Nomic Logo

Why Choose Nomic Embeddings?

High Performance

Our models consistently outperform competitors on industry benchmarks like MTEB and MIRACL.

Open Source

Full access to model weights, training data, and code. No vendor lock-in or API dependencies.

Cost Efficient

Compact models with efficient inference. Run locally or in the cloud at a fraction of the cost.

Efficient Models. Uncompromising Performance.

ModelAvgBittext MiningClass.Clust.Pair Class.RerankingRetrievalSTS$/1M Token
Nomic Embed V262.4865.1260.3745.5976.3361.7257.2671.03$0.01
Voyage 3 Lite60.8860.1257.9345.6975.0760.2958.9268.20$0.02
OpenAI Embed 3 Small58.6450.3255.1646.7876.6459.9452.2469.42$0.02
Arctic Embed M 2.058.4453.7354.3843.0274.8661.6754.8366.60$0.01
Nomic Embed v2 provides best in class performance per dollar on the MMTEB benchmark.
ModelAvgarbndeenesfafifrhiidjakoruswtethyozh
Nomic Embed v266.076.773.656.654.756.359.277.155.860.554.267.065.965.266.382.678.378.359.5
Voyage-3-Large59.569.668.346.248.443.851.170.839.854.847.262.363.957.867.976.774.575.652.1
OpenAI Text Embedding 3 Large54.9------------------
Nomic Embed v2 achieves state-of-the-art performance on the multilingual MIRACL benchmark.
ModelPythonJavaRubyPHPJavaScriptGo
Nomic Embed Code81.680.581.972.377.193.8
Voyage Code 380.980.584.671.779.293.2
Nomic CodeRankEmbed-137M78.476.979.368.871.492.7
OpenAI Embed 3 Large70.872.975.359.668.187.6
CodeSage Large v274.272.376.765.272.584.6
The Nomic Embed Code suite achieves state-of-the-art performance on the CodeSearchNet benchmark.
ModelAverageMIT BioEcon FoodAXAFood Multi LingualAXA Multi LingualMIT Bio Multi LingualEcon Multi LingualFood ESG
Nomic Embed PDF0.60340.67050.56260.55180.65940.54270.57910.63840.52040.7060
T-Systems ColQwen2.5-3B0.59900.65300.54800.51700.69300.53300.60000.61700.51200.7210
Llama Index vdr-2b-multi-v10.58400.60600.61200.50300.68800.51200.61000.56900.52800.6310
Voyage Multimodal 30.55000.56400.58800.47200.64100.46200.59500.51500.55000.5610
Nomic Embed PDF delivers superior document embedding performance for PDF search and retrieval.

The Developer's Choice

Benchmarks can be gamed. Usage can't. Join the 35+ Million developers who trust Nomic embedding models for their production applications.

Embedding Solutions for Any Application

The Nomic Embedding Ecosystem is designed to provide the best embedding models for any application. We offer a range of models for different use cases, including multilingual, multimodal, code, and document search applications.

Nomic Embed v2

A state of the art multilingual embedder with a mixture-of-experts architecture.

Key Features:

  • SOTA performance on the MIRACL benchmark
  • Support for 100+ languages
  • 305M active parameters for efficient inference
  • Open weights, data, and code

Nomic Embed Text v1.5

The most popular open source text embedder on Hugging Face.

Key Features:

  • Outperforms OpenAI Embeddings on the MTEB benchmark
  • Matryoshka and Binary embeddings for efficient storage
  • 137M parameters for efficient inference
  • Open weights, data, and code

Nomic Embed Vision v1.5

A vision embedder aligned to the Nomic Embed Text v1.5 latent space.

Key Features:

  • Multimodal extension to Nomic Embed Text v1.5
  • Strong performance across text, image, and mixed modality search in a unified latent space
  • Open weights, data, and code

Nomic Embed Code

A state of the art code embedding model.

Key Features:

  • SOTA performance on the CodeSearchNet benchmark
  • Supports Python, Javascript, Java, Go, PHP, and Ruby
  • Pair with Nomic CodeRankEmbed-137M efficient inference
  • Open weights, data, and code
nomic logo
nomic logonomic logo nomic logo nomic logonomic logonomic logo nomic logo nomic logo
“Henceforth, it is the map that precedes the territory” – Jean Baudrillard