Claude 3.5 Sonnet
por Anthropic 路 Publicado el 2024-10-22
28.8
puntuaci贸n promedio
$6.00/1M
Precio de entrada
$30.00/1M
Precio de salida
200K tokens (~100 books)
Ventana de contexto
multimodal
Tipo
Tested on 10 benchmarks with 28.8% average. Top scores: MMLU (82.0%), MATH level 5 (51.7%), VideoMME (46.7%).
Puntuaciones de benchmark
| Benchmark | Categor铆a | Puntuaci贸n | Bar |
|---|---|---|---|
| MMLU | knowledge | 82.0 | |
| MATH level 5 | math | 51.7 | |
| VideoMME | multimodal | 46.7 | |
| GPQA diamond | knowledge | 38.7 | |
| WeirdML | coding | 31.0 | |
| Cybench | coding | 17.5 | |
| SimpleBench | reasoning | 13.0 | |
| OTIS Mock AIME 2024-2025 | math | 6.4 | |
| FrontierMath-2025-02-28-Private | math | 1.0 | |
| FrontierMath-Tier-4-2025-07-01-Private | math | 0.1 |
Modelos similares
Meta
28.7
Anthropic
28.7
OpenAI
28.6
Meta
29.1