SEAIAug 8, 2025

Devstral: Fine-tuning Language Models for Coding Agent Applications

DeepMind
arXiv:2509.25193v112 citationsh-index: 27Has Code
Originality Synthesis-oriented
AI Analysis

This work addresses the need for lightweight, high-performance models for coding agents, offering an incremental improvement in efficiency for software development tasks.

The paper tackles the problem of developing efficient language models for coding agent applications by introducing Devstral-Small, a 24B model that achieves competitive performance compared to much larger models, specifically being the best among those below 100B size.

We introduce Devstral-Small, a lightweight open source model for code agents with the best performance among models below 100B size. In this technical report, we give an overview of how we design and develop a model and craft specializations in agentic software development. The resulting model, Devstral-Small is a small 24B model, fast and easy to serve. Despite its size, Devstral-Small still attains competitive performance compared to models more than an order of magnitude larger.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes