Alibaba Cloud / Qwen Team model product
Qwen3 VL 4B Thinking
Qwen3 VL 4B Thinking is a multimodal language model for reasoning across text, images, and video.
Updated Sep 8, 2026. Default version: Qwen3 VL 4B Thinking
LLMBoard Score21.8Qwen3 VL 4B Thinking
Coverage80%48 benchmark families
Context window262.1KTokens
Official input priceN/AOfficial price unavailable
Qwen3 VL 4B Thinking Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen3 VL 4B Thinking Benchmark Results
Benchmark scores for Qwen3 VL 4B Thinking.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMLVU-M | Score75.70% | Rank05 | Participants8 | Percentile42.86% | EvidenceC | Evaluated |
| BenchmarkMuirBench | Score75.00% | Rank05 | Participants12 | Percentile63.64% | EvidenceC | Evaluated |
| BenchmarkMMMU (val) | Score70.80% | Rank06 | Participants13 | Percentile58.33% | EvidenceC | Evaluated |
| BenchmarkCharadesSTA | Score59.00% | Rank08 | Participants12 | Percentile36.36% | EvidenceC | Evaluated |
| BenchmarkHallusion Bench | Score64.10% | Rank09 | Participants18 | Percentile52.94% | EvidenceC | Evaluated |
| BenchmarkInfoVQAtest | Score83.00% | Rank10 | Participants12 | Percentile18.18% | EvidenceC | Evaluated |
| BenchmarkMM-MT-Bench | Score7.70 points | Rank10 | Participants17 | Percentile43.75% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (en) | Score61.80% | Rank10 | Participants14 | Percentile30.77% | EvidenceC | Evaluated |
| BenchmarkScreenSpot | Score92.90% | Rank10 | Participants16 | Percentile40.00% | EvidenceC | Evaluated |
| BenchmarkWritingBench | Score84.00% | Rank10 | Participants15 | Percentile35.71% | EvidenceC | Evaluated |
| BenchmarkDocVQAtest | Score94.20% | Rank11 | Participants11 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkLiveBench 20241125 | Score68.40% | Rank11 | Participants14 | Percentile23.08% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (zh) | Score55.80% | Rank11 | Participants11 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkBLINK | Score63.40% | Rank12 | Participants15 | Percentile21.43% | EvidenceC | Evaluated |
| BenchmarkMMBench-V1.1 | Score86.70% | Rank12 | Participants20 | Percentile42.11% | EvidenceC | Evaluated |
| BenchmarkMulti-IF | Score73.60% | Rank12 | Participants23 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkCharXiv-D | Score83.90% | Rank13 | Participants17 | Percentile25.00% | EvidenceC | Evaluated |
| BenchmarkCreative Writing v3 | Score76.10% | Rank13 | Participants13 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkMMStar | Score73.20% | Rank13 | Participants25 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkBFCL-v3 | Score67.30% | Rank15 | Participants19 | Percentile22.22% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score79.50% | Rank15 | Participants25 | Percentile41.67% | EvidenceC | Evaluated |
| BenchmarkMVBench | Score69.30% | Rank15 | Participants18 | Percentile17.65% | EvidenceC | Evaluated |
| BenchmarkOSWorld | Score31.40% | Rank15 | Participants20 | Percentile26.32% | EvidenceC | Evaluated |
| BenchmarkODinW | Score39.40% | Rank16 | Participants16 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkPolyMATH | Score44.60% | Rank17 | Participants23 | Percentile27.27% | EvidenceC | Evaluated |
| BenchmarkArena-Hard v2 | Score36.80% | Rank18 | Participants19 | Percentile5.56% | EvidenceC | Evaluated |
| BenchmarkCC-OCR | Score73.80% | Rank18 | Participants18 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkERQA | Score47.30% | Rank20 | Participants26 | Percentile24.00% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score84.90% | Rank22 | Participants34 | Percentile36.36% | EvidenceC | Evaluated |
| BenchmarkRealWorldQA | Score73.20% | Rank22 | Participants31 | Percentile30.00% | EvidenceC | Evaluated |
Qwen3 VL 4B 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 4B Thinking Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 0
No provider prices
The default version has no current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Qwen3 VL 4B Thinking Runtime Performance
Provider-specific output speed and catalog latency for Qwen3 VL 4B Thinking. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderDeepInfra | Output Speed8.77 tok/s | Catalog Latency7.53 s | Max Input262.1K | Max Output262.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Qwen3 VL 4B Thinking Specifications
Technical details for the model's default version.
- Version
- Qwen3 VL 4B Thinking
- Released
- Sep 22, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 4B
- Context window
- 262.1K
- Max output
- 262.1K
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- Apache 2.0
Qwen3 VL 4B 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 4B Thinking | Released | LLMBoard21.82 | Parameters4B | Context262.1K | Max output262.1K | Open weightsYes | LicenseApache 2.0 |
Models similar to Qwen3 VL 4B Thinking
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen2.5 VL 72B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B
Alibaba Cloud / Qwen Team
AC
QwQ 32B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 72B
Alibaba Cloud / Qwen Team
AC
Qwen2 VL 72B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 4B
Alibaba Cloud / Qwen Team
What is Qwen3 VL 4B Thinking?
Key information about Qwen3 VL 4B Thinking and its available data.
Qwen3 VL 4B 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 4B Thinking.
When was Qwen3 VL 4B Thinking released?
Qwen3 VL 4B Thinking's default version was released on Sep 22, 2025.
How much does Qwen3 VL 4B Thinking cost?
No official standard PAYG price is currently available for Qwen3 VL 4B Thinking.
Who created Qwen3 VL 4B Thinking?
Qwen3 VL 4B Thinking was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen3 VL 4B Thinking?
The default version has a 262.1K token context window.
Is Qwen3 VL 4B Thinking open weight?
Yes. The default version is marked as open weight under Apache 2.0.
How many API providers offer Qwen3 VL 4B Thinking?
No provider offering is currently linked to the default version.