Gemini 4 Argon scores 87% on embodied reasoning benchmark ERQA
Argon leads frontier models on the embodied reasoning benchmark ERQA at 87%, and its Real2Sim builds a physics simulation from a single photo and generates 4,500 training episodes.
Google released Gemini 4 Argon yesterday. It scores 87% on ERQA, the embodied reasoning benchmark, first among frontier models. What stood out to me is Real2Sim. How it works: Argon takes one photo of a workspace. It builds a simulation twin with calibrated physics. It generates 4,500 training episodes inside that twin. A robot policy trained on that data went from 56% to 75% success in the real world. With Argon, Google is automating the engineering work around the robot. https://x.com/Google/status/2110041301253075358/video/1