Google DeepMind·· 3 d ago
Gemini 4 Argon for Robotics
Gemini 4 Argon for Robotics
AI summary
Gemini 4 Argon marks a step change in physical understanding, code generation, and visual-semantic reasoning—unlocking new workflows across the robotics stack and accelerating progress toward physical AGI. Using pure reasoning, Argon scores 87% on the Embodied Reasoning (ERQA) benchmark, outperforming every other frontier model.
Selection record
Threshold 60Official, first-handFirst 87Second 88
AdmittedSum of both 175 ≥ twice the threshold 120
- Source tier
- Official, first-hand; this tier's threshold is 60
- Pre-filter
- passed：Gemini 4 Argon机器人模型，含AI功能与用法
- Why it was chosen
- Gives Argon's 87% ERQA score and four robotics workflow examples, enough to judge where physical reasoning models can actually be applied.
- Same event
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: Google DeepMind · deepmind.google