Qwen

Qwen3.6 Plus

by Qwentext+image+video->text1 endpoint
Neura Intelligence Index
66.0/ 100
Rank
#111
Confidence
high
Benchmarks
11(28% coverage)

Overview

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...

Capabilities

Text generation
Image understanding
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
TextImageVideo
Output
Text

Technical Specifications

Context Window
1M tokens
Max Output
65.5K tokens
Tokenizer
Qwen3
Uptime (24h)
10000.0%
Country
🇨🇳CN
Release Date
March 31, 20265mo

Supported Parameters

frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

general

BenchmarkScoreSource
MMMLU
89.5
verified

coding

BenchmarkScoreSource
SWE-bench Verified
78.8
verified
SWE-Bench Pro
56.6
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
90.4
verified
Humanity's Last Exam
28.8
verified

multimodal

BenchmarkScoreSource
MMMU
86
verified
CharXiv Reasoning
81.5
verified
MMMU-Pro
78.8
verified
ScreenSpot Pro
68.2
verified

agent

BenchmarkScoreSource
MCP Atlas
74.1
verified
Toolathlon
39.8
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.33
Output$1.95
Cache write$0.41
Added
April 2, 2026
Last synced 9/18/2026