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 Directory

Scoring & Data

Scoring & Data
1224 models729 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 Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Alibaba Cloud / Qwen Team model product

Qwen3 VL 8B Thinking

Qwen3 VL 8B Thinking is a multimodal language model for understanding text, images, and video with a focus on reasoning and STEM tasks.

Updated Sep 8, 2026. Default version: Qwen3 VL 8B Thinking

LLMBoard Score27.3Qwen3 VL 8B Thinking
Coverage80%50 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable

On this page

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

Qwen3 VL 8B Thinking Capability Profile

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

Qwen3 VL 8B Thinking LLMBoard score breakdown

Qwen3 VL 8B Thinking Benchmark Results

Benchmark scores for Qwen3 VL 8B Thinking.

30 of 50 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkMuirBenchScore76.80%Rank04Participants12Percentile72.73%EvidenceCEvaluatedSep 8, 2026
BenchmarkBLINKScore68.70%Rank05Participants15Percentile71.43%EvidenceCEvaluatedSep 8, 2026
BenchmarkMMMU (val)Score74.10%Rank05Participants13Percentile66.67%EvidenceCEvaluatedSep 8, 2026
BenchmarkOCRBench-V2 (en)Score63.90%Rank06Participants14Percentile61.54%EvidenceCEvaluatedSep 8, 2026
BenchmarkWritingBenchScore85.50%Rank06Participants15Percentile64.29%EvidenceCEvaluatedSep 8, 2026
BenchmarkCharadesSTAScore59.90%Rank07Participants12Percentile45.45%EvidenceCEvaluatedSep 8, 2026
BenchmarkInfoVQAtestScore86.00%Rank07Participants12Percentile45.45%EvidenceCEvaluatedSep 8, 2026
BenchmarkMLVU-MScore75.10%Rank07Participants8Percentile14.29%EvidenceCEvaluatedSep 8, 2026
BenchmarkMM-MT-BenchScore8.00 pointsRank07Participants17Percentile62.50%EvidenceCEvaluatedSep 8, 2026
BenchmarkOCRBench-V2 (zh)Score59.20%Rank07Participants11Percentile40.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkDocVQAtestScore95.30%Rank08Participants11Percentile30.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkHallusion BenchScore65.40%Rank08Participants18Percentile58.82%EvidenceCEvaluatedSep 8, 2026
BenchmarkScreenSpotScore93.60%Rank09Participants16Percentile46.67%EvidenceCEvaluatedSep 8, 2026
BenchmarkCharXiv-DScore85.90%Rank10Participants17Percentile43.75%EvidenceCEvaluatedSep 8, 2026
BenchmarkLiveBench 20241125Score69.80%Rank10Participants14Percentile30.77%EvidenceCEvaluatedSep 8, 2026
BenchmarkMMBench-V1.1Score87.50%Rank10Participants20Percentile52.63%EvidenceCEvaluatedSep 8, 2026
BenchmarkMMStarScore75.30%Rank11Participants25Percentile58.33%EvidenceCEvaluatedSep 8, 2026
BenchmarkMulti-IFScore75.10%Rank11Participants23Percentile54.55%EvidenceCEvaluatedSep 8, 2026
BenchmarkCreative Writing v3Score82.40%Rank12Participants13Percentile8.33%EvidenceCEvaluatedSep 8, 2026
BenchmarkMathVista-MiniScore81.40%Rank13Participants25Percentile50.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkOSWorldScore33.90%Rank13Participants20Percentile36.84%EvidenceCEvaluatedSep 8, 2026
BenchmarkVideo-MMEScore71.80%Rank14Participants17Percentile18.75%EvidenceCEvaluatedSep 8, 2026
BenchmarkODinWScore39.80%Rank15Participants16Percentile6.67%EvidenceCEvaluatedSep 8, 2026
BenchmarkPolyMATHScore47.50%Rank15Participants23Percentile36.36%EvidenceCEvaluatedSep 8, 2026
BenchmarkSimpleQAScore49.60%Rank15Participants47Percentile69.57%EvidenceCEvaluatedSep 8, 2026
BenchmarkArena-Hard v2Score51.10%Rank16Participants19Percentile16.67%EvidenceCEvaluatedSep 8, 2026
BenchmarkCC-OCRScore76.30%Rank16Participants18Percentile11.76%EvidenceCEvaluatedSep 8, 2026
BenchmarkMVBenchScore69.00%Rank16Participants18Percentile11.76%EvidenceCEvaluatedSep 8, 2026
BenchmarkBFCL-v3Score63.00%Rank19Participants19Percentile0.00%EvidenceCEvaluatedSep 8, 2026
BenchmarkOCRBenchScore81.90%Rank20Participants24Percentile17.39%EvidenceCEvaluatedSep 8, 2026

