Most of reality is never written down. We are building an open science of world models.

Physical Reasoning is an open source research collective studying world models: systems that learn the dynamics of the physical world and predict what happens next. We work across robotics, self-driving, prediction markets, and the sciences.

Read our blog →

Most world-model research is conducted within a small number of industrial labs and evaluated on proprietary data. Evaluation protocols are not standardized, and whether a model has learned the underlying dynamics or only the surface statistics of its training distribution is rarely measured directly.

The physics of the world should be open. We conduct our research in public, and every result is published, including negative ones, together with the code to reproduce it.

Researchers, builders, and leaders from

Supported with compute from

Research directions

  1. Predictive validity on real-world outcomes

    We elicit forecasts on resolved real-world questions as of their open date and score calibration against realized outcomes. Forecast accuracy is a measurable proxy for world model quality.

  2. Physical consistency of generated video

    A benchmark built from probe tasks with simulator ground truth for gravity, object permanence, and collision, scored by a model-agnostic harness with a public leaderboard.

  3. Representational content of model internals

    Plausible generation is compatible with internals that encode nothing about objects, mass, or velocity. We train probes on model activations to determine what is represented and what is missing.