Mistral
Mistral Large 3
Mistral Large 3 2512 is Mistral’s most capable model to date. It has a sparse mixture-of-experts architecture with 41B active parameters (675B total).
Introducing Mistral 3Model Snapshot
TypeLanguage
ReleaseDec 2, 2025
Context256,000
Tagstool-use, vision
Overall
Rank #302 across 600
15.9
Coding
Rank #207 across 266
20.1
Blended Price
Rank #160 across 379
$0.750/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed68.6 tok/s
First Token0.67s
Max Output256,000
Pricing
Blended$0.750/M
Input$0.500/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 15.9 | #302 |
| Artificial Analysis Coding Index | coding | 20.1 | #207 |
| Artificial Analysis Math Index | math | 38.0 | #166 |
| MMLU-Pro | reasoning | 80.7% | #89 |