This page may contain stale information. Last updated: 2026-06-01

Overview

NVIDIA Cosmos 3 is an open frontier foundation model for physical-ai announced at GTC Taipei on May 31, 2026. It is the first fully open “omnimodel” unifying vision reasoning, world generation, and action prediction in a single Mixture-of-Transformers (MoT) architecture.

Model Variants

ModelParametersTarget HardwareUse Case
Cosmos 3 Nano16BRTX PRO 6000Real-time robotics inference
Cosmos 3 Super64BHopper/BlackwellSynthetic data generation, advanced reasoning
Cosmos 3 EdgeTBDEdge devicesReal-time inference (coming)

Architecture

  • Reasoner tower: Autoregressive VLM interpreting multimodal inputs (text, images, video)
  • Generator tower: Diffusion-based physics-aware video and action generation

Benchmarks

Leads open-source models on VANTAGE-Bench, PAI-Bench, R-Bench Physics-IQ, RoboLab, and Artificial Analysis text-to-image/image-to-video leaderboards. NVIDIA HUE (Human Evaluation) framework for fine-grained quality assessment.

Ecosystem

  • Open weights on Hugging Face, code on GitHub
  • Six SDG datasets (robotics, driving, warehouse, physics, human motion, spatial reasoning)
  • Cosmos NIM microservices for production deployment
  • Cosmos Coalition: Agile Robots, Black Forest Labs, Generalist, LTX, Runway, Skild AI

"Months to days" training cycle claims are NVIDIA-stated marketing — not independently verified.

Sources