Gemini 4 Argon for Robotics

Summary

Gemini 4 Argon is a new model that achieves a step change in physical understanding, code generation, and visual-semantic reasoning for robotics. It scores 87% on the Embodied Reasoning (ERQA) benchmark using pure reasoning, outperforming other frontier models. The model can be applied across the entire robotics lifecycle, including robot control, Real2Sim reconstruction, physical understanding, and research self-improvement. Examples include controlling a Spot quadruped to practice foot-pedal trash bin disposal in MuJoCo before executing, zero-shot control of a robotic arm, steering a video world model to rearrange Scrabble tiles, reconstructing simulation twins from robot camera feeds or hand-drawn sketches, and reproducing robotics papers as self-contained MuJoCo WebAssembly browser labs with a single prompt. Argon also performs agentic multimodal hindsight labeling for dexterity understanding and dense value functions, and can self-improve by diagnosing failures and optimizing speed, bridging coding, visual perception, physics simulation, and embodied control toward physical AGI.

Takeaways

1. 1

   Gemini 4 Argon scores 87% on the Embodied Reasoning (ERQA) benchmark using pure reasoning, outperforming other frontier models.

2. 2

   The model can control robots in zero-shot, including mobile manipulation with MuJoCo practice and closed-loop steering of video world models.

3. 3

   Argon can reconstruct physically calibrated simulation twins from robot camera feeds, egocentric human video, or hand-drawn sketches (Real2Sim).

FAQ