Mistral AI

Magistral Medium

Multimodal
Zero-eval

by Mistral AI

+
+
+
+
About

Magistral Medium was introduced as a specialized model for advanced reasoning and analytical tasks, designed to handle complex problem-solving scenarios. Built to serve enterprise and professional applications requiring sophisticated reasoning, it represents Mistral's focus on high-quality analytical capabilities.

+
+
+
+
Timeline
AnnouncedJun 10, 2025
ReleasedJun 10, 2025
Knowledge CutoffJun 1, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Apache 2.0
Performance Overview
Performance metrics and category breakdown

Overall Performance

6 benchmarks
Average Score
52.6%
Best Score
73.6%
High Performers (80%+)
0
+
+
+
+
All Benchmark Results for Magistral Medium
Complete list of benchmark scores with detailed information
AIME 2024
text
0.74
73.6%
Self-reported
GPQA
text
0.71
70.8%
Self-reported
AIME 2025
text
0.65
64.9%
Self-reported
LiveCodeBench
text
0.50
50.3%
Self-reported
Aider-Polyglot
text
0.47
47.1%
Self-reported
Humanity's Last Exam
multimodal
0.09
9.0%
Self-reported
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+