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.
发布日期
2026-04-02
参数规模
—
上下文长度
1.0M
支持模态
image, text, video
能力雷达图
38
general
52
coding
88
reasoning
59
science
60
agents
90
multimodal
排行榜排名
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
WideSearch
74.3%自报
MCP Atlas
74.1%自报
TAU3-Bench
70.7%自报
OSWorld-Verified
62.5%自报
TIR-Bench
61.6%自报
Terminal-Bench 2.0Stanford × Laude Institute (2026)
61.6%自报
Claw-Eval
58.7%自报
SWE-Bench ProPrinceton NLP (2024)
56.6%自报
MCP-Mark
48.2%自报
SkillsBench
45.7%自报
VITA-Bench
44.3%自报
DeepPlanning
41.5%自报
Finance Agent v2
40.8%
Toolathlon
39.8%自报
NL2Repo
37.9%自报
FrontierSWE
22.0%
Biology
GPQANYU + Cohere + Anthropic (2023)
90.4%自报
Chemistry
SuperGPQA
71.6%自报
Code
SWE-Bench Verified
78.8%自报
SWE-bench Multilingual
73.8%自报
Finance
MMLU-Pro
88.5%自报
MMLU-ProX
84.7%自报
General
MMLU-Redux
94.5%自报
IFEvalGoogle Research (2023)
94.3%自报
C-Eval
93.3%自报
Global PIQA
89.8%自报
MMMLU
89.5%自报
MAXIFE
88.2%自报
LiveCodeBench v6
87.1%自报
MMMU
86.0%自报
Include
85.1%自报
MMStar
83.3%自报
MMMU-Pro
78.8%自报
IFBench
74.2%自报
LiveBench
70.9%
SimpleVQA
0.67 / 100自报
LongBench v2
62.0%自报
NOVA-63
57.9%自报
Grounding
RefCOCO-avg
0.94 / 100自报
ScreenSpot Pro
68.2%自报
Healthcare
VideoMMMU
84.0%自报
Language
WMT24++
84.3%自报
Long Context
MLVU
86.7%自报
AA-LCR
68.3%自报
MMLongBench-Doc
0.62 / 100自报
Math
HMMT 2025
96.7%自报
AIME 2026
95.3%自报
HMMT25
94.6%自报
We-Math
89.0%自报
DynaMath
88.0%自报
MathVision
88.0%自报
HMMT Feb 26
87.8%自报
IMO-AnswerBench
83.8%自报
PolyMATH
77.4%自报
Humanity's Last Exam
28.8%自报
Multimodal
V*
96.9%自报
AI2D
94.4%自报
OmniDocBench 1.5
91.2%自报
Video-MME
84.2%自报
CC-OCR
83.4%自报
CharXiv-R
81.5%自报
Reasoning
CountBench
0.98 / 100自报
ERQA
65.7%自报
Spatial Reasoning
RealWorldQA
85.4%自报
Vision
ODinW
51.8%自报
AA 评测指数
(Artificial Analysis)Coding Index(Artificial Analysis)54.5
Intelligence Index(Artificial Analysis)40.5
Tau2(Sierra + U Toronto + Vector Institute (2025))1.0
Gpqa(NYU + Cohere + Anthropic (2023))0.9
Ifbench(Google Research (2023))0.8
Lcr(Artificial Analysis)0.7
Terminalbench V2 10.6
Terminalbench Hard(Stanford × Laude Institute (2026))0.4
Scicode(UIUC + Argonne National Lab (2024))0.4
Hle(Center for AI Safety + Scale AI (2025))0.3
Tau Banking0.2
LLM Stats 分类评分
(LLM Stats (zeroeval))Language90
Biology90
Video90
Legal80
Math80
Multimodal80
Physics80
Reasoning80
Spatial Reasoning80
Structured Output80
Instruction Following80
Frontend Development80
Grounding80
Healthcare80
Chemistry80
Text-to-image80
Vision80
Long Context70
Search70
Image To Text70
Finance70
General70
Economics70
Code60
Tool Calling60
Agents50
定价
输入价格$0.5 / 1M tokens
输出价格$3 / 1M tokens
混合价格(3:1)$1.125 / 1M tokens
缓存读取价格$0.05 / 1M tokens
缓存写入价格$0.625 / 1M tokens
速度
Tokens/秒0.0
首Token延迟0.00s
首回答延迟0.00s
供应商价格排行
供应商价格排行
17 个供应商
最便宜: Together最贵: Charm Hyper
供应商输入输出
1Together最便宜
$0
$0
2Novita
$0
$0
3Merge Gateway
$0.276
$1.651
4AIHubMix
$0.28
$1.69
5CrossModel
$0.32
$1.88
6OpenRouter
$0.325
$1.95
7Kilo Gateway
$0.325
$1.95
8Pioneer
$0.325
$1.95
9Alibaba主要
$0.5
$3
10OpenCode Go
$0.5
$3
11Alibaba (China)
$0.5
$3
12ZenMux
$0.5
$3
13OpenCode Zen
$0.5
$3
14LLM Gateway
$0.5
$3
15OrcaRouter
$0.5
$3
16EmpirioLabs AI
$0.5
$3
17Charm Hyper
$2
$6
比较该模型在不同 API 供应商之间的定价。