llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Alibaba Cloud / Qwen Team model product

Qwen3 VL 235B A22B

Qwen3-VL is a large multimodal model that unifies vision, language, and reasoning to achieve human-level perception and cognition across text, images, and video.

Updated Aug 17, 2026. Default version: Qwen3 VL 235B A22B Instruct

Compare
LLMBoard Score42.7Qwen3 VL 235B A22B Instruct
Coverage100%50 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Qwen3 VL 235B A22B Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Qwen3 VL 235B A22B Instruct LLMBoard score breakdown

Qwen3 VL 235B A22B Benchmark Results

Benchmark scores for Qwen3 VL 235B A22B Instruct.

30 of 50 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkCharadesSTAScore64.8%Rank01Participants12Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkDocVQAtestScore97.1%Rank01Participants11Percentile100.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkCC-OCRScore82.2%Rank02Participants18Percentile94.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkCreative Writing v3Score86.5%Rank02Participants13Percentile91.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMMUvalScore78.7%Rank02Participants4Percentile66.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkBLINKScore70.7%Rank03Participants15Percentile85.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkCSimpleQAScore83.4%Rank03Participants8Percentile71.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkInfoVQAtestScore89.2%Rank03Participants12Percentile81.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkLiveCodeBench v5Score61.4%Rank03Participants9Percentile75.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMultiPL-EScore86.1%Rank03Participants13Percentile83.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkOCRBenchScore92.0%Rank03Participants24Percentile91.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkOCRBench-V2 (en)Score67.1%Rank03Participants14Percentile84.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkOCRBench-V2 (zh)Score61.8%Rank03Participants11Percentile80.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkScreenSpotScore95.4%Rank03Participants16Percentile86.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkAndroidWorld_SRScore63.7%Rank04Participants8Percentile57.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkODinWScore48.6%Rank04Participants16Percentile80.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkArena-Hard v2Score77.4%Rank05Participants16Percentile73.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkMM-MT-BenchScore8.5 pointsRank05Participants17Percentile75.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkOSWorldScore66.7%Rank05Participants20Percentile79.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkVideoMME w/o sub.Score79.2%Rank05Participants10Percentile55.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkWritingBenchScore85.5%Rank05Participants15Percentile71.4%EvidenceCEvaluatedAug 17, 2026
BenchmarkLiveBench 20241125Score74.8%Rank06Participants14Percentile61.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkMuirBenchScore72.8%Rank06Participants12Percentile54.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkMLVUScore84.3%Rank08Participants10Percentile22.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMBench-V1.1Score89.9%Rank08Participants20Percentile63.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMStarScore78.4%Rank08Participants24Percentile69.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkMulti-IFScore76.3%Rank08Participants23Percentile68.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkIncludeScore80.0%Rank09Participants31Percentile73.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkMathVista-MiniScore84.9%Rank09Participants24Percentile65.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkHallusion BenchScore63.2%Rank11Participants18Percentile41.2%EvidenceCEvaluatedAug 17, 2026
BenchmarkLVBenchScore67.7%Rank11Participants25Percentile58.3%EvidenceCEvaluatedAug 17, 2026
BenchmarkAI2DScore89.7%Rank12Participants33Percentile65.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkRealWorldQAScore79.3%Rank13Participants29Percentile57.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkScreenSpot ProScore62.0%Rank13Participants25Percentile50.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkSimpleQAScore51.9%Rank13Participants47Percentile73.9%EvidenceCEvaluatedAug 17, 2026
BenchmarkBFCL-v3Score67.7%Rank14Participants19Percentile27.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLU-ProXScore77.8%Rank14Participants32Percentile58.1%EvidenceCEvaluatedAug 17, 2026
BenchmarkERQAScore51.3%Rank16Participants24Percentile34.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLUScore88.8%Rank16Participants101Percentile85.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkSuperGPQAScore60.4%Rank17Participants34Percentile51.5%EvidenceCEvaluatedAug 17, 2026
BenchmarkHMMT25Score57.4%Rank19Participants25Percentile25.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMathVisionScore66.5%Rank19Participants33Percentile43.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLU-ReduxScore92.2%Rank19Participants48Percentile61.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkVideoMMMUScore74.7%Rank20Participants26Percentile24.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkIFEvalScore87.8%Rank29Participants67Percentile57.6%EvidenceCEvaluatedAug 17, 2026
BenchmarkCharXiv-RScore62.1%Rank39Participants51Percentile24.0%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMMU-ProScore68.1%Rank40Participants68Percentile41.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkLiveCodeBench v6Score54.3%Rank44Participants56Percentile21.8%EvidenceCEvaluatedAug 17, 2026
BenchmarkMMLU-ProScore81.8%Rank44Participants134Percentile67.7%EvidenceCEvaluatedAug 17, 2026
BenchmarkAIME 2025Score74.7%Rank79Participants115Percentile31.6%EvidenceCEvaluatedAug 17, 2026

Qwen3 VL 235B A22B Arena Results

Preference and agent-evaluation results for the default version.

