Beta
Classificação/Claude Opus 4.5
Anthropic

Claude Opus 4.5

por Anthropic · Lançado em 2025-11-24

46.5
pontuação média
$5.00/1M
Preço de entrada
$25.00/1M
Preço de saída
200K tokens (~100 books)
Janela de contexto
multimodal
Tipo

Tested on 18 benchmarks with 46.5% average. Top scores: OTIS Mock AIME 2024-2025 (86.1%), GPQA diamond (81.4%), ARC-AGI (80.0%).

Pontuações de benchmark

BenchmarkCategoriaPontuaçãoBar
OTIS Mock AIME 2024-2025math86.1
GPQA diamondknowledge81.4
ARC-AGIreasoning80.0
GeoBenchknowledge75.0
SWE-Bench Verified (Bash Only)coding74.4
OSWorldagentic66.3
WeirdMLcoding63.7
Terminal Benchcoding63.1
SimpleBenchreasoning54.4
SimpleQA Verifiedknowledge41.8
ARC-AGI-2reasoning37.6
GSO-Benchcoding26.5
HLEknowledge21.4
FrontierMath-2025-02-28-Privatemath20.7
APEX-Agentsagentic18.4
Chess Puzzlesknowledge12.0
VPCTknowledge10.0
FrontierMath-Tier-4-2025-07-01-Privatemath4.2

Modelos similares

xAIGrok 3 Mini
xAI
46.6
xAIGrok 3 Mini Beta
xAI
46.6
OpenAIo4 Mini
OpenAI
46.3
AnthropicClaude Sonnet 4.6
Anthropic
47.3

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