CoIRSource: MTEB Extra Text Boards data
Google · Embedding
embeddinggemma-2
EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space.
Evidence and sources
🤗 google/embeddinggemma-2llminfo IQ 105.1, ranked among embedding models. From 46 benchmarks. Plenty of data behind it.How llminfo IQ is computedReleased 6 Oct 2026Maker HQ: US (according to Google's own website)
Sources: Cloudflare Workers AI, llminfo researchPrimary data from Cloudflare Workers AI
from llminfo research: release date
Input & output
from the model's typeText
Embeddings
Also known as: google/embeddinggemma-2
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works