跳轉到主要內容

Claude Sonnet 4.6 (Non-reasoning, High Effort)

AnthropicClaudeProprietary

描述

Claude Sonnet 4.6 is a full upgrade of the model's skills across coding, computer use, long-context reasoning, agent planning, knowledge work, and design. Users preferred Sonnet 4.6 over Sonnet 4.5 approximately 70% of the time. First Sonnet-class model with 1M token context window (beta) and context compaction. Major improvement in computer use skills compared to prior Sonnet models. Default model on Free and Pro plans. Pricing: $3/$15 per million tokens (input/output).

發布日期
2026-02-17
參數規模
上下文長度
1.0M
支援模態
audio, image, pdf, text, video

能力雷達圖

31
general
47
coding
80
reasoning
55
science估算
80
agents
80
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
程式碼能力榜58
75.0
AA
通用能力榜124
60.0
AA
科學能力100
61.0
AA

基準測試分數 (LLM Stats)

Agents

GDPval-AA1417.00 / 3000自報
BrowseComp74.7%自報
OSWorld72.5%自報
Finance Agent63.3%自報
MCP Atlas61.3%自報
Terminal-Bench 2.059.1%自報
Finance Agent v251.0%自報
Legal Agent Benchmark5.4%自報

Biology

GPQA89.9%自報

Code

SWE-Bench Verified79.6%自報

Communication

Tau2 Telecom97.9%自報
Tau2 Retail91.7%自報

General

MMMLU89.3%自報
MMMU-Pro75.6%自報
LiveBench75.5%自報

Math

Humanity's Last Exam49.0%自報

Reasoning

ARC-AGI v258.3%自報

AA 評測指數

Intelligence Index
35.9
Gpqa
0.8
Tau2
0.8
Lcr
0.6
Scicode
0.5
Terminalbench Hard
0.5
Ifbench
0.4
Hle
0.1

LLM Stats 分類評分

Legal
100
Finance
100
General
100
Agents
100
Reasoning
75
Language
90
Physics
90
Biology
90
Chemistry
90
Communication
90
Frontend Development
80
Tool Calling
80
Math
70
Multimodal
70
Search
70
Code
70
Spatial Reasoning
60
Vision
60
Long Context
40
Healthcare
20

定價

輸入價格$3 / 1M tokens
輸出價格$15 / 1M tokens
混合價格(3:1)$6 / 1M tokens
快取讀取價格$0.3 / 1M tokens
快取寫入價格$3.75 / 1M tokens

速度

Tokens/秒59.5
首Token延遲0.99s
首回答延遲0.99s

供應商價格排行

供應商價格排行

6 個供應商

最便宜: Anthropic最貴: Amazon Bedrock
供應商輸入輸出
1Anthropic最便宜
$0
$0.00002
2AIHubMix
$3
$15
3Vertex (Anthropic)
$3
$15
4Vertex
$3
$15
5Databricks
$3
$15
6Amazon Bedrock
$3.3
$16.5

比較該模型在不同 API 供應商之間的定價。

外部連結