An advanced language model with improved reasoning capabilities, particularly excelling in coding and mathematical tasks. Features a 128K token context window and enhanced problem-solving abilities compared to its predecessor.
发布日期2024年3月28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 |
|---|---|---|---|
| GSM8k | math reasoning | 90.0 | 来源 |
| DocVQA | vision multimodal | 85.6 | 来源 |
| MMLU | general reasoning language math | 81.3 | 来源 |
| HumanEval | reasoning code | 74.1 | 来源 |
| MMMU | multimodal reasoning general | 53.6 | 来源 |
| MathVista | math vision multimodal | 52.8 | 来源 |
| MMLU-Pro | language reasoning math general | 51.0 | 来源 |
| MATH | math reasoning | 50.6 | 来源 |
| GPQA | reasoning general | 35.9 | 来源 |
Pricing
API 价格对比
暂无 API 价格。