5 rows
Columns

Show columns

Sort by
Arena
Category
Rank
Rating / score
Votes
Observations
Result date
ArenavisionCategoryoverallRank50Rating / score1246.8Votes12,102ObservationsN/AResult dateAug 6, 2026
Arenavision style controlCategoryoverallRank63Rating / score1214.6Votes12,102ObservationsN/AResult dateAug 6, 2026
ArenatextCategoryoverallRank94Rating / score1420.8Votes11,560ObservationsN/AResult dateAug 12, 2026
Arenatext style controlCategoryoverallRank121Rating / score1414.5Votes11,560ObservationsN/AResult dateAug 12, 2026
Arenatext factualityCategoryoverallRank124Rating / score1410.0Votes3,112ObservationsN/AResult dateAug 12, 2026

Qwen3 VL 235B A22B Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.20 input, $0.88 output per 1M via LLM Gateway
Tracked offerings
7
7 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderLLM GatewayProvider model IDqwen3-vl-235b-a22b-instructRegionglobalInput / 1M$0.20Output / 1M$0.88Context262.1KUpdatedAug 17, 2026
ProviderOpenRouterProvider model IDqwen/qwen3-vl-235b-a22b-instructRegionglobalInput / 1M$0.21Output / 1M$1.9Context262.1KUpdatedAug 17, 2026
ProviderTensorXProvider model IDqwen/qwen3-vl-235b-a22b-instructRegionglobalInput / 1M$0.21Output / 1M$1.9Context131KUpdatedAug 17, 2026
ProviderNanoGPTProvider model IDqwen/Qwen3-VL-235B-A22B-InstructRegionglobalInput / 1M$0.30Output / 1M$1.2Context128KUpdatedAug 17, 2026
ProviderHeliconeProvider model IDqwen3-vl-235b-a22b-instructRegionglobalInput / 1M$0.30Output / 1M$1.5Context256KUpdatedAug 17, 2026
ProviderNovitaAIProvider model IDqwen/qwen3-vl-235b-a22b-instructRegionglobalInput / 1M$0.30Output / 1M$1.5Context131.1KUpdatedAug 17, 2026
ProviderVercel AI GatewayProvider model IDalibaba/qwen3-vl-235b-a22b-instructRegionglobalInput / 1M$0.40Output / 1M$1.6Context131.1KUpdatedAug 17, 2026

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

Qwen3 VL 235B A22B Runtime Performance

Provider-specific output speed and catalog latency for Qwen3 VL 235B A22B Instruct. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Browse runtime rankings

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Qwen3 VL 235B A22B Specifications

Technical details for the model's default version.

Version
Qwen3 VL 235B A22B Instruct
Released
Sep 22, 2025
Knowledge cutoff
Unknown
Parameters
236B
Context window
262.1K
Max output
262.1K
Inputs
image, text, video
Outputs
text
Open weights
No
License
Apache 2.0

Qwen3 VL 235B A22B Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 rows
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionQwen3 VL 235B A22B InstructReleasedSep 22, 2025LLMBoard42.7Parameters236BContext262.1KMax output262.1KOpen weightsNoLicenseApache 2.0

Qwen3 VL 235B A22B vs nearby models

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

Qwen3 VL 235B A22BvsNova 2 OmniQwen3 VL 235B A22BvsGPT-OSS-120BQwen3 VL 235B A22BvsStep3 VL 10BQwen3 VL 235B A22BvsNova 2 LiteQwen3 VL 235B A22BvsQwen3 235B A22BQwen3 VL 235B A22BvsGLM 4.5 Air

Models similar to Qwen3 VL 235B A22B

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

#128-0.8
AC

Qwen3 235B A22B

Alibaba Cloud / Qwen Team

41.9 LLMBoard

DetailsCompare
#132-1.8
AC

Qwen3.5 9B

Alibaba Cloud / Qwen Team

40.9 LLMBoard

DetailsCompare
#134-2.3
AC

Qwen3 Next 80B A3B Thinking

Alibaba Cloud / Qwen Team

40.4 LLMBoard

DetailsCompare
#135-2.4
AC

Qwen3 Max

Alibaba Cloud / Qwen Team

40.2 LLMBoard

DetailsCompare
#113+2.6
AC

Qwen3 VL 235B A22B Thinking

Alibaba Cloud / Qwen Team

45.3 LLMBoard

DetailsCompare
#136-2.8
AC

Qwen3 VL 32B Thinking

Alibaba Cloud / Qwen Team

39.8 LLMBoard

DetailsCompare

What is Qwen3 VL 235B A22B?

Key information about Qwen3 VL 235B A22B and its available data.

Qwen3-VL is a large multimodal model that unifies vision, language, and reasoning to achieve human-level perception and cognition across text, images, and video. Built on a 235B-parameter architecture, it integrates early joint training of visual and textual modalities for strong language grounding.

The model supports up to a 1 million-token context window and excels at visual understanding, spatial reasoning, long video comprehension, and tool-based interaction. It can generate code from images, perform precise 2D/3D object grounding, and operate digital interfaces like a visual agent.

5 Pro in perception benchmarks, while the “Thinking” version leads in multimodal reasoning and STEM tasks. With multilingual OCR, creative writing, and fine-grained scene interpretation, Qwen3-VL establishes a new open-source frontier for integrated vision-language intelligence.

Data as of 2026-08-17.

FAQ

Common questions about Qwen3 VL 235B A22B.

When was Qwen3 VL 235B A22B released?

Qwen3 VL 235B A22B's default version was released on Sep 22, 2025.

How much does Qwen3 VL 235B A22B cost?

No official standard PAYG price is currently available for Qwen3 VL 235B A22B. The lowest tracked third-party offer starts at $0.20 input and $0.88 output via LLM Gateway.

Who created Qwen3 VL 235B A22B?

Qwen3 VL 235B A22B was created by Alibaba Cloud / Qwen Team.

What is the context window for Qwen3 VL 235B A22B?

The default version has a 262.1K token context window.

Is Qwen3 VL 235B A22B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Qwen3 VL 235B A22B?

7 provider offerings are linked to the default version.

What models should I compare Qwen3 VL 235B A22B with?

Nearby ranked alternatives include Nova 2 Omni, GPT-OSS-120B, Step3 VL 10B.