Home/Models/Qwen3.6 Plus
Alibaba Qwen logo

Qwen3.6 Plus

by Alibaba Qwen · Released Apr 2026

Open SourceMultimodal1M Context
69.8
avg score
Rank #50
Compare
Better than 82% of all models
Context
1.0M tokens (~500 books)
Input $/1M
$0.33
Output $/1M
$1.95
Type
multimodal
License
Open Source
Benchmarks
20 tested
Data updated today
About

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...

Tested on 20 benchmarks with 59.9% average. Top scores: Chatbot Arena Elo — Coding (1461.9%), Chatbot Arena Elo — Overall (1444.2%), OTIS Mock AIME 2024-2025 (90.5%).

Capabilities
coding
63.7
#38 globally
reasoning
72.9
#30 globally
math
52.2
#82 globally
knowledge
54.8
#89 globally
language
66.7
#89 globally
speed
67.6
#32 globally
Benchmark Scores
Compare All
Tested on 20 benchmarks · Ranked across 7 categories
Score Distribution (all 274 models)
0255075100
▲ You are here
LiveBench — Coding

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

78.2
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.

57.9
LiveBench — Agentic Coding

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

55.0
LiveBench — Reasoning

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

75.8
LiveBench — Data Analysis

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

69.9
OTIS Mock AIME 2024-2025

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

90.5
LiveBench — Mathematics

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

83.7
FrontierMath-2025-02-28-Private

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 Problems are unpublished and cannot be memorized.

26.2
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
qwen3-6-plus
Specifications
  • Typemultimodal
  • Context1.0M tokens (~500 books)
  • ReleasedApr 2026
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.003
Available On
Alibaba Qwen logoAlibaba Qwen$0.33
Share & Export
Tweet
Qwen3.6 Plus is an open-source multimodal AI model by Alibaba Qwen, released in April 2026. It has an average benchmark score of 69.8. Context window: 1M tokens.