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 | #रैंक | स्कोर | स्रोत |
|---|---|---|---|
| Agents & Tools | 44 | 58.0 | LS |
| Code Ranking | 31 | 78.0 | AA |
| General Ranking | 15 | 88.0 | AA |
| Multimodal Ranking | 14 | 87.0 | LS |
| Reasoning | 28 | 82.0 | LS |
| Science | 47 | 73.0 | AA |
बेंचमार्क स्कोर (LLM Stats)
Agents
WideSearch
74.3%स्वयं
MCP Atlas
74.1%स्वयं
TAU3-Bench
70.7%स्वयं
OSWorld-Verified
62.5%स्वयं
TIR-Bench
61.6%स्वयं
Terminal-Bench 2.0
61.6%स्वयं
Claw-Eval
58.7%स्वयं
SWE-Bench Pro
56.6%स्वयं
MCP-Mark
48.2%स्वयं
SkillsBench
45.7%स्वयं
VITA-Bench
44.3%स्वयं
DeepPlanning
41.5%स्वयं
Toolathlon
39.8%स्वयं
NL2Repo
37.9%स्वयं
Biology
GPQA
90.4%स्वयं
Chemistry
SuperGPQA
71.6%स्वयं
Code
SWE-Bench Verified
78.8%स्वयं
SWE-bench Multilingual
73.8%स्वयं
Finance
MMLU-Pro
88.5%स्वयं
MMLU-ProX
84.7%स्वयं
General
MMLU-Redux
94.5%स्वयं
IFEval
94.3%स्वयं
C-Eval
93.3%स्वयं
Global PIQA
89.8%स्वयं
MMMLU
89.5%स्वयं
MAXIFE
88.2%स्वयं
LiveCodeBench v6
87.1%स्वयं
MMMU
86.0%स्वयं
Include
85.1%स्वयं
MMStar
83.3%स्वयं
MMMU-Pro
78.8%स्वयं
IFBench
74.2%स्वयं
SimpleVQA
0.67 / 100स्वयं
LongBench v2
62.0%स्वयं
NOVA-63
57.9%स्वयं
Grounding
RefCOCO-avg
0.94 / 100स्वयं
ScreenSpot Pro
68.2%स्वयं
Healthcare
VideoMMMU
84.0%स्वयं
Language
WMT24++
84.3%स्वयं
Long Context
MLVU
86.7%स्वयं
AA-LCR
68.3%स्वयं
MMLongBench-Doc
0.62 / 100स्वयं
Math
HMMT 2025
96.7%स्वयं
AIME 2026
95.3%स्वयं
HMMT25
94.6%स्वयं
We-Math
89.0%स्वयं
DynaMath
88.0%स्वयं
MathVision
88.0%स्वयं
HMMT Feb 26
87.8%स्वयं
IMO-AnswerBench
83.8%स्वयं
PolyMATH
77.4%स्वयं
Humanity's Last Exam
28.8%स्वयं
Multimodal
V*
96.9%स्वयं
AI2D
94.4%स्वयं
OmniDocBench 1.5
91.2%स्वयं
Video-MME
84.2%स्वयं
CC-OCR
83.4%स्वयं
CharXiv-R
81.5%स्वयं
Reasoning
CountBench
0.98 / 100स्वयं
ERQA
65.7%स्वयं
Spatial Reasoning
RealWorldQA
85.4%स्वयं
Vision
ODinW
51.8%स्वयं
AA मूल्यांकन सूचकांक
Intelligence Index50.0
Coding Index42.9
Tau21.0
Gpqa0.9
Ifbench0.8
Lcr0.7
Terminalbench Hard0.4
Scicode0.4
Hle0.3
LLM Stats श्रेणी स्कोर
Video90
Biology90
Language90
Spatial Reasoning80
Structured Output80
Text-to-image80
Vision80
Chemistry80
Finance80
Frontend Development80
General80
Grounding80
Healthcare80
Instruction Following80
Legal80
Math80
Multimodal80
Physics80
Reasoning80
Code70
Economics70
Image To Text70
Long Context70
Search70
Tool Calling60
Agents60
Coding50
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)| प्रदाता | इनपुट मूल्य | आउटपुट मूल्य |
|---|---|---|
| Together | 500K | 3.0M |