Identity
- Type
- startup
- Country label
- Germany
- HQ country
- Germany
- Founding country
- not in the notes
- Parent
- not in the notes
- Parent country
- not in the notes
- Country basis
- secondary
Where this comes from
Convention D1: a dual label, HQ first, when the HQ, founding or parent country differ.
Models by Class
Models
ModelClassOpennessParametersReleased

FLUX.1 Krea DevKrea.ai, Inc., Black Forest Labsimage generationJul 2025

Links
Organisation
Black Forest Labsstartup, Germany
Models
FLUX.3 Action BaseBlack Forest Labs, robot policy
FLUX 3 ImageBlack Forest Labs, image generation
FLUX 3 VideoBlack Forest Labs, video generation
FLUX.2Black Forest Labs, image generation+14 more
Use Casesnone recorded
Who Runs Itnone recorded
Models 18
FLUX.1 Krea DevKrea.ai, Inc., Black Forest Labs, image generationDeveloper+6
Scores
| Benchmark | Model | Score | Who ran it | Setting |
|---|---|---|---|---|
| Artificial Analysis Image Arena | FLUX1.1 [pro] | 891 Elo | independent | text-to-image, 7,439 samples |
| Artificial Analysis Text-to-Image Arena | FLUX 3 Image | 1,115 Elo | independent | rank shown as 8-11 |
| Artificial Analysis Text-to-Image Arena | FLUX.2 [dev] | 1,000 Elo | independent | approximate rank |
| Artificial Analysis Text-to-Image Arena | FLUX.2 [klein] 4B | 864 Elo | independent | approximate rank |
| Artificial Analysis Text-to-Image Arena | FLUX.2 [klein] 9B | 941 Elo | independent | approximate rank |
| Artificial Analysis Text-to-Video leaderboard | FLUX 3 Video | 1,128 Elo | independent | listed as FLUX 3 |
| LMArena Text-to-Video Arena | FLUX 3 Video | 1,493 Elo | independent | preliminary |
| Qwen-Image-Bench | FLUX 2 Max | 55.33 score | vendor-reported | Qwen chart only; methodology unreleased |
Where this comes from
Every recorded score of this organisation's models, with who ran it. Scores from different settings are not directly comparable.
Sources
- Flux (text-to-image model) - Wikipedia en.wikipedia.org https://en.wikipedia.org/wiki/Black_Forest_Labs
- Black Forest Labs FLUX 3 Multimodal Video Model - DataNorth datanorth.ai https://datanorth.ai/news/black-forest-labs-releases-flux-3
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Black Forest Labs", https://aurion.semai.id/organisations/black-forest-labs/, records of October 2026.