Перейти к основному содержанию
AITier

Qwen3.5 35B A3B (Non-reasoning)

AlibabaQwenОткрытые весаApache 2.0 · Коммерческое использование

Описание

Qwen3.5-35B-A3B is a multimodal Mixture-of-Experts model with 35 billion total parameters and 3 billion activated parameters. It combines strong reasoning, coding, agentic, and visual understanding performance with production-friendly efficiency and a native 262K context window.

Дата выхода
2026-02-24
Параметры
35.0B
Длина контекста
262K
Модальности
audio, image, text, video

Радар способностей

15
general
37
coding
82
reasoning
61
science
60
agents
80
multimodal

Рейтинги

Домен#МестоОценкаИсточник
Агентные возможности62
46.0
LS
Рейтинг кодинга337
44.0
AA
Общий рейтинг285
44.0
AA
Мультимодальный рейтинг102
46.0
LS
Наука245
52.0
AA

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Agents

t2-bench81.2%Сам.
VITA-Bench31.9%Сам.
DeepPlanning22.8%Сам.

Chat

IFEvalGoogle Research (2023)91.9%Сам.
Multi-Challenge60.0%Сам.

Code

FullStackBench en58.1%Сам.
FullStackBench zh55.0%Сам.

General

C-Eval90.2%Сам.
MAXIFE86.6%Сам.
Include79.7%Сам.
AndroidWorld_SR71.1%Сам.
NOVA-6357.1%Сам.

Healthcare

PMC-VQA62.0%Сам.
MedXpertQA61.4%Сам.

Instruction Following

IFBench70.2%Сам.

Language

MMLU-Redux93.3%Сам.
MMLU-Pro85.3%Сам.
MMMLU85.2%Сам.
MMLU-ProX81.0%Сам.
WMT24++76.3%Сам.

Long Context

LongBench v259.0%Сам.

Math

HMMT2589.2%Сам.
HMMT 202589.0%Сам.
MathVista-Mini86.2%Сам.
DynaMath85.0%Сам.
MathVision83.9%Сам.
CodeForces0.82 / 3000Сам.
PolyMATH64.4%Сам.

Multimodal

VideoMME w/o sub.82.5%Сам.
MMMU81.4%Сам.
VideoMMMU80.4%Сам.
TIR-Bench55.5%Сам.
OSWorld-Verified54.5%Сам.

Reasoning

Global PIQA86.6%Сам.
GPQANYU + Cohere + Anthropic (2023)84.2%Сам.
CharXiv-R77.5%Сам.
LiveCodeBench v674.6%Сам.
BrowseComp-zh69.5%Сам.
SWE-Bench Verified69.2%Сам.
SuperGPQA63.4%Сам.
BrowseCompOpenAI (2025)61.0%Сам.
AA-LCR58.5%Сам.
Humanity's Last Exam47.4%Сам.
Seal-041.4%Сам.
Terminal-Bench 2.0Stanford × Laude Institute (2026)40.5%Сам.
OJBench36.0%Сам.

Search

WideSearch57.1%Сам.

Tool Calling

BFCL-V467.3%Сам.

Video

MLVU85.6%Сам.

Vision

CountBench0.98 / 100Сам.
VLMsAreBlind97.0%Сам.
V*92.7%Сам.
AI2D92.6%Сам.
MMBench-V1.191.5%Сам.
OCRBench91.0%Сам.
OmniDocBench 1.589.3%Сам.
RefCOCO-avg0.89 / 100Сам.
VideoMME w sub.86.6%Сам.
RealWorldQA84.1%Сам.
EmbSpatialBench0.83 / 100Сам.
MMStar81.9%Сам.
CC-OCR80.7%Сам.
LingoQA79.2%Сам.
SlakeVQA78.7%Сам.
MMMU-Pro75.1%Сам.
MVBench74.8%Сам.
MMVU72.3%Сам.
LVBench71.4%Сам.
ScreenSpot Pro68.6%Сам.
Hallusion Bench67.9%Сам.
ERQA64.8%Сам.
RefSpatialBench0.64 / 100Сам.
MMLongBench-Doc0.59 / 100Сам.
SimpleVQA0.58 / 100Сам.
ODinW42.6%Сам.
BabyVision38.4%Сам.
ZEROBench-Sub0.34 / 100Сам.
SUNRGBD0.33 / 100Сам.
Nuscene14.6%Сам.
Hypersim0.13 / 100Сам.
ZEROBench0.08 / 100Сам.

Индексы оценки AA

(Artificial Analysis)
Tau2(Sierra + U Toronto + Vector Institute (2025))
86.3
Gpqa(NYU + Cohere + Anthropic (2023))
81.9
Lcr(Artificial Analysis)
63.0
Ifbench(Google Research (2023))
44.5
Terminalbench V2 1
40.8
Coding Index(Artificial Analysis)
37.0
Intelligence Index(Artificial Analysis)
15.1
Hle(Center for AI Safety + Scale AI (2025))
13.4
Terminalbench Hard(Stanford × Laude Institute (2026))
10.6
Tau Banking
4.9

Оценки категорий LLM Stats

(LLM Stats (zeroeval))
Chat
80
Image To Text
80
Instruction Following
80
Language
80
Legal
80
Math
80
Physics
80
Structured Output
80
Embodied
80
Finance
80
Biology
80
Text-to-image
80
Video
80
Long Context
70
Multimodal
70
Reasoning
70
Spatial Reasoning
70
Frontend Development
70
General
70
Grounding
70
Healthcare
70
Chemistry
70
Vision
70
Search
60
Code
60
Communication
60
Economics
60
Tool Calling
60
Agents
50
3d
20
Spatial
10

Цены

Цена ввода$0.25 / 1M токенов
Цена вывода$2 / 1M токенов
Смешанная цена (3:1)$0.688 / 1M токенов

Скорость

Токенов/сек0.0
Задержка первого токена0.00s
Время до первого ответа0.00s

Рейтинг цен провайдеров

Рейтинг цен провайдеров

6 провайдеров

Самый дешевый: DeepInfraСамый дорогой: DevPass (LLM Gateway)
ПровайдерВводВывод
1DeepInfraСамый дешевый
$0
$0
2AIHubMix
$0.0564
$0.4512
3302.AI
$0.06
$0.46
4Requesty
$0.14
$1
5AlibabaОсновной
$0.25
$2
6DevPass (LLM Gateway)
$0.25
$2

Сравнение цен разных API-провайдеров для этой модели.

Внешние ссылки

LLM StatsArtificial Analysis