Alibaba Cloud / Qwen Team model product
Qwen2.5 VL 72B
5 VL 72B is a vision-language llm from Alibaba Cloud / Qwen Team.
Updated Sep 8, 2026. Default version: Qwen2.5 VL 72B Instruct
LLMBoard Score21.6Qwen2.5 VL 72B Instruct
Coverage0%26 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Qwen2.5 VL 72B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Qwen2.5 VL 72B Benchmark Results
Benchmark scores for Qwen2.5 VL 72B Instruct.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAITZ_EM | Score83.20% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAndroid Control Low_EM | Score93.70% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkDocVQA | Score96.40% | Rank01 | Participants28 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMBench-Video | Score2.02% | Rank01 | Participants3 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkMMVet | Score76.19% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkPerceptionTest | Score73.20% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkTempCompass | Score74.80% | Rank01 | Participants2 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAndroid Control High_EM | Score67.36% | Rank02 | Participants3 | Percentile50.00% | EvidenceC | Evaluated |
| BenchmarkEgoSchema | Score76.20% | Rank02 | Participants9 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkMMBench | Score88.00% | Rank02 | Participants9 | Percentile87.50% | EvidenceC | Evaluated |
| BenchmarkMobileMiniWob++_SR | Score68.00% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkChartQA | Score89.50% | Rank03 | Participants26 | Percentile92.00% | EvidenceC | Evaluated |
| BenchmarkAndroidWorld_SR | Score35.00% | Rank06 | Participants8 | Percentile28.57% | EvidenceC | Evaluated |
| BenchmarkMLVU-M | Score74.60% | Rank08 | Participants8 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkVideoMME w/o sub. | Score73.30% | Rank08 | Participants10 | Percentile22.22% | EvidenceC | Evaluated |
| BenchmarkOCRBench | Score88.50% | Rank10 | Participants24 | Percentile60.87% | EvidenceC | Evaluated |
| BenchmarkOCRBench-V2 (en) | Score61.50% | Rank11 | Participants14 | Percentile23.08% | EvidenceC | Evaluated |
| BenchmarkCC-OCR | Score79.80% | Rank12 | Participants18 | Percentile35.29% | EvidenceC | Evaluated |
| BenchmarkMVBench | Score70.40% | Rank12 | Participants18 | Percentile35.29% | EvidenceC | Evaluated |
| BenchmarkScreenSpot | Score87.10% | Rank13 | Participants16 | Percentile20.00% | EvidenceC | Evaluated |
| BenchmarkHallusion Bench | Score55.16% | Rank16 | Participants18 | Percentile11.76% | EvidenceC | Evaluated |
| BenchmarkMMStar | Score70.80% | Rank16 | Participants25 | Percentile37.50% | EvidenceC | Evaluated |
| BenchmarkAI2D | Score88.40% | Rank17 | Participants34 | Percentile51.52% | EvidenceC | Evaluated |
| BenchmarkMathVista-Mini | Score74.80% | Rank17 | Participants25 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkOSWorld | Score8.83% | Rank19 | Participants20 | Percentile5.26% | EvidenceC | Evaluated |
| BenchmarkScreenSpot Pro | Score43.60% | Rank24 | Participants26 | Percentile8.00% | EvidenceC | Evaluated |
| BenchmarkLVBench | Score47.30% | Rank25 | Participants28 | Percentile11.11% | EvidenceC | Evaluated |
| BenchmarkMathVision | Score38.10% | Rank32 | Participants35 | Percentile8.82% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score70.20% | Rank32 | Participants64 | Percentile50.79% | EvidenceC | Evaluated |
| BenchmarkMMMU-Pro | Score51.10% | Rank60 | Participants69 | Percentile13.24% | EvidenceC | Evaluated |
Qwen2.5 VL 72B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorychinese | Rank78 | Rating / score1,106.23 | Votes119 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank78 | Rating / score1,125.42 | Votes119 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank88 | Rating / score1,107.41 | Votes3,768 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank89 | Rating / score1,114.63 | Votes2,169 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank89 | Rating / score1,123.93 | Votes2,169 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank89 | Rating / score1,121.57 | Votes3,768 | ObservationsN/A | Result date |
Qwen2.5 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.
Qwen2.5 VL 72B Runtime Performance
Provider-specific output speed and catalog latency for Qwen2.5 VL 72B 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.
Qwen2.5 VL 72B Specifications
Technical details for the model's default version.
- Version
- Qwen2.5 VL 72B Instruct
- Released
- Jan 26, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 72B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- Yes
- License
- tongyi-qianwen
Qwen2.5 VL 72B 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 |
|---|
| VersionQwen2.5 VL 72B Instruct | Released | LLMBoard21.56 | Parameters72B | ContextN/A | Max outputN/A | Open weightsYes | Licensetongyi-qianwen |
Models similar to Qwen2.5 VL 72B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen3 VL 4B Thinking
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 8B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 72B
Alibaba Cloud / Qwen Team
AC
QwQ 32B
Alibaba Cloud / Qwen Team
AC
Qwen2 VL 72B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 4B
Alibaba Cloud / Qwen Team
What is Qwen2.5 VL 72B?
Key information about Qwen2.5 VL 72B and its available data.
5 VL 72B is a vision-language model designed to recognize objects, analyze text, charts, and layouts in images, understand long videos, perform visual localization, and generate structured outputs from documents.
Data as of 2026-09-08.
FAQ
Common questions about Qwen2.5 VL 72B.
When was Qwen2.5 VL 72B released?
Qwen2.5 VL 72B's default version was released on Jan 26, 2025.
How much does Qwen2.5 VL 72B cost?
No official standard PAYG price is currently available for Qwen2.5 VL 72B.
Who created Qwen2.5 VL 72B?
Qwen2.5 VL 72B was created by Alibaba Cloud / Qwen Team.
What is the context window for Qwen2.5 VL 72B?
A context window is not available for the default version.
Is Qwen2.5 VL 72B open weight?
Yes. The default version is marked as open weight under tongyi-qianwen.
How many API providers offer Qwen2.5 VL 72B?
No provider offering is currently linked to the default version.