Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.
发布日期2024年2月29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 |
|---|---|---|---|
| ARC-C | reasoning general | 93.2 | 来源 |
| GSM8k | math reasoning | 92.3 | 来源 |
| HellaSwag | reasoning | 89.0 | 来源 |
| MGSM | math reasoning | 83.5 | 来源 |
| BIG-Bench Hard | reasoning math language | 82.9 | 来源 |
| MMLU | general reasoning language math | 79.0 | 来源 |
| DROP | reasoning math | 78.9 | 来源 |
| HumanEval | reasoning code | 73.0 | 来源 |
| MMLU-Pro | language reasoning math general | 56.8 | 来源 |
| MATH | math reasoning | 43.1 | 来源 |
| GPQA | reasoning general | 40.4 | 来源 |
Pricing
API 价格对比
暂无 API 价格。