DataLearner logo
DE

Devstral Medium

Coding model

Devstral Medium

Release date: 2025-07-10Updated: 2025-07-11 15:17:36777
Live demoGitHubHugging FaceCompare
Parameters
Not disclosed
Context length
128K
Chinese support
Supported
Reasoning ability

Devstral Medium is an AI model published by MistralAI, released on 2025-07-10, for Coding model, and 128K context length, with a 61.60 score on SWE-bench Verified.

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

Devstral Medium

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
4K tokens
Model type
Coding model
Modality (in / out)
Text → Text
Release date
2025-07-10
Model file size
No data
MoE architecture
No
Total params / Active params
No data / N/A
Knowledge cutoff
No data
Devstral Medium

Open source & experience

Code license
Proprietary
Weights license
Proprietary
GitHub repo
GitHub link unavailable
Hugging Face
Hugging Face link unavailable
Devstral Medium

Official resources

Paper
DataLearnerAI blog
Devstral Medium

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard
TypeConditionInputOutput
Text-$0.400/ 1M$2.00/ 1M
Devstral Medium

Benchmark Results

Devstral Medium currently shows benchmark results led by SWE-bench Verified (80 / 113, score 61.60). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking

Coding and Software Engineer

1 evaluations
Benchmark / mode
Score
Rank/total
61.60
80 / 113

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Devstral Medium

Publisher

Devstral Medium

Model Overview

Devstral Medium is an AI model published by MistralAI, released on 2025-07-10, for Coding model, and 128K context length, with a 61.60 score on SWE-bench Verified.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code