Qwen3.6 Plus
AlibabaQwenProprietary
Описание
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.
Дата выхода
2026-04-02
Параметры
—
Длина контекста
1.0M
Модальности
image, text, video
Радар способностей
27
general
55
coding
88
reasoning
70
science
60
agents
90
multimodal
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| Агентные возможности | 32 | 54.0 | LS |
| Рейтинг кодинга | 159 | 72.0 | AA |
| Общий рейтинг | 79 | 69.0 | AA |
| Математическое мышление | 48 | 84.0 | LB |
| Мультимодальный рейтинг | 5 | 73.0 | LS |
| Рассуждения | 49 | 76.0 | LB |
| Наука | 136 | 68.0 | AA |
Оценки бенчмарков (LLM Stats)
(LLM Stats (zeroeval))Agents
TAU3-Bench
70.7%Сам.
MCP-Mark
48.2%Сам.
VITA-Bench
44.3%Сам.
DeepPlanning
41.5%Сам.
Finance Agent v2
40.8%
Toolathlon
39.8%Сам.
Chat
IFEvalGoogle Research (2023)
94.3%Сам.
Code
Claw-Eval
58.7%Сам.
SkillsBench
45.7%Сам.
NL2Repo
37.9%Сам.
FrontierSWE
22.0%
General
C-Eval
93.3%Сам.
MAXIFE
88.2%Сам.
Include
85.1%Сам.
NOVA-63
57.9%Сам.
Instruction Following
IFBench
74.2%Сам.
Language
MMLU-Redux
94.5%Сам.
MMMLU
89.5%Сам.
MMLU-Pro
88.5%Сам.
MMLU-ProX
84.7%Сам.
WMT24++
84.3%Сам.
Long Context
LongBench v2
62.0%Сам.
Math
HMMT 2025
96.7%Сам.
AIME 2026
95.3%Сам.
HMMT25
94.6%Сам.
We-Math
89.0%Сам.
DynaMath
88.0%Сам.
MathVision
88.0%Сам.
HMMT Feb 26
87.8%Сам.
IMO-AnswerBench
83.8%Сам.
PolyMATH
77.4%Сам.
LiveBench
70.9%
Multimodal
MMMU
86.0%Сам.
Video-MME
84.2%Сам.
VideoMMMU
84.0%Сам.
OSWorld-Verified
62.5%Сам.
TIR-Bench
61.6%Сам.
Reasoning
GPQANYU + Cohere + Anthropic (2023)
90.4%Сам.
Global PIQA
89.8%Сам.
LiveCodeBench v6
87.1%Сам.
CharXiv-R
81.5%Сам.
SWE-Bench Verified
78.8%Сам.
MCP Atlas
74.1%Сам.
SWE-bench Multilingual
73.8%Сам.
SuperGPQA
71.6%Сам.
AA-LCR
68.3%Сам.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
61.6%Сам.
SWE-Bench ProPrinceton NLP (2024)
56.6%Сам.
Humanity's Last Exam
28.8%Сам.
Search
WideSearch
74.3%Сам.
Video
MLVU
86.7%Сам.
Vision
CountBench
0.98 / 100Сам.
V*
96.9%Сам.
AI2D
94.4%Сам.
RefCOCO-avg
0.94 / 100Сам.
OmniDocBench 1.5
91.2%Сам.
RealWorldQA
85.4%Сам.
CC-OCR
83.4%Сам.
MMStar
83.3%Сам.
MMMU-Pro
78.8%Сам.
ScreenSpot Pro
68.2%Сам.
SimpleVQA
0.67 / 100Сам.
ERQA
65.7%Сам.
MMLongBench-Doc
0.62 / 100Сам.
ODinW
51.8%Сам.
Индексы оценки AA
(Artificial Analysis)Tau2(Sierra + U Toronto + Vector Institute (2025))97.7
Gpqa(NYU + Cohere + Anthropic (2023))88.2
Lcr(Artificial Analysis)78.3
Ifbench(Google Research (2023))75.2
Terminalbench V2 161.4
Coding Index(Artificial Analysis)54.5
Terminalbench Hard(Stanford × Laude Institute (2026))43.9
Hle(Center for AI Safety + Scale AI (2025))27.8
Intelligence Index(Artificial Analysis)27.0
Tau Banking20.8
Оценки категорий LLM Stats
(LLM Stats (zeroeval))Chat90
Language90
Biology90
Video90
Instruction Following80
Legal80
Math80
Multimodal80
Physics80
Reasoning80
Spatial Reasoning80
Structured Output80
Frontend Development80
Grounding80
Healthcare80
Chemistry80
Text-to-image80
Vision80
Image To Text70
Long Context70
Search70
Finance70
General70
Economics70
Code60
Tool Calling60
Agents50
Цены
Цена ввода$0.5 / 1M токенов
Цена вывода$3 / 1M токенов
Смешанная цена (3:1)$1.125 / 1M токенов
Цена чтения кэша$0.05 / 1M токенов
Цена записи кэша$0.625 / 1M токенов
Скорость
Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s
Рейтинг цен провайдеров
Рейтинг цен провайдеров
21 провайдеров
Самый дешевый: NovitaСамый дорогой: Ofox
ПровайдерВводВывод
1NovitaСамый дешевый
$0
$0
2Together
$0
$0
3Merge Gateway
$0.276
$1.651
4AIHubMix
$0.28
$1.69
5302.AI
$0.3
$1.8
6CrossModel
$0.32
$1.88
7NanoGPT
$0.325
$1.95
8OpenRouter
$0.325
$1.95
9Kilo Gateway
$0.325
$1.95
10Pioneer
$0.325
$1.95
11AlibabaОсновной
$0.5
$3
12OpenCode Go
$0.5
$3
13Alibaba (China)
$0.5
$3
14ZenMux
$0.5
$3
15OpenCode Zen
$0.5
$3
16Requesty
$0.5
$3
17DevPass (LLM Gateway)
$0.5
$3
18OrcaRouter
$0.5
$3
19LLMTR
$0.5
$3
20EmpirioLabs AI
$0.5
$3
21Ofox
$0.5
$3
Сравнение цен разных API-провайдеров для этой модели.