Gemini Robotics-ER 1.6 Preview

Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

RELEASE DATEApr 14, 2026
WEIGHTSClosed weights
CONTEXT WINDOW131.1K
MAX OUTPUT65.5K
REASONINGYes
TOOL CALLINGYes
INPUTStext, image, video, audio
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.