跳轉到主要內容

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.

發布日期
2025-09-29
參數規模
上下文長度
200K
支援模態
audio, image, pdf, text, video

能力雷達圖

80
general
50
coding
90
reasoning
68
science估算
80
agents
70
multimodal

Science 在缺少專門科學評測時使用推理能力代理估算。

排行榜排名

領域#排名分數來源
智慧體能力模型榜54
56.0
LS

基準測試分數 (LLM Stats)

Agents

OSWorld61.4%自報
Terminal-Bench50.0%自報

Biology

GPQA83.4%自報

Code

SWE-bench Verified (Agentic Coding)77.2%自報

Communication

TAU-bench Retail86.2%自報
TAU-bench Airline70.0%自報

General

MMMLU89.1%自報
MMMUval77.8%自報

Math

AIME 202587.0%自報

AA 評測指數

暫無 AA 評測資料

LLM Stats 分類評分

Language
90
Math
90
Physics
80
Reasoning
80
General
80
Healthcare
80
Biology
80
Chemistry
80
Communication
80
Tool Calling
80
Multimodal
70
Vision
70
Agents
60
Long Context
50
Code
50

定價

輸入價格$0 / 1M tokens
輸出價格$0.00002 / 1M tokens
混合價格(3:1)$0.00001 / 1M tokens
快取讀取價格$0.3 / 1M tokens
快取寫入價格$3.75 / 1M tokens

速度

暫無速度資料

供應商價格排行

供應商價格排行

27 個供應商

最便宜: Anthropic最貴: Venice AI
供應商輸入輸出
1Anthropic主要
$0
$0.00002
2QiHang
$0.43
$2.14
3Poe
$2.6
$13
4Jiekou.AI
$2.7
$13.5
5NanoGPT
$2.992
$14.994
6302.AI
$3
$15
7Abacus
$3
$15
8Perplexity Agent
$3
$15
9OpenRouter
$3
$15
10ZenMux
$3
$15
11Kilo Gateway
$3
$15
12Cloudflare AI Gateway
$3
$15
13GitHub Copilot
$3
$15
14OpenCode Zen
$3
$15
15Helicone
$3
$15
16Azure Cognitive Services
$3
$15
17Vertex (Anthropic)
$3
$15
18Requesty
$3
$15
19Vercel AI Gateway
$3
$15
20LLM Gateway
$3
$15
21Vertex
$3
$15
22Azure
$3
$15
23NEAR AI Cloud
$3
$15.5
24OrcaRouter
$3
$15
25Merge Gateway
$3
$15
26Neon
$3
$15
27Venice AI
$3.75
$18.75

比較該模型在不同 API 供應商之間的定價。

外部連結