Loading model details...
reasoningcodingmultilingualvisionfunction-calling
性能基准测试
MMLU88.7%
GPQA59.4%
HumanEval92%
Math53%
模型概述
Claude 3.5 Sonnet represents a significant leap forward in AI capabilities. It sets new industry benchmarks for graduate-level reasoning (GPQA), undergraduate-level knowledge (MMLU), and coding proficiency (HumanEval). The model is designed to handle complex, multi-step workflows with impressive accuracy while maintaining the conversational tone and natural language understanding that Claude is known for.
常见用例
Complex reasoning and analysis
Advanced coding and debugging
Mathematical problem solving
Research and analysis
Creative writing and content generation
Multilingual translation and localization
Technical documentation
试用此模型
通过我们的交互式演示体验模型的功能
使用您自己的提示词测试模型，实时查看结果
关键规格
Context Window
200,000 tokens
Max Output
8,192 tokens
Training Data
Up to April 2024
Languages
100+ languages
Input Speed
87 tokens/s
Output Speed
32 tokens/s
价格明细
| 层级 | 输入价格 | 输出价格 |
|---|---|---|
| Input | $3/million tokens | $15/million tokens |
| Cached | $0.3/million tokens | $15/million tokens |
费用计算器
$0.0180
功能与特性
Vision
Function Calling
Streaming
JSON Mode
System Prompts
✕Code Execution
✕Image Generation
✕Audio Input
✕Audio Output
Multimodal
✕Search
✕Web Browsing
集成示例
import anthropic
client = anthropic.Anthropic(api_key="your-api-key")
message = client.messages.create(
model="claude-3-5-sonnet-20241022",
max_tokens=1024,
messages=[
{"role": "user", "content": "Hello, Claude!"}
]
)
print(message.content)社区评分
4.8
★★★★★
基于社区评价
版本历史与更新日志
3.5 Sonnet (October 2024)
2024-10-22- ✓Improved reasoning capabilities
- ✓Enhanced coding performance
- ✓Better multilingual understanding
- ✓New prompt caching feature