Grok 3
来自 xAI · 发布于 2025-06-10
38.4
平均分
$3.00/1M
输入价格
$15.00/1M
输出价格
131K tokens (~66 books)
上下文窗口
text
类型
Tested on 13 benchmarks with 38.4% average. Top scores: MATH level 5 (88.8%), Lech Mazur Writing (76.4%), GPQA diamond (67.7%).
基准测试分数
| 基准测试 | 类别 | 分数 | Bar |
|---|---|---|---|
| MATH level 5 | math | 88.8 | |
| Lech Mazur Writing | knowledge | 76.4 | |
| GPQA diamond | knowledge | 67.7 | |
| Fiction.LiveBench | knowledge | 58.3 | |
| OTIS Mock AIME 2024-2025 | math | 55.5 | |
| Aider polyglot | coding | 53.3 | |
| WeirdML | coding | 37.2 | |
| Balrog | knowledge | 29.5 | |
| SimpleBench | reasoning | 23.3 | |
| ARC-AGI | reasoning | 5.5 | |
| FrontierMath-2025-02-28-Private | math | 3.8 | |
| FrontierMath-Tier-4-2025-07-01-Private | math | 0.1 | |
| ARC-AGI-2 | reasoning | 0.1 |