Saltar al contenido principal

Claude Sonnet 5 (Max)

AnthropicClaudeProprietary

Descripción

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`.

Fecha de lanzamiento
2026-06-30
Parámetros
—
Longitud del contexto
1.0M
Modalidades
image, pdf, text

Radar de capacidades

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

Science se estima a partir de las puntuaciones científicas de LLM Stats o del razonamiento cuando no hay benchmarks científicos dedicados.

Rankings

Dominio#PosiciónPuntuaciónFuente
Capacidad agéntica120
37.0
LS
Ranking de codificación36
75.0
LB
Ranking multimodal54
56.0
LS
Razonamiento19
89.0
LB

Puntuaciones de benchmarks (LLM Stats)

(LLM Stats (zeroeval))

Agents

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

Code

DeepSWE 1.154.0%
BenchCAD37.3%Aut.

General

GDP.pdf81.6%Aut.

Healthcare

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

Legal

Legal Agent Benchmark5.8%Aut.

Math

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

Multimodal

OSWorld-Verified81.2%Aut.

Reasoning

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

Índices de evaluación AA

(Artificial Analysis)

No hay datos de evaluación AA disponibles

Puntuaciones por categoría 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

Precios

Precio de entrada$2 / 1M tokens
Precio de salida$10 / 1M tokens
Precio mixto (3:1)$4 / 1M tokens
Precio de lectura caché$0.2 / 1M tokens
Precio de escritura caché$2.5 / 1M tokens

Velocidad

Tokens/seg80.5
Retraso del primer token167.06s
Tiempo hasta la respuesta167.06s

Ranking de Precios por Proveedor

Ranking de Precios por Proveedor

2 proveedores

Más barato: AnthropicMás caro: DeepInfra
ProveedorEntradaSalida
1AnthropicPRINCIPAL
$2
$10
2DeepInfra
$3
$15

Comparar precios entre diferentes proveedores de API para este modelo.

Fuentes externas