跳轉到主要內容

Claude Sonnet 5 (Max)

AnthropicClaudeProprietary

描述

Claude Sonnet 5 is Anthropic's most agentic Sonnet-class model, an upgrade to Sonnet 4.6 that narrows the gap to Opus 4.8 on reasoning, tool use, coding, computer use, and knowledge work while staying lower priced. It plans, uses tools like browsers and terminals, and runs autonomously for long-horizon tasks. Capability gains include SWE-Bench Verified (85.2%), SWE-Bench Pro (63.2%), SWE-Bench Multilingual (78.3%), Terminal-Bench 2.1 (80.4%), OSWorld-Verified (81.2%), BrowseComp (84.7% single-agent, 86.6% multi-agent), Humanity's Last Exam with tools (57.4%), USAMO 2026 (79.5%), GDPval-AA v2 (1618 Elo), HealthBench Professional (57.8%), and FrontierCode v1 (38.8%). It supports adaptive thinking with selectable effort levels up to 'extra high' (xhigh) and a 1M-token context window with context compaction. The safety assessment found lower rates of misaligned behavior, hallucination, and sycophancy than Sonnet 4.6, with improved prompt-injection robustness; it ships with cyber safeguards enabled by default and uses an updated tokenizer (input maps to roughly 1.0-1.35x more tokens than Sonnet 4.6). Default model on Free and Pro plans and available to Max, Team, and Enterprise users, in Claude Code, and on the Claude Platform. Launches with introductory pricing of $2/$10 per million input/output tokens through August 31, 2026, then $3/$15. Available via the Claude API as `claude-sonnet-5`.

發布日期
2026-06-30
參數規模
—
上下文長度
1.0M
支援模態
image, pdf, text

能力雷達圖

2
general
50
coding
12
reasoning
51
science估算
40
agents
80
multimodal

缺少專門科學評測時,Science 由 LLM Stats 科學得分或推理能力估算。

排行榜排名

領域#排名分數來源
智慧體能力模型榜120
37.0
LS
程式碼能力榜36
75.0
LB
多模態榜54
56.0
LS
推理能力19
89.0
LB

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

OfficeQA Pro59.4%自報
Toolathlon54.3%自報
AutomationBench13.5%自報

Code

DeepSWE 1.154.0%
BenchCAD37.3%自報

General

GDP.pdf81.6%自報

Healthcare

HealthBench Professional57.8%自報
LifeSci Diamond (2026-11)1.8%

Legal

Legal Agent Benchmark5.8%自報

Math

USAMO 202633.39 / 42自報
ArXivMath72.2%自報

Multimodal

OSWorld-Verified81.2%自報

Reasoning

CharXiv-R88.3%自報
ChartMuseum86.7%自報
SWE-Bench Verified85.2%自報
BrowseCompOpenAI (2025)84.7%自報
Terminal-Bench 2.0Stanford × Laude Institute (2026)80.4%自報
SWE-bench Multilingual78.3%自報
SWE-Bench ProPrinceton NLP (2024)63.2%自報
Humanity's Last Exam57.4%自報
FrontierCode 1.142.7%
FrontierCode38.8%自報
SWE-Bench Multimodal28.1%自報
Terminal-Bench 4.012.4%

AA 評測指數

(Artificial Analysis)

暫無 AA 評測資料

LLM Stats 分類評分

(LLM Stats (zeroeval))
Math
12
Reasoning
2
General
2
Frontend Development
90
Search
80
Multimodal
60
Healthcare
60
Vision
60
Agents
50
Code
50
Tool Calling
40
Legal
10

定價

輸入價格$2 / 1M tokens
輸出價格$10 / 1M tokens
混合價格(3:1)$4 / 1M tokens
快取讀取價格$0.2 / 1M tokens
快取寫入價格$2.5 / 1M tokens

速度

Tokens/秒80.5
首Token延遲167.06s
首回答延遲167.06s

供應商價格排行

供應商價格排行

2 個供應商

最便宜: Anthropic最貴: DeepInfra
供應商輸入輸出
1Anthropic主要
$2
$10
2DeepInfra
$3
$15

比較該模型在不同 API 供應商之間的定價。

外部連結