Qwen3 235B A22B 2507 Instruct
AlibabaQwenОткрытые весаApache 2.0 · Коммерческое использование
Описание
Qwen3-235B-A22B-Instruct-2507 is the updated instruct version of Qwen3-235B-A22B featuring significant improvements in general capabilities including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. It provides substantial gains in long-tail knowledge coverage across multiple languages and markedly better alignment with user preferences in subjective and open-ended tasks.
Дата выхода
2025-07-21
Параметры
235.0B
Длина контекста
262K
Модальности
text
Радар способностей
37
general
49
coding
76
reasoning
49
science
60
agents
0
multimodal
Рейтинги
| Домен | #Место | Оценка | Источник |
|---|---|---|---|
| Агентные возможности | 53 | 52.0 | LS |
| Рейтинг кодинга | 292 | 40.0 | AA |
| Общий рейтинг | 280 | 46.0 | AA |
| Наука | 232 | 52.0 | AA |
Оценки бенчмарков (LLM Stats)
(LLM Stats (zeroeval))Agents
BFCL-v3
70.9%Сам.
Biology
GPQANYU + Cohere + Anthropic (2023)
77.5%Сам.
Chemistry
SuperGPQA
62.6%Сам.
Code
Aider-Polyglot
57.3%Сам.
Communication
WritingBench
85.2%Сам.
Multi-IF
77.5%Сам.
Tau2 Retail
71.3%Сам.
Tau2 Airline
44.0%Сам.
Creativity
Creative Writing v3
87.5%Сам.
Arena-Hard v2
79.2%Сам.
Factuality
SimpleQA
54.3%Сам.
Finance
MMLU-Pro
83.0%Сам.
MMLU-ProX
79.4%Сам.
General
MMLU-Redux
93.1%Сам.
IFEvalGoogle Research (2023)
88.7%Сам.
MultiPL-E
87.9%Сам.
CSimpleQA
84.3%Сам.
Include
79.5%Сам.
LiveBench 20241125
75.4%Сам.
LiveCodeBench v6
51.8%Сам.
Math
AIME 2025
70.3%Сам.
HMMT25
55.4%Сам.
PolyMATH
50.2%Сам.
Reasoning
ZebraLogic
95.0%Сам.
ARC-AGI
41.8%Сам.
Индексы оценки AA
(Artificial Analysis)Math Index(Artificial Analysis)71.7
Intelligence Index(Artificial Analysis)18.4
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))1.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.8
Gpqa(NYU + Cohere + Anthropic (2023))0.8
Aime(MAA (Mathematical Association of America))0.7
Aime 25(MAA (Mathematical Association of America))0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.5
Ifbench(Google Research (2023))0.5
Scicode(UIUC + Argonne National Lab (2024))0.4
Tau2(Sierra + U Toronto + Vector Institute (2025))0.3
Lcr(Artificial Analysis)0.3
Terminalbench Hard(Stanford × Laude Institute (2026))0.2
Hle(Center for AI Safety + Scale AI (2025))0.1
Оценки категорий LLM Stats
(LLM Stats (zeroeval))Legal80
Structured Output80
Instruction Following80
Language80
Finance80
Healthcare80
Biology80
Creativity80
Writing80
Math70
Physics70
Reasoning70
General70
Agents70
Chemistry70
Communication70
Code60
Economics60
Tool Calling60
Multimodal50
Spatial Reasoning50
Factuality50
Vision50
Цены
Цена ввода$0.7 / 1M токенов
Цена вывода$2.8 / 1M токенов
Смешанная цена (3:1)$1.225 / 1M токенов
Скорость
Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s
Рейтинг цен провайдеров
Рейтинг цен провайдеров
7 провайдеров
Самый дешевый: CortecsСамый дорогой: GreenPT
ПровайдерВводВывод
1CortecsСамый дешевый
$0.069
$0.455
2LLM Gateway
$0.09
$0.58
3Venice AI
$0.15
$0.75
4302.AI
$0.29
$1.143
5AlibabaОсновной
$0.7
$2.8
6Scaleway
$0.75
$2.25
7GreenPT
$1.026
$3.078
Сравнение цен разных API-провайдеров для этой модели.