Qwen3 Max Thinking
AlibabaQwenProprietary
Описание
The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques
Дата выхода
2026-01-26
Параметры
1.0T
Длина контекста
262K
Модальности
text
Радар способностей
23
general
50
coding
86
reasoning
68
science
40
agents
0
multimodal
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| Агентные возможности | 78 | 41.0 | LS |
| Рейтинг кодинга | 230 | 61.0 | AA |
| Общий рейтинг | 153 | 59.0 | AA |
| Наука | 140 | 67.0 | AA |
Оценки бенчмарков (LLM Stats)
(LLM Stats (zeroeval))Agents
VITA-Bench
40.9%Сам.
MCP-Mark
33.5%Сам.
DeepPlanning
28.7%Сам.
Toolathlon
18.8%Сам.
Chat
IFEvalGoogle Research (2023)
93.4%Сам.
Multi-Challenge
63.3%Сам.
Code
SecCodeBench
57.5%Сам.
General
C-Eval
93.7%Сам.
MAXIFE
84.0%Сам.
NOVA-63
54.2%Сам.
Instruction Following
IFBench
70.9%Сам.
Knowledge
HLE-Verified
37.6%Сам.
Language
MMLU-Redux
92.8%Сам.
MMLU-Pro
85.7%Сам.
MMMLU
84.4%Сам.
WMT24++
77.6%Сам.
Long Context
LongBench v2
60.6%Сам.
Math
AIME 2026
93.3%Сам.
IMO-AnswerBench
83.9%Сам.
Reasoning
GPQANYU + Cohere + Anthropic (2023)
87.4%Сам.
Global PIQA
86.0%Сам.
LiveCodeBench v6
85.9%Сам.
SWE-Bench Verified
75.3%Сам.
AA-LCR
68.7%Сам.
SuperGPQA
67.3%Сам.
SWE-bench Multilingual
66.7%Сам.
BrowseComp-zh
60.9%Сам.
BrowseCompOpenAI (2025)
53.9%Сам.
Humanity's Last Exam (with tools, text-only)
49.8%Сам.
Seal-0
46.9%Сам.
Humanity's Last Exam (no tools, text-only)
30.2%Сам.
Terminal-Bench 2.0Stanford × Laude Institute (2026)
22.5%Сам.
Search
WideSearch
57.9%Сам.
Tool Calling
BFCL-V4
67.7%Сам.
Индексы оценки AA
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))86.1
Tau2(Sierra + U Toronto + Vector Institute (2025))83.6
Lcr(Artificial Analysis)74.3
Ifbench(Google Research (2023))70.7
Hle(Center for AI Safety + Scale AI (2025))28.0
Terminalbench Hard(Stanford × Laude Institute (2026))24.2
Intelligence Index(Artificial Analysis)21.3
Оценки категорий LLM Stats
(LLM Stats (zeroeval))Language90
Biology90
Chat80
Instruction Following80
Legal80
Physics80
Structured Output80
Finance80
Frontend Development80
Healthcare80
Chemistry80
Math70
Economics70
Long Context60
Reasoning60
General60
Communication60
Search50
Code50
Knowledge40
Agents40
Tool Calling40
Цены
Цена вводаБесплатно
Цена выводаБесплатно
Смешанная цена (3:1)Бесплатно
Скорость
Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s
Рейтинг цен провайдеров
Рейтинг цен провайдеров
1 провайдеров
ПровайдерВводВывод
1DeepInfra
$0
$0.00001
Сравнение цен разных API-провайдеров для этой модели.