# Efficient Code Embeddings from Code Generation Models

Source: [Efficient Code Embeddings from Code Generation Models](<https://www.sota2.com/research/paper/68fa7af11e209131cea85e2c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:20.885Z

Authors: Daria Kryvosheieva, Saba Sturua, Michael G\\"unther, Scott Martens, Han Xiao

Published: 2025-08-29T01:18:15.000Z

## Abstract

jina-code-embeddings is a novel code embedding model suite designed to retrieve code from natural language queries, perform technical question-answering, and identify semantically similar code snippets across programming languages. It makes innovative use of an autoregressive backbone pre-trained on both text and code, generating embeddings via last-token pooling. We outline the training recipe and demonstrate state-of-the-art performance despite the relatively small size of the models, validating this approach to code embedding model construction.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.21290>)

[PDF](<https://arxiv.org/pdf/2508.21290.pdf>)