Signal SentrySearchUpdated Nov 20, 05:30 UTCAM Drop
Models · scorecard

Embeddinggemma 2

What the vendor claims, next to what independent boards measured. The two are never mixed in one column.

At a glance

OpenRouter does not list this model, so there is no price or context window here.

What the vendor claims

Quoted word for word from the vendor's own launch post or model card. Claims, not measurements.

Scores the vendor claims, each with its source and the quoted line
BenchmarkClaimedSource
MTEB CodeThe source says: delivering a significant 9.92-point improvement on code performance (in MTEB Code, from 68.76 to 78.68)78.68Google DeepMind · Oct 6From Drop #009 · Wed, Oct 7, 2026 · Morning

Independent results

Measured by independent sources (Epoch AI, LMArena, OpenRouter's benchmark runs, τ²-bench, Vectara), not by the vendor. "Listed as" is the source's own name for the model, so you can check our match.

No independent results yet. They appear here as Epoch AI and LMArena add this model.

In the Drops

Models

Google releases Foresight, an offline meeting note-taker for Mac

TechCrunch says Google AI Edge Foresight runs fully offline on Apple Silicon, using the 740-million-parameter EmbeddingGemma 2 to capture meeting notes and a Gemma 4-powered assistant to answer questions from notes and documents.

Why it matters: It shows small on-device models doing a job that note-taking startups like Granola sell, with no internet connection needed.

From Drop #012 · Thu, Oct 8, 2026 · Evening
Models

Google releases EmbeddingGemma 2, a 740M open multimodal embedding model

Google DeepMind says it maps text, code, images, audio and video into one space, needs about 191MB of active RAM for text when quantized, and ships under Apache 2.0.

Why it matters: It brings search and RAG on device, without sending data out. Google says its MTEB Code score rose from 68.76 to 78.68.

From Drop #009 · Wed, Oct 7, 2026 · Morning