跳轉到主要內容
AITier

Qwen3.5 35B A3B (Non-reasoning)

AlibabaQwen開源權重Apache 2.0 · 商用許可

描述

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.

發布日期
2026-02-24
參數規模
35.0B
上下文長度
262K
支援模態
audio, image, text, video

能力雷達圖

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

排行榜排名

領域#排名分數來源
智慧體能力模型榜62
46.0
LS
程式碼能力榜331
44.0
AA
通用能力榜281
44.0
AA
多模態榜101
46.0
LS
科學能力239
52.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Chat

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

Code

FullStackBench en58.1%自報
FullStackBench zh55.0%自報

General

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

Healthcare

PMC-VQA62.0%自報
MedXpertQA61.4%自報

Instruction Following

IFBench70.2%自報

Language

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

Long Context

LongBench v259.0%自報

Math

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

Multimodal

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

Reasoning

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

Search

WideSearch57.1%自報

Tool Calling

BFCL-V467.3%自報

Video

MLVU85.6%自報

Vision

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

AA 評測指數

(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

LLM Stats 分類評分

(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

定價

輸入價格$0.25 / 1M tokens
輸出價格$2 / 1M tokens
混合價格(3:1)$0.688 / 1M tokens

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

供應商價格排行

6 個供應商

最便宜: DeepInfra最貴: DevPass (LLM Gateway)
供應商輸入輸出
1DeepInfra最便宜
$0
$0
2AIHubMix
$0.0564
$0.4512
3302.AI
$0.06
$0.46
4Requesty
$0.14
$1
5Alibaba主要
$0.25
$2
6DevPass (LLM Gateway)
$0.25
$2

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM StatsArtificial Analysis