o1-preview
来自 OpenAI · 发布于 2024-01-01
41.5
平均分
N/A
输入价格
N/A
输出价格
N/A
上下文窗口
text
类型
Tested on 9 benchmarks with 41.5% average. Top scores: Chatbot Arena Elo — Overall (1387.7%), MATH level 5 (81.7%), Aider — Code Editing (79.7%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| Chatbot Arena Elo — Overall | arena | 1387.7 | |
| MATH level 5 | math | 81.7 | |
| Aider — Code Editing | coding | 79.7 | |
| 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 |