Project AURIONAI Use-Cases Research & Innovation
video generation

FLUX 3 Video

BFL's first video model, early access from 23 Jul 2026, up to 20 s with synchronised audio. Vendor claims 77% and 93% preference against Runway Gen-4.5 and Luma Ray 3.2.

Black Forest LabsBlack Forest LabsGermanyFLUXFamily
Black Forest Labs
Levelmodel
Classvideo generation
Parametersnot in the notes
Contextnot in the notes
Released23 Jul 2026
Opennessproprietary
Runs onnot in the notes
Statusactive

Benchmark Results

independent
Artificial Analysis Text-to-Video leaderboardgenerative media
listed as FLUX 3independent
1,128
8001,0001,200

Score in Elo; the axis starts at 800, as Elo has no zero. Higher is better.

rank 6, AA Text-to-Video leaderboard10 Oct 2026 artificialanalysis.ai
LMArena Text-to-Video Arenagenerative media
preliminaryindependent
1,493 ±17
1,2001,4001,600

Score in Elo; the axis starts at 1,200, as Elo has no zero. Higher is better.

rank 3, LMArena Text-to-Video, updated 21 Sep 202621 Sep 2026 arena.ai
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).

R&D Topics

Text-to-video foundation modelsproduced byJoint audio and video generationproduced by

Identity

Developer
Black Forest Labs
Family
FLUX
Released
23 Jul 2026 sourcessecondary report
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 Unified (Self-Flow)
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
gated preview, API
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.

Lineage

The notes record no lineage for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. Black Forest Labs FLUX 3 Multimodal Video Model - DataNorth datanorth.ai https://datanorth.ai/news/black-forest-labs-releases-flux-3
  2. AA-Video-T2V v2.0 Leaderboard - Top AI Video Models | Artificial Analysis artificialanalysis.ai https://artificialanalysis.ai/video/leaderboard/text-to-video
  3. Text-to-Video Arena: Best AI Video Generators arena.ai https://arena.ai/leaderboard/text-to-video

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "FLUX 3 Video", https://aurion.semai.id/models/black-forest-labs-flux-3-video/, records of October 2026.