GPT-4o (2024-08-06)
제공 OpenAI · 출시일 2024-08-06
35.6
평균 점수
$2.50/1M
입력 가격
$10.00/1M
출력 가격
128K tokens (~64 books)
컨텍스트 윈도우
multimodal
유형
Tested on 11 benchmarks with 35.6% average. Top scores: Chatbot Arena Elo — Overall (1334.3%), MMLU (79.1%), Aider — Code Editing (71.4%).
벤치마크 점수
| 벤치마크 | 카테고리 | 점수 | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1334.3 | |
| MMLU | knowledge | 79.1 | |
| Aider — Code Editing | coding | 71.4 | |
| VideoMME | multimodal | 62.5 | |
| MATH level 5 | math | 53.3 | |
| GPQA diamond | knowledge | 32.3 | |
| CadEval | coding | 26.0 | |
| Aider polyglot | coding | 23.1 | |
| OTIS Mock AIME 2024-2025 | math | 6.3 | |
| SimpleBench | reasoning | 1.4 | |
| FrontierMath-2025-02-28-Private | math | 0.3 |
유사 모델
OpenAI
35.9
OpenAI
35.2
Alibaba Qwen
35.2
Google DeepMind
36.0