AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

GWM-1

Runway·

World Modelsworld-modelcloud

Overview

Runway's first General World Model: an autoregressive model built on top of Gen-4.5 that generates frame by frame, runs in real time at 24 fps and is steered interactively through camera pose, robot commands or audio. Ships as three variants, GWM Worlds for explorable environments, GWM Avatars for speaking characters with facial expression and lip sync, and GWM Robotics for synthetic robot training data, which Runway plans to merge into one model. Announced together with native audio for Gen-4.5 and pitched as more general than Google's Genie 3: a simulator for training agents in domains such as robotics and life sciences.

Capabilities and innovations

Real-time frame-by-frame world simulation at 24 fpsInteractive control via camera pose, robot commands and audioExplorable worlds, avatars and robotics variantsSynthetic training data for robotsAutoregressive world model built on a video generation model (Gen-4.5)Action-conditioned real-time simulation

Benchmarks

No established, comparable metric exists for world models yet. A video model goes from prompt to clip; a world model goes from an image or scene to a navigable space with camera control, which no video or image board measures. No scores and no crown until one exists.

Links

More from Runway

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.