Claude Fable 5 vs Claude Sonnet 5.5 vs Claude Opus 5.5

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

Anthropic
Claude Fable 5GA
9.5
AI Panel
Anthropic
Claude Sonnet 5.5GA
9.3
AI Panel
Anthropic
Claude Opus 5.5GA
9.7
AI Panel

Identity & lifecycle

ProviderAnthropicAnthropicAnthropic
Family / tierClaude 5 · FableClaude 5 · SonnetClaude 5 · Opus
StatusGAGAGA
Released2026-06-092026-09-282026-09-22
Knowledge cutoff2026-012026-062026-06

Architecture & context

Context window1M1M1M
Max output tokens128K128K128K
Input modalitiestext, image, filetext, imagetext, image
Reasoning modealwaysoptionalalways
Open weightsNoNoNo

Pricing (per Mtok)

Input$10$2$4
Output$50$10$20
Cached input$1$0.2$0.2
Batch input$5$1$2
Free tierNoYesNo

Speed

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

Trust & deployment

Trains on inputsNoNoNo
LicenseProprietaryProprietaryProprietary
CloudsBedrock, Vertex AI, Azure AI FoundryBedrock, Vertex AI, Azure AI FoundryBedrock, Vertex AI, Azure AI Foundry
ComplianceSOC2, HIPAA, GDPR, ISO27001SOC2, HIPAA, ISO27001, ISO42001SOC2, ISO27001, ISO42001, HIPAA

AI Panel scoring

Unified score9.59.39.7
Decision Maker9.59.59.5
Domain Strategist9.59.29.5
Finance Lead78.89
Domain Practitioner9.59.39
Power User99.29.5
Skeptic7.588.5
Value score6.59.29

Benchmarks

SWE-bench Verified95——
Terminal-Bench88——
Humanity's Last Exam—56.964.4
LMArena Elo150614711504
LMArena Coding Elo155215361538
Artificial Analysis Index—5658

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