Levelmodel
Classvideo generation
Parametersnot in the notes
Contextnot in the notes
Releasednot in the notes
Opennessproprietary
Runs onnot in the notes
Statusactive
Benchmark Results
maintainer-run
VBench v1generative media
Quality score; submission-based boardmaintainer-run
85.7
050100
Score in %. Higher is better.
VBench (v1) text-to-video
Total score; submission-based boardmaintainer-run
85.06
050100
Score in %. Higher is better.
rank 9, VBench (v1) text-to-video
VBench-2.0 2.0generative media
Total scoremaintainer-run
66.72
050100
Score in %. Higher is better.
rank 1, VBench-2.0
Creativity scoremaintainer-run
60.85
050100
Score in %. Higher is better.
VBench-2.0
Where this comes from
Every score names who ran it: vendor-reported, maintainer-run or independent. A rank is shown with the population it was ranked in (gap rule 3).
Lineage
successor
Veo 3.1 is a child (successor)high confidencenotesWhere this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.
R&D Topics
Identity
- Developer
- Google DeepMind
- Family
- Veo
- Released
- – sources
- Weights published
- –
- Record checked
- 10 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- not in the notes
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Context length
- not in the notes
- Input
- text
- Output
- video
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- proprietary
- Licence
- Proprietary sources
- Access routes
- not in the notes
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Industry Use Cases
No industry use case links this model.
Links
ModelVeo 3Google DeepMind, video generation
Veo 3Google DeepMind, video generationR&D TopicsText-to-Video Foundation Models
Use Casesnone recorded
Who Runs Itnone recorded
Organisations 1
Sources
- Veo 3.1 , Google DeepMind deepmind.google https://deepmind.google/models/veo/
- VBench Leaderboard - a Hugging Face Space by Vchitect huggingface.co https://huggingface.co/spaces/Vchitect/VBench_Leaderboard
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Veo 3", https://aurion.semai.id/models/google-deepmind-veo-3/, records of October 2026.