Grok-2 (Dec 2024)
来自 xAI · 发布于 2024-01-01
33.2
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 8 benchmarks with 33.2% average. Top scores: Lech Mazur Writing (63.6%), MATH level 5 (63.5%), Aider — Code Editing (58.6%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| Lech Mazur Writing | knowledge | 63.6 | |
| MATH level 5 | math | 63.5 | |
| Aider — Code Editing | coding | 58.6 | |
| GPQA diamond | knowledge | 38.4 | |
| WeirdML | coding | 22.2 | |
| OTIS Mock AIME 2024-2025 | math | 11.4 | |
| SimpleBench | reasoning | 7.2 | |
| FrontierMath-2025-02-28-Private | math | 0.7 |