Llama 3.3 70B Instruct (free)
Open Sourcedi Meta · Rilascio 2024-12-06
29.1
punteggio medio
N/A
Prezzo Input
N/A
Prezzo Output
66K tokens (~33 books)
Finestra di Contesto
text
Tipo
Tested on 8 benchmarks with 29.1% average. Top scores: MMLU (81.7%), MATH level 5 (41.6%), Fiction.LiveBench (33.3%).
Punteggi Benchmark
| Benchmark | Categoria | Punteggio | Bar |
|---|---|---|---|
| MMLU | knowledge | 81.7 | |
| MATH level 5 | math | 41.6 | |
| Fiction.LiveBench | knowledge | 33.3 | |
| GPQA diamond | knowledge | 29.9 | |
| Balrog | knowledge | 23.0 | |
| WeirdML | coding | 14.4 | |
| OTIS Mock AIME 2024-2025 | math | 5.0 | |
| SimpleBench | reasoning | 3.9 |