跳转到主要内容

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
200K
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
多模态榜68
53.0
LS

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

TAU-bench Retail86.2%自报

Language

MMMLU89.1%自报

Math

AIME 202587.0%自报

Multimodal

OSWorld61.4%自报

Reasoning

GPQANYU + Cohere + Anthropic (2023)83.4%自报
SWE-bench Verified (Agentic Coding)77.2%自报
TAU-bench Airline70.0%自报
Terminal-Bench50.0%自报

Vision

MMMUval77.8%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))
Chat
90
Language
90
Math
90
Physics
80
Reasoning
80
Healthcare
80
Biology
80
Chemistry
80
Communication
80
Tool Calling
80
Multimodal
70
General
70
Vision
70
Agents
60
Long Context
50
Code
50

定价

输入价格$3 / 1M tokens
输出价格$15 / 1M tokens
混合价格(3:1)$6 / 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

28 个供应商

最便宜: Anthropic最贵: Kilo Gateway
供应商输入输出
1Anthropic最便宜
$0
$0.00002
2QiHang
$0.43
$2.14
3Poe
$2.5758
$12.8788
4302.AI
$3
$15
5NanoGPT
$3
$15
6Abacus
$3
$15
7OpenRouter
$3
$15
8Jiekou.AI
$3
$15
9ZenMux
$3
$15
10Cloudflare AI Gateway
$3
$15
11OpenCode
$3
$15
12Helicone
$3
$15
13Azure Cognitive Services
$3
$15
14Vertex (Anthropic)
$3
$15
15Requesty
$3
$15
16Vercel AI Gateway
$3
$15
17DevPass (LLM Gateway)
$3
$15
18Vertex
$3
$15
19Azure
$3
$15
20OrcaRouter
$3
$15
21Snowflake Cortex
$3
$15
22Neon
$3
$15
23Ofox
$3
$15
24AI/ML API
$3.174
$15.87
25AIHubMix
$3.3
$16.5
26Opper
$3.3
$16.5
27Hubris
$4.5877
$22.9386
28Kilo Gateway
$6
$22.5

比较该模型在不同 API 供应商之间的定价。

外部链接