Claude 3.5 Sonnet is a powerful AI model. It excels in graduate-level reasoning, undergraduate-level knowledge, and coding proficiency, with improved understanding of nuance, humor, and complex instructions.
发布日期2024年6月21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 |
|---|---|---|---|
| 安全防御榜·Bias | security | 97.3 | — |
| GSM8k | math reasoning | 96.4 | 来源 |
| 安全防御榜·Toxicity | security | 96.3 | — |
| 安全防御榜·Human Rights | security | 95.6 | — |
| 安全防御榜 | security | 93.3 | — |
| BIG-Bench Hard | reasoning math language | 93.1 | 来源 |
| 安全防御榜·Info Safety | security | 93.0 | — |
| HumanEval | reasoning code | 92.0 | 来源 |
| 安全防御榜·Malicious Use | security | 91.9 | — |
| MGSM | math reasoning | 91.6 | 来源 |
| 安全防御榜·Socioeconomic | security | 91.1 | — |
| MMLU | general reasoning language math | 90.4 | 来源 |
| 安全防御榜·Child Safety | security | 88.0 | — |
| DROP | reasoning math | 87.1 | 来源 |
| MMLU-Pro | language reasoning math general | 76.1 | 来源 |
| MATH | math reasoning | 71.1 | 来源 |
| GPQA | reasoning general | 59.4 | 来源 |
Pricing
API 价格对比
暂无 API 价格。