Claude 3 Opus is Anthropic's most intelligent model, with best-in-market performance on highly complex tasks. It can navigate open-ended prompts and sight-unseen scenarios with remarkable fluency and human-like understanding, showing the outer limits of what's possible with generative AI.
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 | 96.4 | 来源 |
| HellaSwag | reasoning | 95.4 | 来源 |
| GSM8k | math reasoning | 95.0 | 来源 |
| MGSM | math reasoning | 90.7 | 来源 |
| BIG-Bench Hard | reasoning math language | 86.8 | 来源 |
| MMLU | general reasoning language math | 86.8 | 来源 |
| HumanEval | reasoning code | 84.9 | 来源 |
| DROP | reasoning math | 83.1 | 来源 |
| MMLU-Pro | language reasoning math general | 68.5 | 来源 |
| MATH | math reasoning | 60.1 | 来源 |
| GPQA | reasoning general | 50.4 | 来源 |
Pricing
API 价格对比
暂无 API 价格。