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

22
general
36
coding
82
reasoning
50
science
60
agents
80
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability96
40.0
LS
Code Ranking256
46.0
AA
General Ranking226
52.0
AA
Multimodal Ranking45
47.0
LS
Science227
52.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

3d

SUNRGBD0.33 / 100SR
Hypersim0.13 / 100SR

Agents

t2-bench81.2%SR
AndroidWorld_SR71.1%SR
BFCL-V467.3%SR
BrowseCompOpenAI (2025)61.0%SR
FullStackBench en58.1%SR
WideSearch57.1%SR
TIR-Bench55.5%SR
FullStackBench zh55.0%SR
OSWorld-Verified54.5%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)40.5%SR
VITA-Bench31.9%SR
DeepPlanning22.8%SR

Biology

GPQANYU + Cohere + Anthropic (2023)84.2%SR

Chemistry

SuperGPQA63.4%SR

Code

SWE-Bench Verified69.2%SR

Communication

Multi-Challenge60.0%SR

Embodied

EmbSpatialBench0.83 / 100SR

Finance

MMLU-Pro85.3%SR
MMLU-ProX81.0%SR

General

MMLU-Redux93.3%SR
IFEvalGoogle Research (2023)91.9%SR
C-Eval90.2%SR
MAXIFE86.6%SR
Global PIQA86.6%SR
MMMLU85.2%SR
MMStar81.9%SR
MMMU81.4%SR
Include79.7%SR
MMMU-Pro75.1%SR
LiveCodeBench v674.6%SR
IFBench70.2%SR
LongBench v259.0%SR
SimpleVQA0.58 / 100SR
NOVA-6357.1%SR

Grounding

RefCOCO-avg0.89 / 100SR
ScreenSpot Pro68.6%SR
RefSpatialBench0.64 / 100SR

Healthcare

VideoMMMU80.4%SR
SlakeVQA78.7%SR
PMC-VQA62.0%SR
MedXpertQA61.4%SR

Image To Text

OCRBench91.0%SR

Language

LingoQA79.2%SR
WMT24++76.3%SR

Long Context

MLVU85.6%SR
LVBench71.4%SR
MMLongBench-Doc0.59 / 100SR
AA-LCR58.5%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
Humanity's Last Exam47.4%SR

Multimodal

VLMsAreBlind97.0%SR
V*92.7%SR
AI2D92.6%SR
MMBench-V1.191.5%SR
OmniDocBench 1.589.3%SR
VideoMME w sub.86.6%SR
VideoMME w/o sub.82.5%SR
CC-OCR80.7%SR
CharXiv-R77.5%SR
MVBench74.8%SR
MMVU72.3%SR
BabyVision38.4%SR
ZEROBench-Sub0.34 / 100SR
Nuscene14.6%SR
ZEROBench0.08 / 100SR

Reasoning

CountBench0.98 / 100SR
BrowseComp-zh69.5%SR
Hallusion Bench67.9%SR
ERQA64.8%SR
Seal-041.4%SR
OJBench36.0%SR

Spatial Reasoning

RealWorldQA84.1%SR

Vision

ODinW42.6%SR

AA Evaluation Indices

(Artificial Analysis)
Coding Index(Artificial Analysis)
37.0
Intelligence Index(Artificial Analysis)
24.3
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Lcr(Artificial Analysis)
0.6
Ifbench(Google Research (2023))
0.4
Terminalbench V2 1
0.4
Scicode(UIUC + Argonne National Lab (2024))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.1
Terminalbench Hard(Stanford × Laude Institute (2026))
0.1
Tau Banking
0.0

LLM Stats Category Scores

(LLM Stats (zeroeval))
Legal
80
Math
80
Physics
80
Structured Output
80
Image To Text
80
Instruction Following
80
Language
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/sec161.3
Time to First Token1.21s
Time to Answer1.21s

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1AlibabaPRIMARY
$0.25
$2

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis