llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen3.5 35B A3B

Alibaba Cloud / Qwen Team model product

Qwen3.5 35B A3B

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.

Updated Aug 10, 2026. Default version: Qwen3.5-35B-A3B

Compare
LLMBoard score53.3Qwen3.5-35B-A3B
Coverage100%19 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Qwen3.5-35B-A3B
Released
Feb 24, 2026
Knowledge cutoff
Unknown
Parameters
35B
Context window
262.1K
Max output
65.5K
Inputs
audio, image, text, video
Outputs
text
Open weights
Yes
License
Apache 2.0

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Qwen3.5-35B-A3B category scores

Benchmark results

Published benchmark records for the scored version Qwen3.5-35B-A3B.

81 rows
Columns

Show columns

AndroidWorld_SR0.718100.0%CAug 7, 2026
Hypersim0.114100.0%CAug 7, 2026
VLMsAreBlind1.014100.0%CAug 7, 2026
CountBench1.02680.0%CAug 7, 2026
BrowseComp-zh0.731383.3%CAug 7, 2026
FullStackBench en0.6330.0%CAug 7, 2026
FullStackBench zh0.6330.0%CAug 7, 2026
Hallusion Bench0.731686.7%CAug 7, 2026
MMLongBench-Doc0.63550.0%CAug 7, 2026
MMStar0.832290.5%CAug 7, 2026
MVBench0.731787.5%CAug 7, 2026
Nuscene0.1330.0%CAug 7, 2026
PMC-VQA0.6330.0%CAug 7, 2026
SlakeVQA0.83433.3%CAug 7, 2026
TIR-Bench0.63433.3%CAug 7, 2026
VideoMME w/o sub.0.831077.8%CAug 7, 2026
LingoQA0.8440.0%CAug 7, 2026
MedXpertQA0.641272.7%CAug 7, 2026
MMVU0.7440.0%CAug 7, 2026
OCRBench0.942285.7%CAug 7, 2026
SUNRGBD0.3440.0%CAug 7, 2026
ZEROBench-Sub0.34525.0%CAug 7, 2026
CodeForces0.851673.3%CAug 7, 2026
DynaMath0.85733.3%CAug 7, 2026
MMBench-V1.10.951876.5%CAug 7, 2026
OJBench0.45950.0%CAug 7, 2026
BFCL-V40.761358.3%CAug 7, 2026
DeepPlanning0.26937.5%CAug 7, 2026
MathVista-Mini0.962377.3%CAug 7, 2026
OmniDocBench 1.50.961666.7%CAug 7, 2026
RefSpatialBench0.6660.0%CAug 7, 2026
Seal-00.4660.0%CAug 7, 2026
V*0.96716.7%CAug 7, 2026
VideoMME w sub.0.961044.4%CAug 7, 2026
EmbSpatialBench0.87814.3%CAug 7, 2026
ERQA0.672372.7%CAug 7, 2026
MAXIFE0.971140.0%CAug 7, 2026
MLVU0.971033.3%CAug 7, 2026
NOVA-630.671140.0%CAug 7, 2026
PolyMATH0.672372.7%CAug 7, 2026
RefCOCO-avg0.9770.0%CAug 7, 2026
C-Eval0.981858.8%CAug 7, 2026
HMMT250.982570.8%CAug 7, 2026
LVBench0.782469.6%CAug 7, 2026
RealWorldQA0.882672.0%CAug 7, 2026
t2-bench0.882368.2%CAug 7, 2026
VITA-Bench0.381022.2%CAug 7, 2026
ZEROBench0.18912.5%CAug 7, 2026
AI2D0.993274.2%CAug 7, 2026
BabyVision0.4990.0%CAug 7, 2026
CC-OCR0.891852.9%CAug 7, 2026
Global PIQA0.991333.3%CAug 7, 2026
MMLU-ProX0.893274.2%CAug 7, 2026
WideSearch0.6990.0%CAug 7, 2026
ScreenSpot Pro0.7102460.9%CAug 7, 2026
AA-LCR0.6111528.6%CAug 7, 2026
IFEval0.9116584.4%CAug 7, 2026
Include0.8113166.7%CAug 7, 2026
MathVision0.8113267.7%CAug 7, 2026
MMLU-Redux0.9114878.7%CAug 7, 2026
Multi-Challenge0.6112964.3%CAug 7, 2026
ODinW0.4111633.3%CAug 7, 2026
SimpleVQA0.6111316.7%CAug 7, 2026
WMT24++0.8112354.5%CAug 7, 2026
LongBench v20.6121731.3%CAug 7, 2026
MMMU0.8136380.7%CAug 7, 2026
MMLU-Pro0.91412989.8%CAug 7, 2026
SuperGPQA0.6143460.6%CAug 7, 2026
IFBench0.7162844.4%CAug 7, 2026
VideoMMMU0.8162640.0%CAug 7, 2026
HMMT 20250.9193343.8%CAug 7, 2026
OSWorld-Verified0.521224.8%CAug 7, 2026
LiveCodeBench v60.7245355.8%CAug 7, 2026
Humanity's Last Exam0.5259273.6%CAug 7, 2026
CharXiv-R0.8264745.6%CAug 7, 2026
MMMLU0.9324935.4%CAug 7, 2026
MMMU-Pro0.8336550.0%CAug 7, 2026
BrowseComp0.6355840.4%CAug 7, 2026
Terminal-Bench 2.00.445498.3%CAug 7, 2026
GPQA0.86123374.1%CAug 7, 2026
SWE-Bench Verified0.76310439.8%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

