Mistral
Magistral Medium 1
Complex thinking, backed by deep understanding, with transparent reasoning you can follow and verify. The model excels in maintaining high-fidelity reasoning across numerous languages, even when switching between languages mid-task.
Introducing Mistral 3Model Snapshot
TypeLanguage
ReleaseJun 10, 2025
Context128,000
Tagsreasoning, tool-use, vision
Overall
Rank #345 across 600
12.5
Coding
No rank
n/a
Blended Price
No rank
n/a
Strength Profile
Percentile score by analysis domain.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Max Output64,000
Streaming speed is not measured for this model yet.
Pricing
Blended-
Input-
Output-
Catalog$2.00/M in / $5.00/M out
Metadata
Providers
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 12.5 | #345 |
| Artificial Analysis Math Index | math | 40.3 | #158 |
| MMLU-Pro | reasoning | 75.3% | #152 |
| GPQA | reasoning | 67.9% | #287 |
| Humanity's Last Exam |