Claude Sonnet 5.5 vs Claude Opus 5.5

Best cell per row highlighted. Null means undisclosed — never counted as zero.

Anthropic
Claude Sonnet 5.5GA
9.3
AI Panel
Anthropic
Claude Opus 5.5GA
9.7
AI Panel

Identity & lifecycle

ProviderAnthropicAnthropic
Family / tierClaude 5 · SonnetClaude 5 · Opus
StatusGAGA
Released2026-09-282026-09-22
Knowledge cutoff2026-062026-06

Architecture & context

Context window1M1M
Max output tokens128K128K
Input modalitiestext, imagetext, image
Reasoning modeoptionalalways
Open weightsNoNo

Pricing (per Mtok)

Input$2$4
Output$10$20
Cached input$0.2$0.2
Batch input$1$2
Free tierYesNo

Speed

Output speed (tok/s)97.672.8
Time to first token (s)12.723.7
Latency tierfastmedium

Trust & deployment

Trains on inputsNoNo
LicenseProprietaryProprietary
CloudsBedrock, Vertex AI, Azure AI FoundryBedrock, Vertex AI, Azure AI Foundry
ComplianceSOC2, HIPAA, ISO27001, ISO42001SOC2, ISO27001, ISO42001, HIPAA

AI Panel scoring

Unified score9.39.7
Decision Maker9.59.5
Domain Strategist9.29.5
Finance Lead8.89
Domain Practitioner9.39
Power User9.29.5
Skeptic88.5
Value score9.29

Benchmarks

Humanity's Last Exam56.964.4
LMArena Elo14711504
LMArena Coding Elo15361538
Artificial Analysis Index5658

Scores link to their sources. Missing cells mean the vendor hasn't disclosed a result — honesty over padding.