Codestral Embed

We are excited to release Codestral Embed, our first embedding model specialized for code. It performs especially well for retrieval use cases on real-world code data. 

Codestral Embed significantly outperforms leading code embedders in the market today: Voyage Code 3, Cohere Embed v4.0 and OpenAI’s large embedding model.

Codestral Embed can output embeddings with different dimensions and precisions, and the figure below illustrates the trade-offs between retrieval quality and storage costs. Codestral Embed with dimension 256 and int8 precision still performs better than any model from our competitors. The dimensions of our embeddings are ordered by relevance. For any integer target dimension n, you can choose to keep the first n dimensions for a smooth trade-off between quality and cost.

Results

Below  we show the performance of Codestral Embed for several categories. The details of the benchmarks corresponding to each category can be found in the table in the “Benchmarks details” section.

SWE-Bench is based on a dataset of real-world GitHub issues and corresponding fixes, and is especially relevant for retrieval-augmented generation for coding agents. Text2Code (GitHub) contains benchmarks relevant for giving context for code completion or edition. We believe that these two categories are especially relevant to code assistants. 

Use cases

Codestral Embed is optimized for high-performance code retrieval and semantic understanding. It enables a range of practical applications across development workflows, especially when working with large-scale code corpora. 

1. Retrieval-augmented generation 

Codestral Embed facilitates rapid and efficient context retrieval for code completion, editing, or explanation tasks. It is ideal for AI-powered software engineering in copilots or coding agent frameworks.