跳轉到主要內容

Claude Sonnet 5.5 (Max, Default Fallback)

AnthropicClaudeProprietary

描述

Claude Sonnet 5.5 is the second model in Anthropic's Claude 5.5 family and a faster, lower-cost complement to Claude Opus 5.5. It targets well-scoped everyday tasks, coding, and polished documents, slides, and spreadsheets, and runs 30%+ faster than Claude Sonnet 5 while typically using far fewer tokens at the same $2/$10 per million input/output prices. It accepts text and image input with text output, supports multilingual and vision workloads, tool use, and adaptive thinking (Claude Platform default effort high; Claude Code and apps default medium). Context window is 1M tokens with 128K max output on the sync Messages API; reliable knowledge and training-data cutoffs are June 2026. Cache reads are $0.10 and 5-minute cache writes are $2.50 per million tokens. Capability scores are self-reported from the Claude Sonnet 5.5 System Card (Table 8.1.A and §8) and the launch announcement. Available on the Claude API as `claude-sonnet-5-5`.

發布日期
2026-09-28
參數規模
—
上下文長度
1.0M
支援模態
image, pdf, text

能力雷達圖

55
general
70
coding
70
reasoning
51
science估算
60
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17
63.0
LS
程式碼能力榜6
95.0
LB
通用能力榜5
84.0
AA
數學推理7
96.0
LB
多模態榜40
59.0
LS
推理能力6
92.0
LB
科學能力7
79.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Agents

AA-Briefcase v1.11811.00 / 3000自報
Program Bench79.7%自報
Toolathlon-Verified77.8%自報
OfficeQA76.9%自報
OfficeQA Pro65.6%自報
AutomationBench44.7%自報

Biology

BioMysteryBench89.2%自報
De novo protein binder design82.3%自報
LatchBio SpatialBench Verified72.5%自報
Biomedical image analysis72.2%自報
Protocols Troubleshooting67.3%自報
Protocols Understanding (V2)66.6%自報
Medicinal Chemistry (ADME)65.3%自報
Protein Design — Library Ranking54.8%自報
Protein Design — Sequence Generation51.0%自報
BioMysteryBench (Human Difficult)44.7%自報
Morphology-to-molecule matching25.0%自報

Code

BenchCAD (with Python tool)96.3%自報
BenchCAD74.7%自報
DeepSWE 1.171.0%自報
FrontierSWE V261.9%自報
CursorBench 4.055.5%自報

General

GDPval-AA 2.11844.00 / 3000自報
Global-MMLU92.1%自報

Healthcare

HealthBench Professional (raw)77.1%自報
HealthBench (raw)69.4%自報
HealthBench Professional69.2%自報
HealthBench65.4%自報
PhysicianBench63.2%自報

Language

MILU91.6%自報

Legal

Legal Agent Benchmark11.7%自報

Math

ArXivMath (with tools)95.2%自報
ArXivMath86.8%自報

Multimodal

OSWorld 2.1 (partial)80.1%自報
OSWorld 2.1 (strict)43.5%自報

Reasoning

SWE-bench Multilingual90.3%自報
SWE-Bench ProPrinceton NLP (2024)81.3%自報
Terminal-Bench 4.070.6%自報
Humanity's Last Exam (with tools)64.5%自報
FrontierCode 1.1 (Extended)64.4%自報
Terminal-Bench-Science 0.159.9%自報
Humanity's Last Exam (no tools, text-only)56.9%自報
SWE-Bench Multimodal54.3%自報
FrontierCode 1.152.1%自報

Science

LatchBio SingleCellBench59.1%自報

Vision

Chartography90.2%自報
Chartography (no tools)61.6%自報

AA 評測指數

(Artificial Analysis)
Engineering(Artificial Analysis)
58.5
Strategy And Ops
58.1
Finance And Accounting
55.8
Intelligence Index(Artificial Analysis)
54.5
Healthcare And Medical
54.2
Economics
54.1
Legal
52.2

LLM Stats 分類評分

(LLM Stats (zeroeval))
Productivity
100
Agents
100
Reasoning
100
General
90
Language
90
Math
70
Multimodal
70
Healthcare
70
Chemistry
70
Code
70
Vision
70
Science
60
Biology
60
Tool Calling
60
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$0.1 / 1M tokens
快取寫入價格$2.5 / 1M tokens

速度

Tokens/秒132.3
首Token延遲471.77s
首回答延遲471.77s

供應商價格排行

供應商價格排行

1 個供應商

供應商輸入輸出
1Anthropic主要
$2
$10

比較該模型在不同 API 供應商之間的定價。

外部連結