AC
Qwen2.5 32B
Alibaba Cloud / Qwen Team
Alibaba Cloud / Qwen Team model product
QvQ 72B
An experimental research model focusing on advanced visual reasoning and step-by-step cognitive capabilities.
Updated Aug 17, 2026. Default version: QvQ-72B-Preview
LLMBoard Score14.4QvQ-72B-Preview
Coverage0%3 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
QvQ 72B Benchmark Results
Benchmark scores for QvQ-72B-Preview.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkOlympiadBench | Score20.4% | Rank01 | Participants1 | Percentile100.0% | EvidenceC | Evaluated |
| BenchmarkMathVista | Score71.4% | Rank13 | Participants39 | Percentile68.4% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score70.3% | Rank30 | Participants63 | Percentile53.2% | EvidenceC | Evaluated |
| BenchmarkMathVision | Score35.9% | Rank31 | Participants33 | Percentile6.3% | EvidenceC | Evaluated |
QvQ 72B 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.
QvQ 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.
QvQ 72B Runtime Performance
Provider-specific output speed and catalog latency for QvQ-72B-Preview. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo 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.
QvQ 72B Specifications
Technical details for the model's default version.
- Version
- QvQ-72B-Preview
- Released
- Dec 25, 2024
- Knowledge cutoff
- Unknown
- Parameters
- 73.4B
- Context window
- N/A
- Max output
- N/A
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Qwen
QvQ 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 |
|---|
| VersionQvQ-72B-Preview | Released | LLMBoard14.4 | Parameters73.4B | ContextN/A | Max outputN/A | Open weightsNo | LicenseQwen |
QvQ 72B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to QvQ 72B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
AC
Qwen2.5 VL 7B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 VL 32B
Alibaba Cloud / Qwen Team
AC
Qwen3 VL 4B
Alibaba Cloud / Qwen Team
AC
Qwen2.5 Omni 7B
Alibaba Cloud / Qwen Team
AC
Qwen2 72B
Alibaba Cloud / Qwen Team
What is QvQ 72B?
Key information about QvQ 72B and its available data.
An experimental research model focusing on advanced visual reasoning and step-by-step cognitive capabilities. Achieves strong performance on multi-modal science and mathematics tasks, though exhibits some limitations such as potential language mixing and recursive reasoning loops.
Data as of 2026-08-17.
FAQ
Common questions about QvQ 72B.
When was QvQ 72B released?
QvQ 72B's default version was released on Dec 25, 2024.
How much does QvQ 72B cost?
No official standard PAYG price is currently available for QvQ 72B.
Who created QvQ 72B?
QvQ 72B was created by Alibaba Cloud / Qwen Team.
What is the context window for QvQ 72B?
A context window is not available for the default version.
Is QvQ 72B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer QvQ 72B?
No provider offering is currently linked to the default version.
What models should I compare QvQ 72B with?
Nearby ranked alternatives include Mistral Large 3, Gemma 3 27B, DeepSeek-R1-Distill-Qwen.