Magistral Medium 1

Magistral Medium 1

Mistral · Released Jun 10, 2025 Emerging
Intelligence #342 / 561
26.1 Our Score
AA Index #171 / 368
18.8 Artificial Analysis
Input
Not priced
Output
Not priced
Context
Not reported

Analysis Summary

Magistral Medium 1 sits in the Emerging tier on our leaderboard, ranked #342 of 561 published models on overall intelligence. At $0.000 input and $0.000 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

Magistral Medium 1 from Mistral offers improved reasoning and coding over its smaller sibling, with strong MMLU Pro and LiveCodeBench scores; a capable mid-tier reasoning model at moderate cost.

Assessed May 14, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence4Technical2.7Value0Content4
Intelligence 4/10
Technical 2.7/10
Content 4/10
Value 0/10

Performance Indices

Source: Artificial Analysis

18.8 Intelligence Index
16 Coding Index
16.1 Agentic Index
40.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 67.9% Graduate-level scientific reasoning
HLE 9.5% Humanity's Last Exam
MMLU Pro 75.3% Multi-task language understanding
MATH 500 91.7% Mathematical problem-solving
AIME 70% Competition mathematics
AIME 2025 40.3% Competition mathematics (2025)
SciCode 29.7% Scientific computing

Technical

LiveCodeBench 52.7% Live coding evaluation
TerminalBench Hard 9.1% Agentic terminal tasks
τ²-Bench 23.1% Conversational agent benchmark

Content

IFBench 25.1% Instruction following

Benchmark data from Artificial Analysis and Hugging Face

How does Magistral Medium 1 stack up?

Compare side-by-side with other emerging models.

Compare Models

Model Information

ProviderMistral
Release Date June 10, 2025
Status Active

Leaderboard Categories