GE

Gemini Embedding 001

Embedding modelGemini EmbeddingGemini Embedding 001

Gemini Embedding 001

Release date: 2025-07-14Updated: 2025-07-15 16:56:431,184
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
2K
Chinese support
Supported
Reasoning ability

Gemini Embedding 001 is an AI model published by Google Deep Mind, released on 2025-07-14, for Embedding model, and 2K context length, under the 不开源 license, with a 68.37 score on MTEB.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Gemini Embedding 001

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
2K tokens
Max output length
3K tokens
Model type
Embedding model
Modality (in / out)
Text → Embedding
Release date
2025-07-14
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Gemini Embedding 001

Open source & experience

Code license
不开源
Weights license
不开源
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Live demo
No live demo
Gemini Embedding 001

Official resources

Paper
No paper available
Gemini Embedding 001

API details

API speed
4/5
No public API pricing yet.
Gemini Embedding 001

Benchmark Results

Gemini Embedding 001 currently shows benchmark results led by MTEB (3 / 5, score 68.37). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Text Embedding

1 evaluations
Benchmark / mode
Score
Rank/total
68.37
3 / 5

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Gemini Embedding 001

Publisher

Google Deep Mind
View publisher details
Gemini Embedding 001

Model Overview

Gemini Embedding 001 is an AI model published by Google Deep Mind, released on 2025-07-14, for Embedding model, and 2K context length, under the 不开源 license, with a 68.37 score on MTEB.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code