Mistral Large
Open Sourcedi Mistral AI · Rilascio 2024-02-26
30.0
punteggio medio
$2.00/1M
Prezzo Input
$6.00/1M
Prezzo Output
128K tokens (~64 books)
Finestra di Contesto
text
Tipo
Tested on 8 benchmarks with 30.0% average. Top scores: Lech Mazur Writing (69.0%), Aider — Code Editing (60.2%), MMLU (58.4%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| Lech Mazur Writing | knowledge | 69.0 | |
| Aider — Code Editing | coding | 60.2 | |
| MMLU | knowledge | 58.4 | |
| MATH level 5 | math | 24.5 | |
| GPQA diamond | knowledge | 18.4 | |
| SimpleBench | reasoning | 7.0 | |
| OTIS Mock AIME 2024-2025 | math | 1.9 | |
| FrontierMath-2025-02-28-Private | math | 0.3 |