Alibaba Cloud / Qwen Team model product
Qwen3 VL 235B A22B Thinking
Qwen3 VL 235B A22B Thinking is a vision-language model with a 236B-parameter mixture-of-experts architecture for multimodal reasoning.
Updated Sep 8, 2026. Default version: Qwen3 VL 235B A22B Thinking
LLMBoard Score44.4Qwen3 VL 235B A22B Thinking
Coverage80%58 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
Qwen3 VL 235B A22B Thinking Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 VL 235B A22B Thinking Benchmark Results
Benchmark scores for Qwen3 VL 235B A22B Thinking.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkARKitScenes | Score0.54 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkLiveBench 20241125 | Score79.60% | Rank01 | Participants14 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMathVerse-Mini | Score0.85 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMIABench | Score0.93 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMMUval | Score80.60% | Rank01 | Participants4 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkObjectron | Score0.71 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (zh) | Score63.50% | Rank01 | Participants11 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-G | Score0.68 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkRoboSpatialHome | Score0.74 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSIFO | Score0.77 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkSIFO-Multiturn | Score0.71 points | Rank01 | Participants1 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkZebraLogic | Score97.30% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkCharadesSTA | Score63.50% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkDesign2Code | Score0.93 points | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkInfoVQAtest | Score89.50% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkMM-MT-Bench | Score8.50 points | Rank02 | Participants17 | Percentile93.75% | EvidenceC | Evaluated |
| BenchmarkMuirBench | Score80.10% | Rank02 | Participants12 | Percentile90.91% | EvidenceC | Evaluated |
| BenchmarkRefSpatialBench | Score0.70 points | Rank02 | Participants6 | Percentile80.00% | EvidenceC | Evaluated |
| BenchmarkRefCOCO-avg | Score0.92 points | Rank03 | Participants9 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkScreenSpot | Score95.40% | Rank03 | Participants16 | Percentile86.67% | EvidenceC | Evaluated |
| BenchmarkSUNRGBD | Score0.35 points | Rank03 | Participants4 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkVisuLogic | Score0.34 points | Rank03 | Participants3 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkWritingBench | Score86.70% | Rank03 | Participants15 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkDocVQAtest | Score96.50% | Rank04 | Participants11 | Percentile70.00% | EvidenceC | Evaluated |
| BenchmarkEmbSpatialBench | Score0.84 points | Rank04 | Participants8 | Percentile57.14% | EvidenceC | Evaluated |
| BenchmarkHypersim | Score0.11 points | Rank04 | Participants4 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score79.10% | Rank04 | Participants23 | Percentile86.36% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (en) | Score66.80% | Rank04 | Participants14 | Percentile76.92% | EvidenceC | Evaluated |
| BenchmarkCC-OCR | Score81.50% | Rank05 | Participants18 | Percentile76.47% | EvidenceC | Evaluated |
| BenchmarkCreative Writing v3 | Score85.70% | Rank05 | Participants13 | Percentile66.67% | EvidenceC | Evaluated |
Qwen3 VL 235B A22B Thinking Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycreative writing | Rank12 | Rating / score1,229.91 | Votes219 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank13 | Rating / score1,217.58 | Votes219 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank55 | Rating / score1,234.36 | Votes298 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank57 | Rating / score1,197.58 | Votes176 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank59 | Rating / score1,220.84 | Votes163 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank59 | Rating / score1,181.27 | Votes176 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank60 | Rating / score1,212.59 | Votes471 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank60 | Rating / score1,211.89 | Votes1,327 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank61 | Rating / score1,215.91 | Votes979 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank61 | Rating / score1,206.23 | Votes2,394 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank61 | Rating / score1,226.14 | Votes298 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank66 | Rating / score1,188.95 | Votes163 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank66 | Rating / score1,208.61 | Votes471 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank66 | Rating / score1,200.10 | Votes1,327 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry mathematical | Rank67 | Rating / score1,435.77 | Votes372 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank67 | Rating / score1,193.69 | Votes979 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank69 | Rating / score1,416.77 | Votes179 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank70 | Rating / score1,187.83 | Votes2,394 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank75 | Rating / score1,414.63 | Votes179 | ObservationsN/A | Result date |
| Arenatext | Categoryexpert | Rank83 | Rating / score1,424.36 | Votes378 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank85 | Rating / score1,429.75 | Votes372 | ObservationsN/A | Result date |
| Arenatext | Categoryenglish | Rank91 | Rating / score1,419.86 | Votes3,458 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank92 | Rating / score1,418.25 | Votes431 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank92 | Rating / score1,411.62 | Votes416 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank92 | Rating / score1,350.24 | Votes219 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank93 | Rating / score1,351.53 | Votes219 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank93 | Rating / score1,403.52 | Votes375 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank94 | Rating / score1,442.96 | Votes434 | ObservationsN/A | Result date |
| Arenatext | Categorycoding | Rank94 | Rating / score1,426.09 | Votes1,614 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry entertainment and sports and media | Rank95 | Rating / score1,369.90 | Votes1,434 | ObservationsN/A | Result date |
Qwen3 VL 235B A22B 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 $0.287 input, $2.87 output per 1M via Merge Gateway
- Tracked offerings
- 10
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMerge Gateway | Provider model IDqwen/qwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.287 | Output / 1M$2.87 | Context131.1K | Updated |
| ProviderOrcaRouter | Provider model IDqwen/qwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.40 | Output / 1M$4 | Context131.1K | Updated |
| ProviderOpenRouter | Provider model IDqwen/qwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.40 | Output / 1M$4 | Context131.1K | Updated |
| ProviderEden AI | Provider model IDqwen/qwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.40 | Output / 1M$4 | Context131.1K | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.40 | Output / 1M$4 | Context131.1K | Updated |
| ProviderNanoGPT | Provider model IDqwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.50 | Output / 1M$6 | Context32.8K | Updated |
| ProviderJalapeno Cloud | Provider model IDQwen3-VL-235B-A22B-Thinking | Regionglobal | Input / 1M$0.98 | Output / 1M$3.95 | Context131.1K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3-VL-235B-A22B-Thinking | Regionglobal | Input / 1M$0.98 | Output / 1M$3.95 | Context131.1K | Updated |
| ProviderNovitaAI | Provider model IDqwen/qwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.98 | Output / 1M$3.95 | Context131.1K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3-vl-235b-a22b-thinking | Regionglobal | Input / 1M$0.98 | Output / 1M$3.95 | Context131.1K | Updated |
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 Thinking Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 VL 235B A22B 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 235B A22B Thinking Specifications
Technical details for the model's default version.
- Version
- Qwen3 VL 235B A22B Thinking
- 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
- Yes
- License
- Apache 2.0
Qwen3 VL 235B A22B Thinking Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionQwen3 VL 235B A22B Thinking | Released | LLMBoard44.41 | Parameters236B | Context262.1K | Max output262.1K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3 VL 235B A22B Thinking
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 Max
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3 235B A22B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 235B A22B
Alibaba Cloud / Qwen Team
AC
Qwen3.5 9B
Alibaba Cloud / Qwen Team
AC
Qwen3 Next 80B A3B Thinking
Alibaba Cloud / Qwen Team
What is Qwen3 VL 235B A22B Thinking?
Key information about Qwen3 VL 235B A22B Thinking and its available data.
Qwen3 VL 235B A22B Thinking is a model from Alibaba Cloud / Qwen Team that supports visual understanding, visual agents, visual coding, spatial perception, video understanding, OCR in 32 languages, and multimodal reasoning.
It uses Interleaved-MRoPE, DeepStack, and Text-Timestamp Alignment, with a native 256K context window expandable to 1M.
Data as of 2026-09-08.
FAQ
Common questions about Qwen3 VL 235B A22B Thinking.
When was Qwen3 VL 235B A22B Thinking released?
Qwen3 VL 235B A22B Thinking's default version was released on Sep 22, 2025.
How much does Qwen3 VL 235B A22B Thinking cost?
No official standard PAYG price is currently available for Qwen3 VL 235B A22B Thinking. The lowest tracked third-party offer starts at $0.287 input and $2.87 output via Merge Gateway.
Who created Qwen3 VL 235B A22B Thinking?
Qwen3 VL 235B A22B Thinking was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 VL 235B A22B Thinking?
The default version has a 262.1K token context window.
Is Qwen3 VL 235B A22B Thinking open weight?
Yes. The default version is marked as open weight under Apache 2.0.