Google ships Gemini 4 Argon for Robotics, scores 87% on ERQA beating all frontier models
IMordatch · x · 2026-10-14
Google's developer blog released Gemini 4 Argon for Robotics, describing a step change in physical understanding, code generation, and visual-semantic reasoning toward physical AGI. On the Embodied Reasoning (ERQA) benchmark for physical/spatial problem solving in 3D environments, Argon scores 87% with pure reasoning, outperforming every other frontier model.
The post shares representative prompts across the robotics lifecycle:
- Robot control: MuJoCo practice before zero-shot control of a Boston Dynamics Spot (12-DoF legs + 6-DoF arm) stepping on a foot-pedal trash bin; closed-loop steering of video world models.
- Real2Sim: physically calibrated simulation twins from robot camera feeds, egocentric human video, or hand-drawn sketches.
- Physical understanding: agentic multimodal hindsight labeling, dexterity understanding, dense value functions and progress estimation.
- Research & self-improvement: action improvement via simulation and iterative self-improvement on hardware.
Related event: Google Launches Gemini 4 Argon for Robotics, Hitting 87% on ERQA(5 posts)→
More from Embodied
- EU privacy watchdog calls for smart glasses to clearly signal when recording — Polymarket · 2026-10-14
- How Argon drives Spot: real2sim skill verification in MuJoCo and map-free navigation — ki_ki_ki1 · 2026-10-14
- Agent Argon reads Spot's SDK docs itself, builds trash-sorting skill on Boston Dynamics robot — chris_j_paxton · 2026-10-14
- Meta researcher recruiting multimodal and robotics interns for next summer, no background needed — liuzhuang1234 · 2026-10-14
- UNITAS: a 1.7B 3D-native world action model hits 99.8% on LIBERO and 85% on real tasks — CUHKSZ · 2026-10-14
- Frontier LLM scores on real robot benchmark double every 6 weeks, 15% to 48% in 3 months — ycombinator · 2026-10-14