llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen2.5 VL 72B

Alibaba Cloud / Qwen Team model product

Qwen2.5 VL 72B

Qwen2.5-VL is the new flagship vision-language model of Qwen, significantly improved from Qwen2-VL. It excels at recognizing objects, analyzing text/charts/layouts in images, acting as a visual agent, understanding long videos (over 1 hour) with event pinpointing, performing visual localization (bounding boxes/points), and generating structured outputs from documents.

Updated Aug 10, 2026. Default version: Qwen2.5 VL 72B Instruct

Compare
LLMBoard score22.8Qwen2.5 VL 72B Instruct
Coverage100%26 benchmark families
Context window131.1KTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Qwen2.5 VL 72B Instruct
Released
Jan 26, 2025
Knowledge cutoff
Apr 1, 2024
Parameters
72B
Context window
131.1K
Max output
8.2K
Inputs
image, text
Outputs
text
Open weights
Yes
License
tongyi-qianwen

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Qwen2.5 VL 72B Instruct category scores

Benchmark results

Published benchmark records for the scored version Qwen2.5 VL 72B Instruct.

30 rows
Columns

Show columns

AITZ_EM0.813100.0%CAug 7, 2026
Android Control Low_EM0.913100.0%CAug 7, 2026
DocVQA1.0126100.0%CAug 7, 2026
MMBench-Video0.013100.0%CAug 7, 2026
MMVet0.812100.0%CAug 7, 2026
PerceptionTest0.712100.0%CAug 7, 2026
TempCompass0.712100.0%CAug 7, 2026
Android Control High_EM0.72350.0%CAug 7, 2026
EgoSchema0.82987.5%CAug 7, 2026
MMBench0.92987.5%CAug 7, 2026
MobileMiniWob++_SR0.7220.0%CAug 7, 2026
ChartQA0.932491.3%CAug 7, 2026
AndroidWorld_SR0.36828.6%CAug 7, 2026
MLVU-M0.7880.0%CAug 7, 2026
VideoMME w/o sub.0.781022.2%CAug 7, 2026
OCRBench0.9102257.1%CAug 7, 2026
MVBench0.7111737.5%CAug 7, 2026
OCRBench-V2 (en)0.611129.1%CAug 7, 2026
CC-OCR0.8121835.3%CAug 7, 2026
ScreenSpot0.9131620.0%CAug 7, 2026
Hallusion Bench0.615166.7%CAug 7, 2026
MMStar0.7152233.3%CAug 7, 2026
AI2D0.9163251.6%CAug 7, 2026
MathVista-Mini0.7162331.8%CAug 7, 2026
OSWorld0.119205.3%CAug 7, 2026
LVBench0.5212413.0%CAug 7, 2026
ScreenSpot Pro0.422248.7%CAug 7, 2026
MathVision0.429329.7%CAug 7, 2026
MMMU0.7316351.6%CAug 7, 2026
MMMU-Pro0.5576512.5%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

No published Arena match

The default version has no published Arena rows, or its source alias has not been resolved.

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No published price snapshot

The default version has no provider offering with 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 versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Qwen2.5 VL 72B InstructJan 26, 202522.872B131.1K8.2KYestongyi-qianwen

What is Qwen2.5 VL 72B?

A concise description based on the published model registry.

Qwen2.5-VL is the new flagship vision-language model of Qwen, significantly improved from Qwen2-VL. It excels at recognizing objects, analyzing text/charts/layouts in images, acting as a visual agent, understanding long videos (over 1 hour) with event pinpointing, performing visual localization (bounding boxes/points), and generating structured outputs from documents.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Qwen2.5 VL 72B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Qwen2.5 VL 72BvsMagistral MediumQwen2.5 VL 72BvsQwen3 VL 4B ThinkingQwen2.5 VL 72BvsLlama 3.3 70BQwen2.5 VL 72BvsNova ProQwen2.5 VL 72BvsMiniCPM SALAQwen2.5 VL 72BvsPhi 4 Reasoning

Models similar to Qwen2.5 VL 72B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#179+0.3
AC

Qwen3 VL 4B Thinking

Alibaba Cloud / Qwen Team

23.1 LLMBoard

DetailsCompare
#186-1.2
AC

Qwen2.5 72B

Alibaba Cloud / Qwen Team

21.6 LLMBoard

DetailsCompare
#173+2.1
AC

Qwen3 VL 8B

Alibaba Cloud / Qwen Team

24.9 LLMBoard

DetailsCompare
#171+2.8
AC

Qwen2 VL 72B

Alibaba Cloud / Qwen Team

25.6 LLMBoard

DetailsCompare
#170+2.9
AC

QwQ 32B

Alibaba Cloud / Qwen Team

25.7 LLMBoard

DetailsCompare
#192-3.4
AC

Qwen3 VL 4B

Alibaba Cloud / Qwen Team

19.3 LLMBoard

DetailsCompare

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 is published under Alibaba Cloud / Qwen Team in the model registry.

What is the context window for Qwen2.5 VL 72B?

The default version has a 131.1K token context window.

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 published provider offering is currently linked to the default version.

What models should I compare Qwen2.5 VL 72B with?

Nearby ranked alternatives include Magistral Medium, Qwen3 VL 4B Thinking, Llama 3.3 70B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai