Claude Sonnet 4.5
AnthropicClaudeProprietary
描述
Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding capabilities.
发布日期
2025-09-29
参数规模
—
上下文长度
1.0M
支持模态
audio, image, pdf, text, video
能力雷达图
70
general
50
coding
90
reasoning
68
science估算
80
agents
70
multimodal
缺少专门科学评测时，Science 由 LLM Stats 科学得分或推理能力估算。
排行榜排名
| 领域 | #排名 | 分数 | 来源 |
|---|---|---|---|
| 智能体能力模型榜 | 10 | 65.0 | LS |
基准测试分数 (LLM Stats)
(LLM Stats (zeroeval))Agents
OSWorld
61.4%自报
Terminal-Bench
50.0%自报
Biology
GPQANYU + Cohere + Anthropic (2023)
83.4%自报
Code
SWE-bench Verified (Agentic Coding)
77.2%自报
Communication
TAU-bench Retail
86.2%自报
TAU-bench Airline
70.0%自报
General
MMMLU
89.1%自报
MMMUval
77.8%自报
Math
AIME 2025
87.0%自报
AA 评测指数
(Artificial Analysis)暂无 AA 评测数据
LLM Stats 分类评分
(LLM Stats (zeroeval))Math90
Language90
Physics80
Reasoning80
Healthcare80
Biology80
Chemistry80
Communication80
Tool Calling80
Multimodal70
General70
Vision70
Agents60
Long Context50
Code50
定价
输入价格$0 / 1M tokens
输出价格$0.00002 / 1M tokens
混合价格(3:1)$0.00001 / 1M tokens
缓存读取价格$0.3 / 1M tokens
缓存写入价格$3.75 / 1M tokens
速度
暂无速度数据
供应商价格排行
供应商价格排行
23 个供应商
最便宜: Anthropic最贵: Venice AI
供应商输入输出
1Anthropic主要
$0
$0.00002
2QiHang
$0.43
$2.14
3Poe
$2.6
$13
4Jiekou.AI
$2.7
$13.5
5302.AI
$3
$15
6NanoGPT
$3
$15
7Abacus
$3
$15
8OpenRouter
$3
$15
9ZenMux
$3
$15
10Kilo Gateway
$3
$15
11OpenCode Zen
$3
$15
12Helicone
$3
$15
13Azure Cognitive Services
$3
$15
14Vertex (Anthropic)
$3
$15
15Requesty
$3
$15
16Vercel AI Gateway
$3
$15
17LLM Gateway
$3
$15
18Vertex
$3
$15
19Azure
$3
$15
20OrcaRouter
$3
$15
21Neon
$3
$15
22Pioneer
$3
$15
23Venice AI
$3.75
$18.75
比较该模型在不同 API 供应商之间的定价。