Gemini Embedding 2
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
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 22, 2026
WEIGHTSClosed weights
CONTEXT WINDOW8.2K
MAX OUTPUT3.1K
REASONINGNo
TOOL CALLINGNo
INPUTStext, image, audio, video, pdf
OUTPUTStext
Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.