Qwen3.6 Plus
AlibabaQwenProprietary
描述
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.
發布日期
2026-04-02
參數規模
—
上下文長度
1.0M
支援模態
image, text, video
能力雷達圖
45
general
43
coding
88
reasoning
59
science估算
60
agents
90
multimodal
Science 在缺少專門科學評測時使用推理能力代理估算。
排行榜排名
基準測試分數 (LLM Stats)
Agents
WideSearch
74.3%自報
MCP Atlas
74.1%自報
TAU3-Bench
70.7%自報
OSWorld-Verified
62.5%自報
TIR-Bench
61.6%自報
Terminal-Bench 2.0
61.6%自報
Claw-Eval
58.7%自報
SWE-Bench Pro
56.6%自報
MCP-Mark
48.2%自報
SkillsBench
45.7%自報
VITA-Bench
44.3%自報
DeepPlanning
41.5%自報
Toolathlon
39.8%自報
NL2Repo
37.9%自報
Biology
GPQA
90.4%自報
Chemistry
SuperGPQA
71.6%自報
Code
SWE-Bench Verified
78.8%自報
SWE-bench Multilingual
73.8%自報
Finance
MMLU-Pro
88.5%自報
MMLU-ProX
84.7%自報
General
MMLU-Redux
94.5%自報
IFEval
94.3%自報
C-Eval
93.3%自報
Global PIQA
89.8%自報
MMMLU
89.5%自報
MAXIFE
88.2%自報
LiveCodeBench v6
87.1%自報
MMMU
86.0%自報
Include
85.1%自報
MMStar
83.3%自報
MMMU-Pro
78.8%自報
IFBench
74.2%自報
SimpleVQA
0.67 / 100自報
LongBench v2
62.0%自報
NOVA-63
57.9%自報
Grounding
RefCOCO-avg
0.94 / 100自報
ScreenSpot Pro
68.2%自報
Healthcare
VideoMMMU
84.0%自報
Language
WMT24++
84.3%自報
Long Context
MLVU
86.7%自報
AA-LCR
68.3%自報
MMLongBench-Doc
0.62 / 100自報
Math
HMMT 2025
96.7%自報
AIME 2026
95.3%自報
HMMT25
94.6%自報
We-Math
89.0%自報
DynaMath
88.0%自報
MathVision
88.0%自報
HMMT Feb 26
87.8%自報
IMO-AnswerBench
83.8%自報
PolyMATH
77.4%自報
Humanity's Last Exam
28.8%自報
Multimodal
V*
96.9%自報
AI2D
94.4%自報
OmniDocBench 1.5
91.2%自報
Video-MME
84.2%自報
CC-OCR
83.4%自報
CharXiv-R
81.5%自報
Reasoning
CountBench
0.98 / 100自報
ERQA
65.7%自報
Spatial Reasoning
RealWorldQA
85.4%自報
Vision
ODinW
51.8%自報
AA 評測指數
Intelligence Index50.0
Coding Index42.9
Tau21.0
Gpqa0.9
Ifbench0.8
Lcr0.7
Terminalbench Hard0.4
Scicode0.4
Hle0.3
LLM Stats 分類評分
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
定價
輸入價格$0.5 / 1M tokens
輸出價格$3 / 1M tokens
混合價格(3:1)$1.125 / 1M tokens
速度
Tokens/秒52.7 tokens/s
首Token延遲1.69s
首回答延遲107.01s
可用提供商
(LS 內部計價單位)| 提供商 | 輸入價格 | 輸出價格 |
|---|---|---|
| Together | 500K | 3.0M |