Magistral Small

by Mistral

Magistral Small is Mistral's 24B-parameter open-source reasoning model, released under the Apache 2.0 license and available for self-deployment. It delivers strong mathematical and logical reasoning in a lightweight package that runs well on local hardware. Designed for transparent, step-by-step reasoning, Magistral Small works through multi-step problems across professional domains and exposes interpretable thought processes in the user's language. It reasons across multiple languages including English, French, Spanish, German, Italian, Arabic, Russian, and Simplified Chinese. As an open-weight model with a 128k token context window, Magistral Small balances capability and efficiency. Developers can inspect, modify, and build on it freely while keeping reasoning quality competitive with larger models.

Key info

Input
Output
Features
Context window
128K
Max output
8K

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#313 of 534 LLMs
TierEfficient
Output speed0 tok/s
First token0.00s
Intelligence Index10.7
Math Index41.3
Reasoning & knowledge
MMLU-Pro
75%
GPQA Diamond
64%
Humanity's Last Exam
7%
Long-context reasoning
0%
Coding
LiveCodeBench
51%
SciCode
24%
Agentic & tool use
Terminal-Bench Hard
5%
τ²-Bench Telecom
27%
Math & instruction following
AIME 2025
41%
IFBench
25%

Available routes

No routes currently available — Magistral Small isn't routed through the Opper gateway right now. It may return.

Contact us about this model →

Available models from Mistral

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Magistral Small by Mistral — not currently on Opper | Opper AI