Alibaba Cloud / Qwen Team model product
Qwen2 VL 72B
An instruction-tuned, large multimodal model that excels at visual understanding and step-by-step reasoning.
Updated Aug 12, 2026. Default version: Qwen2-VL-72B-Instruct
LLMBoard score25.5Qwen2-VL-72B-Instruct
Coverage80%12 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Qwen2 VL 72B Specifications
Technical details for the model's default version.
- Version
- Qwen2-VL-72B-Instruct
- Released
- Aug 29, 2024
- Knowledge cutoff
- Jun 30, 2023
- Parameters
- 73.4B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- tongyi-qianwen
Qwen2 VL 72B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen2 VL 72B Benchmark Results
Benchmark scores for Qwen2-VL-72B-Instruct.
| EgoSchema | 0.8 | 1 | 9 | 100.0% | C | |
| MMVetGPT4Turbo | 0.7 | 1 | 1 | 100.0% | C | |
| MTVQA | 0.3 | 1 | 1 | 100.0% | C | |
| TextVQA | 0.9 | 1 | 15 | 100.0% | C | |
| VCR_en_easy | 0.9 | 1 | 1 | 100.0% | C | |
| DocVQAtest | 1.0 | 3 | 11 | 80.0% | C | |
| MMBench | 0.9 | 4 | 9 | 62.5% | C | |
| MMMUval | 0.6 | 4 | 4 | 0.0% | C | |
| ChartQA | 0.9 | 6 | 24 | 78.3% | C | |
| MVBench | 0.7 | 6 | 17 | 68.8% | C | |
| InfoVQAtest | 0.8 | 8 | 12 | 36.4% | C | |
| OCRBench | 0.9 | 12 | 22 | 47.6% | C | |
| RealWorldQA | 0.8 | 15 | 26 | 44.0% | C | |
| MathVista-Mini | 0.7 | 19 | 23 | 18.2% | C | |
| MMMU-Pro | 0.5 | 60 | 66 | 9.2% | C |
Qwen2 VL 72B Arena Results
Preference and agent-evaluation results for the default version.
| vision style control | overall | 118 | 1085.5 | 5,937 | N/A | |
| vision | overall | 119 | 1047.1 | 5,937 | N/A |
Qwen2 VL 72B 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.
Qwen2 VL 72B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Qwen2-VL-72B-Instruct | 25.5 | 73.4B | N/A | N/A | No | tongyi-qianwen |
What is Qwen2 VL 72B?
Key information about Qwen2 VL 72B and its available data.
An instruction-tuned, large multimodal model that excels at visual understanding and step-by-step reasoning.
It supports image and video input, with dynamic resolution handling and improved positional embeddings (M-ROPE), enabling advanced capabilities such as complex problem solving, multilingual text recognition in images, and agent-like interactions in video contexts.
Data as of 2026-08-11.
Qwen2 VL 72B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Qwen2 VL 72B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
QwQ 32B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 4B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen2.5 VL 72B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 30B A3B
Alibaba Cloud / Qwen Team
FAQ
Common questions about Qwen2 VL 72B.
When was Qwen2 VL 72B released?
Qwen2 VL 72B's default version was released on Aug 29, 2024.
How much does Qwen2 VL 72B cost?
No official standard PAYG price is currently available for Qwen2 VL 72B.
Who created Qwen2 VL 72B?
Qwen2 VL 72B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen2 VL 72B?
A context window is not available for the default version.
Is Qwen2 VL 72B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Qwen2 VL 72B?
No provider offering is currently linked to the default version.
What models should I compare Qwen2 VL 72B with?
Nearby ranked alternatives include Gemini 2.0 Flash, Phi 4 Reasoning Plus, DeepSeek-V3.