GPT-4o (2024-11-20)
por OpenAI 路 Publicado el 2024-11-20
28.6
puntuaci贸n promedio
$2.50/1M
Precio de entrada
$10.00/1M
Precio de salida
128K tokens (~64 books)
Ventana de contexto
multimodal
Tipo
Tested on 17 benchmarks with 28.6% average. Top scores: MMLU (84.1%), Lech Mazur Writing (81.8%), GeoBench (71.0%).
Puntuaciones de benchmark
| Benchmark | Categor铆a | Puntuaci贸n | Bar |
|---|---|---|---|
| MMLU | knowledge | 84.1 | |
| Lech Mazur Writing | knowledge | 81.8 | |
| GeoBench | knowledge | 71.0 | |
| VideoMME | multimodal | 62.5 | |
| MATH level 5 | math | 49.8 | |
| GPQA diamond | knowledge | 30.5 | |
| WeirdML | coding | 25.1 | |
| SWE-Bench Verified (Bash Only) | coding | 21.6 | |
| Aider polyglot | coding | 18.2 | |
| Cybench | coding | 12.5 | |
| VPCT | knowledge | 10.0 | |
| The Agent Company | agentic | 8.6 | |
| OTIS Mock AIME 2024-2025 | math | 6.2 | |
| ARC-AGI | reasoning | 4.5 | |
| FrontierMath-2025-02-28-Private | math | 0.3 | |
| GSO-Bench | coding | 0.1 | |
| ARC-AGI-2 | reasoning | 0.1 |
Modelos similares
Meta
28.7
Anthropic
28.7
Anthropic
28.8
Anthropic
28.3