Odyssey-3 Launches Foundation World Model: Autoregressive Diffusion Tops Physics-IQ with Real-Time Causal Prediction

1 reports archived1 independent sourcesupdated 10/9/2026, 14:41:48

Synthesis & Latest Updates

1 Sources Cross-Validated

Odyssey has released the Odyssey-3 series of foundation world models, with the Pro version setting a new record score of 66.1 on the Physics-IQ Verified benchmark. Utilizing an autoregressive diffusion transformer architecture, the model learns physical dynamics and causal relationships from visual observations, enabling real-time environment prediction based on user actions like viewpoint shifts or event triggers, while ranking first across multiple metrics in WorldMark evaluations.

LATEST/Odyssey has released the Odyssey-3 series of foundation world models, with the Pro version setting a new record score of 66.1 on the Physics-IQ Verified benchmark. Utilizing an autoregressive diffusion transformer architecture, the model learns physical dynamics and causal relationships from visual observations, enabling real-time environment prediction based on user actions like viewpoint shifts or event triggers, while ranking first across multiple metrics in WorldMark evaluations.

HEAT TRENDHourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

TIMELINECoverage timeline

Total 1 reports · Latest first

IT之家 · 智能时代T2·Oct 9, 14:4178 pts
Odyssey-3 Launches Foundation World Model: Autoregressive Diffusion Tops Physics-IQ with Real-Time Causal Prediction
Original: 66.1 分登顶：Odyssey-3 基础世界模型登场，AI 开始理解真实世界
- Odyssey-3 Pro achieved a record-high score of 66.1 on the Physics-IQ Verified video-to-video benchmark.
- Utilizes an autoregressive diffusion transformer architecture supporting first/third-person navigation and real-time environmental state response prediction.
- Ranked first in WorldMark evaluations across stylized and realistic environments, balancing physical accuracy with generation cost.
View Evidence Original Source