Grok-2 is a frontier language model with state-of-the-art reasoning capabilities, featuring advanced abilities in chat, coding, and reasoning. It demonstrates superior performance in visual math reasoning, document-based question answering, and excels across various academic benchmarks including reasoning, reading comprehension, math, and science.
发布日期2024年8月13日
参数规模—
上下文长度—
许可证Proprietary
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| DocVQA | vision multimodal | 93.6 | 来源 |
| HumanEval | reasoning code | 88.4 | 来源 |
| MMLU | general reasoning language math | 87.5 | 来源 |
| MATH | math reasoning | 76.1 | 来源 |
| MMLU-Pro | language reasoning math general | 75.5 | 来源 |
| MathVista | math vision multimodal | 69.0 | 来源 |
| MMMU | multimodal reasoning general | 66.1 | 来源 |
| GPQA | reasoning general | 56.0 | 来源 |
Pricing
API 价格对比
暂无 API 价格。