The most intelligent Claude model and the first hybrid reasoning model on the market. Claude 3.7 Sonnet can produce near-instant responses or extended, step-by-step thinking that is made visible to the user. Shows particularly strong improvements in coding and front-end web development.
发布日期2025年2月24日
参数规模—
上下文长度200K
许可证Proprietary
知识截止—
Benchmarks
评测成绩
| 评测基准 | 类别 | 分数 | 来源 |
|---|---|---|---|
| MATH-500 | math reasoning | 96.2 | 来源 |
| IFEval | general | 93.2 | 来源 |
| MMMLU | language reasoning math general | 86.1 | 来源 |
| GPQA | reasoning general | 84.8 | 来源 |
| TAU-bench Retail | reasoning communication | 81.2 | 来源 |
| AIME 2024 | math reasoning | 80.0 | 来源 |
| MMMU | multimodal reasoning general | 75.0 | 来源 |
| SWE-Bench Verified | reasoning frontend_development code | 70.3 | 来源 |
| TAU-bench Airline | reasoning communication | 58.4 | 来源 |
| AIME 2025 | math reasoning | 54.8 | 来源 |
| Terminal-bench | reasoning code | 35.2 | 来源 |
Pricing
API 价格对比
| 服务商 | 输入价 | 输出价 | 上下文 | 吞吐(tok/s) | 延迟(s) | 函数调用 | 代码执行 | 联网搜索 |
|---|---|---|---|---|---|---|---|---|
| Abacus | $3.00 | $15.00 | 200K | — | — | ✓ | ✗ | ✗ |
价格单位：美元/百万 token，数据来自社区整理，仅供参考。