Sobre

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Família do Modelo

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)2026-02-17 Claude Sonnet 4.6 (Non-reasoning, Low Effort)2026-02-17 Claude Opus 4.6 (Adaptive Reasoning, Max Effort)2026-02-05 Claude Opus 4.6 (Non-reasoning, High Effort)2026-02-05 Claude Opus 4.5 (Reasoning)2025-11-24 Claude Opus 4.5 (Non-reasoning)2025-11-24 Claude 4.5 Haiku (Reasoning)2025-10-15 Claude 4.5 Haiku (Non-reasoning)2025-10-15

Benchmarks

MMLU-ProNão avaliado

GPQA Diamond

79.9%

HLE

13.2%

LiveCodeBenchNão avaliado

SciCode

46.9%

TerminalBench Hard

46.2%

MATH-500Não avaliado

AIMENão avaliado

AIME 2025Não avaliado

IFBench

41.2%

Long Context Recall

57.7%

Tau2

79.5%

Média do MercadoMelhor Score

Claude Sonnet 4.6 (Non-reasoning, High Effort)

Sobre

Família do Modelo

Posição no Mercado

Preços

Calculadora de Custo

vs. Modelos Similares

Desempenho

Benchmarks

Comparação Rápida

Modelos Similares