Alternatives to EmbeddingGemma

2024 BAAI multilingual embedding snapshot. Not a 2026 MIRACL or MTEB crown.

Previous Qwen3 embedding snapshot.

Previous Cohere embed snapshot. Not a $0.10/1M 2026 default.

2024 NVIDIA embedding snapshot.

2024 OpenAI embedding snapshot.

Previous OpenAI embedding snapshot. Not a 2026 embedding crown.

Voyage AI's latest SOTA general-purpose embedding model, ranking first across 8 evaluation domains spanning 100 datasets, outperforming OpenAI and Cohere by 9.74% and 20.71% on average.

Tencent WeChat Vision's universal multimodal embedding family (2B/4B/9B) built on Qwen3.5. Text, image, video, and visual-document inputs map to one L2-normalized embedding space.

An open-source multilingual multimodal chat model from Zhipu AI with advanced thinking capabilities, exceptional coding performance, and enhanced UI generation.

Google Gemini 3.5 Live Translate: leftover live-translate sibling on the live Gemini models page. Not the 2026 Flash default. No invent.

Previous Jina Embeddings v4 snapshot.

Open-weight multilingual TTS from BreezeBlue, built for real-time interaction. Reference-free voice design and reference-guided voice direction, with sub-40m.

Previous DeepSeek coder snapshot. Not a 90.2% HumanEval census.

Previous DeepSeek V2.5 snapshot. Not a 2026 chat+coder default.