NVIDIA releases Cosmos 3, a fully open physical-AI model ranking first across 7+ robotics and world-generation benchmarks
NVIDIA released Cosmos 3, a fully open physical-AI model on a mixture-of-transformers architecture that handles text, images, video, sound, and physical actions in a single system, ranking first across 7+ benchmarks including Physics-IQ, RoboLab, and VANTAGE-Bench. Open weights, training scripts, and full datasets are on Hugging Face now — Super at 64B and Nano at 16B — giving robotics and AV teams a pretrained foundation that reduces synthetic-data training cycles from months to days.
Source: nvidianews.nvidia.com ↗
Cosmos 3 is the world's first fully open omnimodel that can natively understand and generate text, images, video, ambient sound and actions with leading physics accuracy, reducing physical AI training and evaluation cycles from months to days.
Why this matters
- → Reduces physical AI training cycles from months to days by providing a pretrained foundation model that handles multimodal inputs and action generation.
- → First fully open omnimodel combines vision reasoning, world simulation, and action prediction in one system for robotics and autonomous vehicles.
- → Open weights and datasets on Hugging Face enable broader developer access to state-of-the-art physical AI capabilities.