मुख्य सामग्री पर जाएं

Qwen3.6 Plus

AlibabaQwenProprietary

विवरण

Qwen3.6 Plus is Alibaba's next-generation flagship model featuring a 1 million token native context window, up to 65,536 output tokens, and always-on chain-of-thought reasoning. It uses a next-generation hybrid architecture optimized for efficiency and scalability. It leads on Terminal-Bench 2.0 agentic coding (61.6), surpassing Claude 4.5 Opus, and achieves strong results on document understanding (OmniDocBench 91.2) and multimodal reasoning (MMMU 86.0). Compared to Qwen 3.5, it is significantly more decisive in reasoning, using fewer tokens on straightforward tasks with better agent stability.

रिलीज़ तिथि
2026-04-02
पैरामीटर
संदर्भ लंबाई
1.0M
मोडैलिटीज़
image, text, video

क्षमता रडार

45
general
43
coding
88
reasoning
59
scienceअनुमानित
60
agents
90
multimodal

समर्पित विज्ञान बेंचमार्क उपलब्ध न होने पर Science तर्क प्रॉक्सी का उपयोग करके अनुमान लगाता है।

रैंकिंग

डोमेन#रैंकस्कोरस्रोत
Agents & Tools44
58.0
LS
Code Ranking31
78.0
AA
General Ranking15
88.0
AA
Multimodal Ranking14
87.0
LS
Reasoning28
82.0
LS
Science47
73.0
AA

बेंचमार्क स्कोर (LLM Stats)

Agents

WideSearch74.3%स्वयं
MCP Atlas74.1%स्वयं
TAU3-Bench70.7%स्वयं
OSWorld-Verified62.5%स्वयं
TIR-Bench61.6%स्वयं
Terminal-Bench 2.061.6%स्वयं
Claw-Eval58.7%स्वयं
SWE-Bench Pro56.6%स्वयं
MCP-Mark48.2%स्वयं
SkillsBench45.7%स्वयं
VITA-Bench44.3%स्वयं
DeepPlanning41.5%स्वयं
Toolathlon39.8%स्वयं
NL2Repo37.9%स्वयं

Biology

GPQA90.4%स्वयं

Chemistry

SuperGPQA71.6%स्वयं

Code

SWE-Bench Verified78.8%स्वयं
SWE-bench Multilingual73.8%स्वयं

Finance

MMLU-Pro88.5%स्वयं
MMLU-ProX84.7%स्वयं

General

MMLU-Redux94.5%स्वयं
IFEval94.3%स्वयं
C-Eval93.3%स्वयं
Global PIQA89.8%स्वयं
MMMLU89.5%स्वयं
MAXIFE88.2%स्वयं
LiveCodeBench v687.1%स्वयं
MMMU86.0%स्वयं
Include85.1%स्वयं
MMStar83.3%स्वयं
MMMU-Pro78.8%स्वयं
IFBench74.2%स्वयं
SimpleVQA0.67 / 100स्वयं
LongBench v262.0%स्वयं
NOVA-6357.9%स्वयं

Grounding

RefCOCO-avg0.94 / 100स्वयं
ScreenSpot Pro68.2%स्वयं

Healthcare

VideoMMMU84.0%स्वयं

Language

WMT24++84.3%स्वयं

Long Context

MLVU86.7%स्वयं
AA-LCR68.3%स्वयं
MMLongBench-Doc0.62 / 100स्वयं

Math

HMMT 202596.7%स्वयं
AIME 202695.3%स्वयं
HMMT2594.6%स्वयं
We-Math89.0%स्वयं
DynaMath88.0%स्वयं
MathVision88.0%स्वयं
HMMT Feb 2687.8%स्वयं
IMO-AnswerBench83.8%स्वयं
PolyMATH77.4%स्वयं
Humanity's Last Exam28.8%स्वयं

Multimodal

V*96.9%स्वयं
AI2D94.4%स्वयं
OmniDocBench 1.591.2%स्वयं
Video-MME84.2%स्वयं
CC-OCR83.4%स्वयं
CharXiv-R81.5%स्वयं

Reasoning

CountBench0.98 / 100स्वयं
ERQA65.7%स्वयं

Spatial Reasoning

RealWorldQA85.4%स्वयं

Vision

ODinW51.8%स्वयं

AA मूल्यांकन सूचकांक

Intelligence Index
50.0
Coding Index
42.9
Tau2
1.0
Gpqa
0.9
Ifbench
0.8
Lcr
0.7
Terminalbench Hard
0.4
Scicode
0.4
Hle
0.3

LLM Stats श्रेणी स्कोर

Video
90
Biology
90
Language
90
Spatial Reasoning
80
Structured Output
80
Text-to-image
80
Vision
80
Chemistry
80
Finance
80
Frontend Development
80
General
80
Grounding
80
Healthcare
80
Instruction Following
80
Legal
80
Math
80
Multimodal
80
Physics
80
Reasoning
80
Code
70
Economics
70
Image To Text
70
Long Context
70
Search
70
Tool Calling
60
Agents
60
Coding
50

मूल्य निर्धारण

इनपुट मूल्य$0.5 / 1M tokens
आउटपुट मूल्य$3 / 1M tokens
मिश्रित मूल्य (3:1)$1.125 / 1M tokens

गति

टोकन/सेकंड52.7 tokens/s
पहले टोकन में देरी1.69s
पहले उत्तर में देरी107.01s

उपलब्ध प्रदाता

(LS आंतरिक इकाइयाँ)
प्रदाताइनपुट मूल्यआउटपुट मूल्य
Together500K3.0M

बाहरी लिंक