Skip to main content
AITier

Qwen3.5 35B A3B (Non-reasoning)

AlibabaQwenOpen WeightApache 2.0 · Commercial OK

Description

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.

Release Date
2026-02-24
Parameters
35.0B
Context Length
262K
Modalities
audio, image, text, video

Capability Radar

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

Rankings

Domain#RankScoreSource
Agentic Capability62
46.0
LS
Code Ranking340
44.0
AA
General Ranking287
44.0
AA
Multimodal Ranking102
46.0
LS
Science248
52.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Chat

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

Code

FullStackBench en58.1%SR
FullStackBench zh55.0%SR

General

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

Healthcare

PMC-VQA62.0%SR
MedXpertQA61.4%SR

Instruction Following

IFBench70.2%SR

Language

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

Long Context

LongBench v259.0%SR

Math

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

Multimodal

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

Reasoning

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

Search

WideSearch57.1%SR

Tool Calling

BFCL-V467.3%SR

Video

MLVU85.6%SR

Vision

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

AA Evaluation Indices

(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 Category Scores

(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

Pricing

Input Price$0.25 / 1M tokens
Output Price$2 / 1M tokens
Blended Price (3:1)$0.688 / 1M tokens

Speed

Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s

Provider Price Ranking

Provider Price Ranking

6 providers

Cheapest: DeepInfraMost Expensive: DevPass (LLM Gateway)
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2AIHubMix
$0.0564
$0.4512
3302.AI
$0.06
$0.46
4Requesty
$0.14
$1
5AlibabaPRIMARY
$0.25
$2
6DevPass (LLM Gateway)
$0.25
$2

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis