Wispr Flow - Don’t type, just speak
Mini toolsVoyage large 2 instruct
At launch, it achieved rank #1 on the MTEB leaderboard with an average score of 68.28, outperforming competing commercial models across retrieval (58.28), classification (81.48), clustering (53.35), and reranking (60.08). The model suits RAG pipelines, semantic search, document classification, clustering, and reranking applications. Batch processing supports up to 120K total tokens per request with a maximum of 1,000 texts per batch. Accessible via API through Python and TypeScript libraries or a REST endpoint.
Overview
voyage-large-2-instruct is a general-purpose text embedding model with a 16K context window and 1024-dimensional output vectors. It is instruction-tuned for enhanced performance on retrieval, classification, clustering, and reranking tasks. At release it ranked #1 on the MTEB leaderboard with an average score of 68.28, outperforming OpenAI v3 large and Cohere English v3.
About Voyage AI
Voyage AI provides best-in-class embedding models and rerankers for search and retrieval over unstructured data, used to power retrieval-augmented generation (RAG) and AI applications. It offers general-purpose, domain-specific (finance, legal, code) and company-specific fine-tuned models. Founded in 2023 and based in Palo Alto, the company was acquired by MongoDB, Inc. in February 2025 and now operates as a MongoDB subsidiary.
View Company Profile