85 rows
Columns

Show columns

text factualitychinese481485.11,096N/AAug 6, 2026
text factualityindustry mathematical761413.11,031N/AAug 6, 2026
text factualityindustry medicine and healthcare761460.41,449N/AAug 6, 2026
text factualitymath771412.51,147N/AAug 6, 2026
textchinese821466.31,592N/AAug 6, 2026
webdevwebdev-react871235.11,336N/AAug 6, 2026
text factualityindustry legal and government891431.71,547N/AAug 6, 2026
webdevwebdev-html911297.5185N/AAug 6, 2026
text factualityexpert971426.41,773N/AAug 6, 2026
webdevoverall971250.41,521N/AAug 6, 2026
webdevwebdev971250.41,521N/AAug 6, 2026
text factualityrussian1001399.72,065N/AAug 6, 2026
textindustry medicine and healthcare1031425.82,148N/AAug 6, 2026
text factualityindustry life and physical and social science1051436.43,417N/AAug 6, 2026
text style controlchinese1061460.31,592N/AAug 6, 2026
text factualityindustry business and management and financial operations1091418.44,116N/AAug 6, 2026
text factualitycreative writing1111365.03,087N/AAug 6, 2026
text factualitymulti turn1111405.43,684N/AAug 6, 2026
textfrench1131416.4825N/AAug 6, 2026
text factualitycoding1131449.26,129N/AAug 6, 2026
textjapanese1141329.9224N/AAug 6, 2026
textkorean1141352.4465N/AAug 6, 2026
text factualityindustry entertainment and sports and media1141365.84,044N/AAug 6, 2026
text factualityinstruction following1141400.57,460N/AAug 6, 2026
text factualityhard prompts english1151438.27,176N/AAug 6, 2026
text factualityindustry writing and literature and language1151382.54,812N/AAug 6, 2026
text factualitylonger query1151416.59,214N/AAug 6, 2026
text factualityindustry software and it services1161443.310,380N/AAug 6, 2026
textpolish1171387.4553N/AAug 6, 2026
text style controlfrench1181424.7825N/AAug 6, 2026
textexpert1221406.62,515N/AAug 6, 2026
textspanish1221391.7884N/AAug 6, 2026
text factualityenglish1231420.613,386N/AAug 6, 2026
text factualityoverall1241408.828,669N/AAug 6, 2026
text factualityexclude ties1241396.220,935N/AAug 6, 2026
textindustry business and management and financial operations1251393.75,810N/AAug 6, 2026
textmath1251405.01,746N/AAug 6, 2026
text factualityhard prompts1261425.418,030N/AAug 6, 2026
text factualitynon english1261392.415,152N/AAug 6, 2026
textindustry mathematical1271406.71,561N/AAug 6, 2026
text style controlindustry medicine and healthcare1281430.82,148N/AAug 6, 2026
text style controlkorean1281343.7465N/AAug 6, 2026
text style controljapanese1291321.2224N/AAug 6, 2026
textindustry software and it services1311415.711,371N/AAug 6, 2026
textinstruction following1311380.39,205N/AAug 6, 2026
texthard prompts english1331409.18,880N/AAug 6, 2026
textindustry life and physical and social science1331412.34,879N/AAug 6, 2026
text style controlexpert1331419.02,515N/AAug 6, 2026
text style controlspanish1331385.4884N/AAug 6, 2026
textenglish1341407.913,573N/AAug 6, 2026
text style controlpolish1341375.6553N/AAug 6, 2026
text style controlindustry business and management and financial operations1351402.25,810N/AAug 6, 2026
text style controlmath1351400.01,746N/AAug 6, 2026
textoverall1361395.628,864N/AAug 6, 2026
textcoding1361409.47,896N/AAug 6, 2026
textexclude ties1361374.421,082N/AAug 6, 2026
textindustry legal and government1361398.02,250N/AAug 6, 2026
textlonger query1361391.910,952N/AAug 6, 2026
textnon english1361379.015,291N/AAug 6, 2026
texthard prompts1371400.618,160N/AAug 6, 2026
textrussian1381378.43,101N/AAug 6, 2026
text style controlindustry mathematical1381407.01,561N/AAug 6, 2026
text style controlinstruction following1381388.29,205N/AAug 6, 2026
textmulti turn1391390.15,166N/AAug 6, 2026
text style controlenglish1391411.313,573N/AAug 6, 2026
text style controlindustry life and physical and social science1391415.24,879N/AAug 6, 2026
text style controlindustry software and it services1401430.811,371N/AAug 6, 2026
textgerman1421358.3475N/AAug 6, 2026
textindustry writing and literature and language1421366.16,605N/AAug 6, 2026
text style controlexclude ties1421375.321,082N/AAug 6, 2026
text style controloverall1431395.328,864N/AAug 6, 2026
text style controlhard prompts english1431423.88,880N/AAug 6, 2026
textcreative writing1441347.94,412N/AAug 6, 2026
textindustry entertainment and sports and media1451347.55,598N/AAug 6, 2026
text style controlindustry legal and government1451399.62,250N/AAug 6, 2026
text style controllonger query1451401.610,952N/AAug 6, 2026
text style controlmulti turn1451394.55,166N/AAug 6, 2026
text style controlnon english1471375.515,291N/AAug 6, 2026
text style controlrussian1471377.73,101N/AAug 6, 2026
text style controlhard prompts1491413.218,160N/AAug 6, 2026
text style controlcoding1501434.67,896N/AAug 6, 2026
text style controlindustry writing and literature and language1531365.36,605N/AAug 6, 2026
text style controlgerman1591348.8475N/AAug 6, 2026
text style controlindustry entertainment and sports and media1611345.05,598N/AAug 6, 2026
text style controlcreative writing1631343.44,412N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.225 input, $1.8 output per 1M via NanoGPT
Tracked offerings
1
1 rows
Columns

