Перейти к основному содержанию

Claude Sonnet 5 (Max)

AnthropicClaudeProprietary

Описание

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`.

Дата выхода
2026-06-30
Параметры
—
Длина контекста
1.0M
Модальности
image, pdf, text

Радар способностей

2
general
50
coding
12
reasoning
51
scienceоцен.
40
agents
80
multimodal

При отсутствии специализированных научных бенчмарков Science оценивается по научным категориям LLM Stats или на основе рассуждений.

Рейтинги

Оценки бенчмарков (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Code

DeepSWE 1.154.0%
BenchCAD37.3%Сам.

General

GDP.pdf81.6%Сам.

Healthcare

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

Legal

Legal Agent Benchmark5.8%Сам.

Math

USAMO 202633.39 / 42Сам.
ArXivMath72.2%Сам.

Multimodal

OSWorld-Verified81.2%Сам.

Reasoning

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

Индексы оценки AA

(Artificial Analysis)

Нет данных AA оценки

Оценки категорий LLM Stats

(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

Цены

Цена ввода$2 / 1M токенов
Цена вывода$10 / 1M токенов
Смешанная цена (3:1)$4 / 1M токенов
Цена чтения кэша$0.2 / 1M токенов
Цена записи кэша$2.5 / 1M токенов

Скорость

Токенов/сек80.5
Задержка первого токена167.06s
Время до первого ответа167.06s

Рейтинг цен провайдеров

Рейтинг цен провайдеров

2 провайдеров

Самый дешевый: AnthropicСамый дорогой: DeepInfra
ПровайдерВводВывод
1AnthropicОсновной
$2
$10
2DeepInfra
$3
$15

Сравнение цен разных API-провайдеров для этой модели.

Внешние ссылки