llm.ing

Claude Opus 4.5 (latest)

AnthropicOpenRouter ↗Artificial Analysis ↗

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence29.1thinkingindependentaaSep 9, 2026
23.7—independentaaSep 9, 2026
29.1—mirroropenrouterOct 5, 2026
Design Arena — 3dpreference1186—mirroropenrouterNov 19, 2026
Design Arena — androidnativepreference1163—mirroropenrouterNov 19, 2026
Design Arena — asciiartpreference1173—mirroropenrouterNov 18, 2026
Design Arena — codecategoriespreference1227—mirroropenrouterNov 18, 2026
Design Arena — datavizpreference1238—mirroropenrouterNov 18, 2026
Design Arena — fullstackpreference1126—mirroropenrouterNov 19, 2026
Design Arena — gamedevpreference1212—mirroropenrouterNov 19, 2026
Design Arena — mobileappspreference1180—mirroropenrouterNov 19, 2026
Design Arena — svgpreference1166—mirroropenrouterNov 19, 2026
Design Arena — uicomponentpreference1225—mirroropenrouterNov 19, 2026
Design Arena — webappspreference1151—mirroropenrouterOct 17, 2026
1137—mirroropenrouterNov 19, 2026
Design Arena — websitepreference1236—mirroropenrouterNov 19, 2026
LMArena Textpreference1447thinking-32kcrowdlmarenaAug 10, 2026
1451—crowdlmarenaOct 15, 2026
LMArena WebDevpreference1495thinking-32kcrowdlmarenaAug 10, 2026
1469—crowdlmarenaOct 13, 2026
Median output speedspeed55 tok/sthinkingindependentaaNov 19, 2026
46 tok/s—independentaaNov 19, 2026
Median time to first tokenspeed15.63sthinkingindependentaaNov 18, 2026
1.40s—independentaaNov 19, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Amazon Bedrock—200K$5 · $25100.00%——
Anthropic—200K$5 · $25100.00%——
Azure—200K$5 · $25100.00%——
Claude Platform on AWS—200K$5 · $25100.00%——
Google—200K$5 · $25———