Sobre

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Gemini 2.5 Pro and GPT-4.1 in code-related tasks, at a fraction of the cost. It is designed for generalization across prompt styles and tool use in code agents and frameworks. Devstral Medium is available via API only (not open-weight), and supports enterprise deployment on private infrastructure, with optional fine-tuning capabilities.

Família do Modelo

Devstral 22025-12-09 Devstral Small 22025-12-09 Mistral: Devstral 2 25122025-12-09 Devstral Small (Jul '25)2025-07-10 Devstral Small (May '25)2025-05-21

Benchmarks

MMLU-Pro

70.8%

GPQA Diamond

49.2%

HLE

3.8%

LiveCodeBench

33.7%

SciCode

29.4%

TerminalBench Hard

9.1%

MATH-500

70.7%

AIME

6.7%

AIME 2025

4.7%

IFBench

29.9%

Long Context Recall

28.7%

Tau2

19.9%

Média do MercadoMelhor Score

Devstral Medium

Sobre

Família do Modelo

Posição no Mercado

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Benchmarks

Open Source

Comparação Rápida

Modelos Similares