Mistral-Small-3.1-24B-Instruct-2503

Name: Mistral-Small-3.1-24B-Instruct-2503
Author: MistralAI

Foundation modelSmall-3.1

Release date: 2025-03-17Updated: 2025-03-18 16:43:34918

Live demoGitHubHugging Face Compare

Parameters

24B

Context length

128K

Chinese support

Supported

Reasoning ability

Mistral-Small-3.1-24B-Instruct-2503 is an AI model published by MistralAI, released on 2025-03-17, for Foundation model, with 24B parameters, and 128K context length, requiring about 48GB storage, under the Apache 2.0 license, with a 88.41 score on HumanEval.

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

Mistral-Small-3.1-24B-Instruct-2503

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

128K tokens

Max output length

No data

Model type

Foundation model

Modality (in / out)

No data

Release date

2025-03-17

Model file size

48GB

MoE architecture

Total params / Active params

24B / N/A

Knowledge cutoff

No data

Mistral-Small-3.1-24B-Instruct-2503

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/Mistral-Small-3.1-24B-Instruct-2503

Live demo

No live demo

Mistral-Small-3.1-24B-Instruct-2503

Official resources

Paper

Mistral Small 3.1

DataLearnerAI blog

Mistral-Small-3.1-24B-Instruct-2503

API details

API speed

No data

No public API pricing yet.

Mistral-Small-3.1-24B-Instruct-2503

Benchmark Results

Mistral-Small-3.1-24B-Instruct-2503 currently shows benchmark results led by HumanEval (13 / 39, score 88.41), MATH (21 / 42, score 69.30), MBPP (15 / 28, score 74.71). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.