Magistral-Medium-2506

Name: Magistral-Medium-2506
Availability: InStock
Author: MistralAI

推理大模型

Release date: 2025-06-10更新于: 2025-06-11 19:29:05649

Live demoGitHubHugging FaceCompare

Parameters

Not disclosed

Context length

128K

Chinese support

Supported

Reasoning ability

Magistral-Medium-2506 is an AI model published by MistralAI, released on 2025-06-10, for 推理大模型, and 128K tokens context length, under the 不开源 license.

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

Magistral-Medium-2506

Model basics

Reasoning traces

Supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

65536 tokens

Model type

推理大模型

Release date

2025-06-10

Model file size

No data

MoE architecture

Total params / Active params

No data / N/A

Knowledge cutoff

No data

Magistral-Medium-2506

Open source & experience

Code license

不开源

Weights license

不开源- 不开源

GitHub repo

GitHub link unavailable

Hugging Face

Hugging Face link unavailable

Live demo

https://chat.mistral.ai/chat?q=

Magistral-Medium-2506

Official resources

Paper

Stands to reason. Magistral

DataLearnerAI blog

No blog post yet

Magistral-Medium-2506

API details

API speed

3/5

No public API pricing yet.

Magistral-Medium-2506

Benchmark Results

Magistral-Medium-2506 currently shows benchmark results led by LiveCodeBench (62 / 109, score 59.36), GPQA Diamond (98 / 166, score 70.83), AIME 2024 (38 / 62, score 73.59). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.