Show columns

NanoGPTqwen3.5-35b-a3bglobal$0.225$1.8260.1KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Qwen3.5 35B A3B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Qwen3.5-35B-A3BFeb 24, 202653.335B262.1K65.5KYesApache 2.0

What is Qwen3.5 35B A3B?

A concise description based on the published model registry.

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.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Qwen3.5 35B A3B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Qwen3.5 35B A3BvsMiniMax M2.1Qwen3.5 35B A3BvsLlama 3.3 70BQwen3.5 35B A3BvsQwen3 Next 80B A3B ThinkingQwen3.5 35B A3BvsQwen2.5 72BQwen3.5 35B A3BvsGemini 2.0 FlashQwen3.5 35B A3BvsSarvam 105B

Models similar to Qwen3.5 35B A3B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#72-0.2
AC

Qwen2.5 72B

Alibaba Cloud / Qwen Team

53.1 LLMBoard

DetailsCompare
#70+0.9
AC

Qwen3 Next 80B A3B Thinking

Alibaba Cloud / Qwen Team

54.1 LLMBoard

DetailsCompare
#78-1.5
AC

Qwen3 VL 32B Thinking

Alibaba Cloud / Qwen Team

51.7 LLMBoard

DetailsCompare
#79-1.7
AC

Qwen2.5 VL 32B

Alibaba Cloud / Qwen Team

51.5 LLMBoard

DetailsCompare
#59+3.7
AC

Qwen2.5 32B

Alibaba Cloud / Qwen Team

56.9 LLMBoard

DetailsCompare
#58+3.8
AC

Qwen3.5 27B

Alibaba Cloud / Qwen Team

57.1 LLMBoard

DetailsCompare

FAQ

Common questions about Qwen3.5 35B A3B.

When was Qwen3.5 35B A3B released?

Qwen3.5 35B A3B's default version was released on Feb 24, 2026.

How much does Qwen3.5 35B A3B cost?

No official standard PAYG price is currently available for Qwen3.5 35B A3B. The lowest tracked third-party offer starts at $0.225 input and $1.8 output via NanoGPT.

Who created Qwen3.5 35B A3B?

Qwen3.5 35B A3B is published under Alibaba Cloud / Qwen Team in the model registry.

What is the context window for Qwen3.5 35B A3B?

The default version has a 262.1K token context window.

Is Qwen3.5 35B A3B open weight?

Yes. The default version is marked as open weight under Apache 2.0.

How many API providers offer Qwen3.5 35B A3B?

1 published provider offerings are linked to the default version.

What models should I compare Qwen3.5 35B A3B with?

Nearby ranked alternatives include MiniMax M2.1, Llama 3.3 70B, Qwen3 Next 80B A3B Thinking.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai