Alibaba Cloud / Qwen Team model product
Qwen3 VL 30B A3B
Qwen3 VL 30B A3B is a multimodal large language model for processing text, images, and video.
Updated Oct 23, 2026. Default version: Qwen3 VL 30B A3B Instruct
LLMBoard Score26.5Qwen3 VL 30B A3B Instruct
Coverage80%50 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
Qwen3 VL 30B A3B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 VL 30B A3B Benchmark Results
Benchmark scores for Qwen3 VL 30B A3B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMLVU-M | Score81.30% | Rank02 | Participants8 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkCharadesSTA | Score63.50% | Rank03 | Participants12 | Percentile81.82% | EvidenceC | Evaluated |
| BenchmarkMMMU (val) | Score74.20% | Rank04 | Participants13 | Percentile75.00% | EvidenceC | Evaluated |
| BenchmarkOCRBench | Score90.30% | Rank05 | Participants24 | Percentile82.61% | EvidenceC | Evaluated |
| BenchmarkScreenSpot | Score94.70% | Rank05 | Participants16 | Percentile73.33% | EvidenceC | Evaluated |
| BenchmarkMM-MT-Bench | Score8.10 points | Rank06 | Participants17 | Percentile68.75% | EvidenceC | Evaluated |
| BenchmarkODinW | Score47.50% | Rank06 | Participants16 | Percentile66.67% | EvidenceC | Evaluated |
| BenchmarkBLINK | Score67.70% | Rank09 | Participants17 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkCC-OCR | Score80.70% | Rank09 | Participants18 | Percentile52.94% | EvidenceC | Evaluated |
| BenchmarkCreative Writing v3 | Score84.60% | Rank09 | Participants14 | Percentile38.46% | EvidenceC | Evaluated |
| BenchmarkDocVQAtest | Score95.00% | Rank09 | Participants11 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (en) | Score63.20% | Rank09 | Participants15 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (zh) | Score57.80% | Rank09 | Participants11 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkMVBench | Score72.30% | Rank10 | Participants18 | Percentile47.06% | EvidenceC | Evaluated |
| BenchmarkInfoVQAtest | Score82.00% | Rank11 | Participants12 | Percentile9.09% | EvidenceC | Evaluated |
| BenchmarkMMBench-V1.1 | Score87.00% | Rank11 | Participants20 | Percentile47.37% | EvidenceC | Evaluated |
| BenchmarkCharXiv-D | Score85.50% | Rank12 | Participants18 | Percentile35.29% | EvidenceC | Evaluated |
| BenchmarkMuirBench | Score62.90% | Rank12 | Participants14 | Percentile15.38% | EvidenceC | Evaluated |
| BenchmarkVideo-MME | Score74.50% | Rank12 | Participants17 | Percentile31.25% | EvidenceC | Evaluated |
| BenchmarkLiveBench 20241125 | Score65.40% | Rank13 | Participants15 | Percentile14.29% | EvidenceC | Evaluated |
| BenchmarkWritingBench | Score82.60% | Rank13 | Participants16 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkArena-Hard v2 | Score58.50% | Rank14 | Participants19 | Percentile27.78% | EvidenceC | Evaluated |
| BenchmarkHallusion Bench | Score61.50% | Rank15 | Participants20 | Percentile26.32% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score80.10% | Rank15 | Participants26 | Percentile44.00% | EvidenceC | Evaluated |
| BenchmarkMMStar | Score72.10% | Rank16 | Participants27 | Percentile42.31% | EvidenceC | Evaluated |
| BenchmarkScreenSpot Pro | Score60.50% | Rank16 | Participants26 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score66.30% | Rank17 | Participants20 | Percentile15.79% | EvidenceC | Evaluated |
| BenchmarkOSWorld | Score30.30% | Rank18 | Participants21 | Percentile15.00% | EvidenceC | Evaluated |
| BenchmarkPolyMATH | Score44.30% | Rank18 | Participants23 | Percentile22.73% | EvidenceC | Evaluated |
| BenchmarkInclude | Score71.60% | Rank20 | Participants31 | Percentile36.67% | EvidenceC | Evaluated |
Qwen3 VL 30B A3B 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 30B A3B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.15 input, $0.60 output per 1M via OpenRouter
- Tracked offerings
- 9
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOpenRouter | Provider model IDqwen/qwen3-vl-30b-a3b-instruct | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context262.1K | Updated |
| ProviderNEAR AI Cloud | Provider model IDQwen/Qwen3-VL-30B-A3B-Instruct | Regionglobal | Input / 1M$0.15 | Output / 1M$0.55 | Context16.4K | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDqwen3-vl-30b-a3b-instruct | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context262.1K | Updated |
| ProviderKilo Gateway | Provider model IDqwen/qwen3-vl-30b-a3b-instruct | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context262.1K | Updated |
| ProviderDeep Infra | Provider model IDQwen/Qwen3-VL-30B-A3B-Instruct | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context262.1K | Updated |
| ProviderMerge Gateway | Provider model IDqwen/qwen3-vl-30b-a3b-instruct | Regionglobal | Input / 1M$0.15 | Output / 1M$0.60 | Context131.1K | Updated |
| ProviderNovita AI | Provider model IDqwen/qwen3-vl-30b-a3b-instruct | Regionglobal | Input / 1M$0.20 | Output / 1M$0.70 | Context131.1K | Updated |
| ProviderHugging Face | Provider model IDQwen/Qwen3-VL-30B-A3B-Instruct | Regionglobal | Input / 1M$0.20 | Output / 1M$0.70 | Context131.1K | Updated |
| ProviderPrime Inference | Provider model IDqwen/qwen3-vl-30b-a3b-instruct | Regionglobal | Input / 1M$0.20 | Output / 1M$0.70 | Context262.1K | 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 30B A3B Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 VL 30B A3B 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.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 VL 30B A3B Specifications
Technical details for the model's default version.
- Version
- Qwen3 VL 30B A3B Instruct
- Released
- Sep 22, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 31B
- Context window
- 262.1K
- Max output
- 262.1K
- Inputs
- image, text, video
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 VL 30B A3B 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 30B A3B Instruct | Released | LLMBoard26.49 | Parameters31B | Context262.1K | Max output262.1K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3 VL 30B A3B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 8B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 14B
Alibaba Cloud / Qwen Team
AC
Qwen3 32B
Alibaba Cloud / Qwen Team
AC
Qwen3 30B A3B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen2 VL 72B
Alibaba Cloud / Qwen Team
What is Qwen3 VL 30B A3B?
Key information about Qwen3 VL 30B A3B and its available data.
Qwen3 VL 30B A3B is a multimodal model from Alibaba Cloud / Qwen Team that combines vision, language, and reasoning. It supports up to a 1 million-token context window and tasks including visual understanding, spatial reasoning, long-video comprehension, multilingual OCR, and tool-based interaction.
Data as of 2026-10-22.
FAQ
Common questions about Qwen3 VL 30B A3B.
When was Qwen3 VL 30B A3B released?
Qwen3 VL 30B A3B's default version was released on Sep 22, 2025.
How much does Qwen3 VL 30B A3B cost?
No official standard PAYG price is currently available for Qwen3 VL 30B A3B. The lowest tracked third-party offer starts at $0.15 input and $0.60 output via OpenRouter.
Who created Qwen3 VL 30B A3B?
Qwen3 VL 30B A3B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 VL 30B A3B?
The default version has a 262.1K token context window.
Is Qwen3 VL 30B A3B open weight?
Yes. The default version is marked as open weight under Apache 2.0.