally
math
68.7
#52 globally
knowledge
54.9
#92 globally
general
34.7
#107 globally
speed
39.3
#68 globally
language
58.3
#107 globally
Benchmark Scores
Compare All
Tested on 18 benchmarks · Ranked across 7 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
LiveBench — Coding

Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.

71.8·
LiveBench — Agentic Coding

LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.

50.0·
reasoningCompare reasoning →
LiveBench — Data Analysis

Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.

70.4·
LiveBench — Reasoning

Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.

70.3·
mathCompare math →
OTIS Mock AIME 2024-2025

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

91.1·
LiveBench — Mathematics

Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.

79.9·
FrontierMath-Tiers-1-3-v2-Private
35.1·
Quick compare:xAI logovs Grok 4.5vs PaLM 2-SxAI logovs Grok 4.3
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Alibaba Qwen Qwen 3.6
Apr 2026
62.2
$0.32/M in262Kctx18 benchmarks
Apr 2026
42.6-19.6
$0.15/M in(-0.17)262Kctx23 benchmarks
Apr 2026
46.6+4.0
$0.19/M in(+0.04)1.0Mctx(+738K)19 benchmarks
Apr 2026
58.4+11.8
$1.03/M in(+0.84)262Kctx(-738K)13 benchmarks
Apr 2026
62.8+4.4
$0.33/M in(-0.70)1.0Mctx(+738K)25 benchmarks
Apr 2026
$0.00/M in(-0.33)1.0Mctx
Mar 2026
$0.00/M in1.0Mctx
See the full Qwen 3.6 family →
Recently Happened
Qwen3.6 27B pricing increased 19%
Sep 26, 2026
Qwen3.6 27B pricing increased 35%
Sep 23, 2026
Qwen3.6 27B pricing dropped 50%
Sep 5, 2026
Qwen3.6 27B pricing increased 88%
Aug 29, 2026
Qwen3.6 27B pricing dropped 47%
Aug 24, 2026
Qwen3.6 27B pricing increased 100%
Aug 20, 2026
Similar Models
xAI logo
Grok 4.5
xAI
62.4$2.00/1M
PaLM 2-S
Unknown
61.7n/a
xAI logo
Grok 4.3
xAI
61.7$1.25/1M
Links
Info
Alibaba QwenPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Alibaba Qwen
Source Code
GitHubHugging Face
BenchGecko API
qwen3-6-27b
Specifications
  • Typemultimodal
  • Context262K tokens (~131 books)
  • ReleasedApr 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.003
Available On
Alibaba Qwen logoAlibaba Qwen$0.32
Categories
codingreasoningmathknowledgegeneralspeedlanguage
Learn More
context-windowtransformeropen weightstokens
Share & Export
Tweet
Related Models
xAI logoGrok 4.5
62.4
PaLM 2-S
61.7
xAI logoGrok 4.3
61.7
Alibaba Qwen logoQwen3.6 Plus
62.8
Qwen3.6 27B is an open-source multimodal AI model by Alibaba Qwen, released in April 2026. It has an average benchmark score of 62.2. Context window: 262K tokens.

Related Models

Grok 4.5 · xAIPaLM 2-S · UnknownGrok 4.3 · xAIQwen3.6 Plus · Alibaba Qwenphi-3-mini 3.8B · Microsoft

Benchmarks

OTIS Mock AIME 2024-2025GPQA diamondLiveBench — MathematicsLiveBench — CodingLiveBench — Data Analysis

Related Pages

Alibaba Qwen · ProviderAlibaba Qwen · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • Qwen3.6 27B by Alibaba Qwen. BenchGecko score 62.2, rank 74 of 312 scored models (normalized average of public benchmark scores).
  • List price $0.32 input · $2.70 output per 1M tokens (as of 2026-10-05).
  • Sold by 6 providers (as of 2026-10-05): Chutes (fp8) $0.30 in / $2.00 out · SiliconFlow (fp8) $0.30 in / $3.20 out · DeepInfra (fp8) $0.32 in / $3.20 out · Phala $0.32 in / $2.70 out · Venice (fp8) $0.33 in / $3.25 out · and 1 more. Every provider

How to cite · data as of 2026-10-05

Qwen3.6 27B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-6-27b

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