Beta
Classificação/Claude Opus 4.6
Anthropic

Claude Opus 4.6

por Anthropic · Lançado em 2026-02-04

55.5
pontuação média
$5.00/1M
Preço de entrada
$25.00/1M
Preço de saída
1.0M tokens (~500 books)
Janela de contexto
multimodal
Tipo

Tested on 14 benchmarks with 55.5% average. Top scores: OTIS Mock AIME 2024-2025 (94.4%), ARC-AGI (94.0%), GPQA diamond (87.4%).

Pontuações de benchmark

BenchmarkCategoriaPontuaçãoBar
OTIS Mock AIME 2024-2025math94.4
ARC-AGIreasoning94.0
GPQA diamondknowledge87.4
WeirdMLcoding77.9
Terminal Benchcoding69.9
ARC-AGI-2reasoning69.2
SimpleBenchreasoning61.1
SimpleQA Verifiedknowledge46.5
FrontierMath-2025-02-28-Privatemath40.7
GSO-Benchcoding33.3
APEX-Agentsagentic31.7
HLEknowledge31.1
FrontierMath-Tier-4-2025-07-01-Privatemath22.9
Chess Puzzlesknowledge17.0

Modelos similares

xAIGrok 4 Fast
xAI
55.9
OpenAIGPT-5.2 Chat
OpenAI
54.8
OpenAIGPT-5.2
OpenAI
54.8
Alibaba QwenQwen3 235B A22B
Alibaba Qwen
56.4

Anthropic Claude Opus Cronologia

Claude 3 Opus
33.7
N/AN/Actx8 benchmarks
Claude Opus 4
40.1+6.4
$15.00/M in200Kctx18 benchmarks
Claude Opus 4.1
38.5-1.6
$15.00/M in200Kctx13 benchmarks
Claude Opus 4.5
46.5+8.0
$5.00/M in(-10)200Kctx18 benchmarks
Claude Opus 4.6
55.5+9.0
$5.00/M in1.0Mctx(+800K)14 benchmarks