FLUX 3 Action
Open-weight 7B model that predicts robot actions from video
Free
Multimodal
7B
parameters
Other
license
Sep 2026
released
Black Forest Labs published FLUX 3 Action on September 23, 2026, a 7-billion-parameter open-weight model that predicts robot actions from video. It scored 42.2% on NVIDIA’s RoboLab-120 benchmark compared with 36.8% for NVIDIA’s own Cosmos 3 Nano, using less than half the parameters. Weights are released on Hugging Face under a new FLUX Kommunity License.
// similar models in Multimodal
Llama 5
Meta's next flagship open-weight multimodal model, built for on-device and datacenter use alike
Meta AI · Multimodal · Free
Gemini 3 Pro
Google's flagship multimodal model with a 1M-token context window
Google DeepMind · Multimodal · Paid
Gemini 3.5 Pro
Google's next-generation frontier model, announced but not yet fully released
Google DeepMind · Multimodal · Paid
GPT-4o
OpenAI's omni model, natively multimodal across text, image, and audio
OpenAI · Multimodal · Paid
Gemini 3.8 Flash
Google's successor to Gemini 3.7 Flash, shipped three weeks later with agentic gains
Google DeepMind · Multimodal · Paid
Gemini 3.7 Flash
Google's successor to Gemini 3.6 Flash, shipped three weeks later with cheaper output pricing
Google DeepMind · Multimodal · Paid