Qwen3 VL 8B Thinking Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Qwen3 VL 8B Thinking Pricing

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

Official API
N/A
Official provider
N/A
Lowest third-party
From $0.18 input, $2.1 output per 1M via OpenRouter
Tracked offerings
1
1 row
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderOpenRouterProvider model IDqwen/qwen3-vl-8b-thinkingRegionglobalInput / 1M$0.18Output / 1M$2.1Context131.1KUpdatedSep 8, 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 8B Thinking Runtime Performance

Provider-specific output speed and catalog latency for Qwen3 VL 8B Thinking. Runtime does not affect the capability score.

No runtime data

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

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

Qwen3 VL 8B Thinking Specifications

Technical details for the model's default version.

Version
Qwen3 VL 8B Thinking
Released
Sep 22, 2025
Knowledge cutoff
Unknown
Parameters
9B
Context window
262.1K
Max output
262.1K
Inputs
image, text
Outputs
text
Open weights
Yes
License
Apache 2.0

Qwen3 VL 8B Thinking Versions

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

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionQwen3 VL 8B ThinkingReleasedSep 22, 2025LLMBoard27.25Parameters9BContext262.1KMax output262.1KOpen weightsYesLicenseApache 2.0

Models similar to Qwen3 VL 8B Thinking

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

#189+0.24
AC

Qwen3 VL 30B A3B

Alibaba Cloud / Qwen Team

27.49 LLMBoard

Details
#183+2.65
AC

Qwen3 32B

Alibaba Cloud / Qwen Team

29.90 LLMBoard

Details
#196-2.85
AC

Qwen2 VL 72B

Alibaba Cloud / Qwen Team

24.40 LLMBoard

Details
#182+3.28
AC

Qwen3 VL 30B A3B Thinking

Alibaba Cloud / Qwen Team

30.53 LLMBoard

Details
#198-3.56
AC

QwQ 32B

Alibaba Cloud / Qwen Team

23.69 LLMBoard

Details
#179+3.73
AC

Qwen3 30B A3B

Alibaba Cloud / Qwen Team

30.98 LLMBoard

Details

What is Qwen3 VL 8B Thinking?

Key information about Qwen3 VL 8B Thinking and its available data.

Qwen3 VL 8B Thinking is a model from Alibaba Cloud / Qwen Team that combines vision, language, and reasoning. It supports visual understanding, spatial reasoning, long-video comprehension, multilingual OCR, and tool-based interaction.

Data as of 2026-09-08.

FAQ

Common questions about Qwen3 VL 8B Thinking.

When was Qwen3 VL 8B Thinking released?

Qwen3 VL 8B Thinking's default version was released on Sep 22, 2025.

How much does Qwen3 VL 8B Thinking cost?

No official standard PAYG price is currently available for Qwen3 VL 8B Thinking. The lowest tracked third-party offer starts at $0.18 input and $2.1 output via OpenRouter.

Who created Qwen3 VL 8B Thinking?

Qwen3 VL 8B Thinking was created by Alibaba Cloud / Qwen Team.

What is the context window for Qwen3 VL 8B Thinking?

The default version has a 262.1K token context window.

Is Qwen3 VL 8B Thinking open weight?

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

How many API providers offer Qwen3 VL 8B Thinking?

1 provider offerings are linked to the default version.

Browse runtime rankings