Model families
Compare representation, action conditioning, spatial output, and availability without collapsing unlike evidence into one score.
8 models
DreamerV3
A latent-dynamics reinforcement-learning system that learns behavior from imagined trajectories.
Meta AI · 2025-06-11V-JEPA 2
A predictive video representation model adapted for action-conditioned robot planning.
Google DeepMind · 2025-08-05Genie 3
A research preview for interactively generated video worlds controlled in real time.
NVIDIA · 2026-06-02Cosmos 3
An open development stack for multimodal world foundation models and physical AI.
World Labs · 2026-09-01Atlas
A spatial world model reported to generate persistent multimodal 3D worlds and video.
Runway · 2025-12-11GWM-1
Runway's general world model research spanning simulated environments and robotics.
Waymo · 2026-02-06Waymo World Model
A driving-focused generative simulator for diverse and counterfactual road scenes.
Wayve · 2025-12-02GAIA-3
Wayve's multi-view generative world model for driving simulation and evaluation.