Llama 3.3 70B Instruct
Open Sourcedi Meta · Rilascio 2024-12-06
46.9
punteggio medio
$0.10/1M
Prezzo Input
$0.32/1M
Prezzo Output
131K tokens (~66 books)
Finestra di Contesto
text
Tipo
Tested on 8 benchmarks with 46.9% average. Top scores: Chatbot Arena Elo — Overall (1318.0%), IFEval (90.0%), Aider — Code Editing (59.4%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1318.0 | |
| IFEval | language | 90.0 | |
| Aider — Code Editing | coding | 59.4 | |
| BBH (HuggingFace) | general | 56.6 | |
| MATH Level 5 | math | 48.3 | |
| MMLU-PRO | knowledge | 48.1 | |
| MUSR | reasoning | 15.6 | |
| GPQA | knowledge | 10.5 |