FLUX 3 Action is a 7-billion-parameter model derived from Black Forest Labs' video and image generator. Per the company it leads the RoboLab-120 ranking with less than half the parameters of the previous best open model. The weights are free for research, and commercial use needs a separate licence.
- The model takes camera frames, the robot's state and a text command, and returns the next moves and how they will look at the same time.
- Per BFL, its guidance-distilled variant reaches 42.2% success on RoboLab, against 36.8% for Cosmos 3 Nano.
- The FLUX Kommunity licence allows non-commercial use, including robotics; commercial use needs an agreement with BFL.
A company known for image generators releases a model for robots. It sounds like a turn, but it is a natural continuation.
If a model can predict the next frames of a video, it already understands a little about how things move. Black Forest Labs take that understanding and make it predict the arm's next move as well: what the robot will do and how the scene will look afterwards.
Fast and smart together
The most interesting experiment in the report is not the ranking. BFL put a large reasoning model, GPT-6 Astra, in charge, with FLUX 3 Action doing the work and the boss stepping in only when needed.
Pure reasoning solves every task, but by their figures each success costs $13.47 and about 16 minutes. The combination solves 90% and costs $8.77 for about 8 minutes. The slow thinker with fast hands comes out cheaper than the thinker doing everything alone.
The ranking comes from simulation, and both it and the costs are the company's. There is also a test on a real arm: the independent Positronic Robotics ran the model on a Franka robot in its lab, and it completed 28 of 30 attempts across ten tasks. Thirty attempts are a start, not a verdict.
The weights are free for research and hobby. For a robot that will work at a client's, the licence is read first, because robotics is named in it explicitly.