Gemini 4 Hydrogen ranks fourth on AA-Robotics v0.1
AI summary
Gemini 4 Hydrogen was the leading Google model on the AA-Robotics v0.1 benchmark, ranking fourth overall behind Claude Fable 5.2, GPT-6 Astra and GPT-6.1 Sol. The report said Hydrogen pointed out a minor spill while pouring a drink and an unclosed lid while tidying blocks.
In-depth insight
The result adds evidence about Gemini 4 Hydrogen’s agentic performance and its ability to recognize errors during physical tasks.
Gemini 4 Hydrogen is the leading Google model on AA-Robotics v0.1, sitting fourth overall behind Claude Fable 5.2 (75), GPT-6 Astra (69) and GPT-6.1 Sol (65)
Hydrogen was very honest about its performance, pointing out a minor spill when pouring the drink and an unclosed lid when tidying blocks