o1-preview
por OpenAI 路 Publicado el 2024-01-01
36.0
puntuaci贸n promedio
N/A
Precio de entrada
N/A
Precio de salida
N/A
Ventana de contexto
text
Tipo
Tested on 7 benchmarks with 36.0% average. Top scores: MATH level 5 (81.7%), WeirdML (47.6%), GPQA diamond (33.8%).
Puntuaciones de benchmark
| Benchmark | Categor铆a | Puntuaci贸n | Bar |
|---|---|---|---|
| MATH level 5 | math | 81.7 | |
| WeirdML | coding | 47.6 | |
| GPQA diamond | knowledge | 33.8 | |
| OTIS Mock AIME 2024-2025 | math | 31.0 | |
| SimpleBench | reasoning | 30.0 | |
| ARC-AGI | reasoning | 18.0 | |
| Cybench | coding | 10.0 |