Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Devstral Small 1.1

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

4096 tokens

Model type

编程大模型

Release date

2025-07-10

Model file size

48GB

MoE architecture

Total params / Active params

240.0B / N/A

Knowledge cutoff

No data

Devstral Small 1.1

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

GitHub link unavailable

Hugging Face

https://huggingface.co/mistralai/Devstral-Small-2507

Live demo

https://chat.mistral.ai/chat

Devstral Small 1.1

Official resources

Paper

Upgrading agentic coding capabilities with the new Devstral models

DataLearnerAI blog

MistralAI发布全新编程大模型：24B开源Devstral Small 1.1在SWE-Bench Verified评分超过旧版DeepSeek R1，编程大模型新的替代

Devstral Small 1.1

API details

API speed

3/5

💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.

Standard pricingStandard

Modality	Input	Output
Text	$0.1	$0.3

Devstral Small 1.1

Benchmark Results

Thinking

编程与软件工程

1 evaluations

Benchmark / mode

Score

Rank/total

SWE-bench Verified

default

53.60

71 / 90

查看评测深度分析与其他模型对比

Devstral Small 1.1

Publisher

MistralAI

View publisher details

Devstral Small 1.1

Model Overview

Devstral Small是法国初创企业MsitralAI开源的一个编程大模型，240亿参数，但是在编程领域的评测结果很好，甚至在SWE-Bench Verified上超过了DeepSeek R1模型。这个模型最早是2025年5月份开源。2025年7月11日，MistralAI发布了一个小幅更新版本，即本模型（Devstral Small 1.1），新版本在SWE-Bench Verfied上提升超过15%。进步明显！

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送