Claude Fable 5 vs Claude Opus 4.7

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

Anthropic
Claude Fable 5GA
9.5
AI Panel
Anthropic
Claude Opus 4.7GA
9.0
AI Panel

Identity & lifecycle

ProviderAnthropicAnthropic
Family / tierClaude 5 · FableClaude 4 · Opus
StatusGAGA
Released2026-06-082026-04-15
Knowledge cutoff2026-01

Architecture & context

Context window1M1M
Max output tokens128K128K
Input modalitiestext, image, filetext, image
Reasoning modealwaysalways
Open weightsNoNo

Pricing (per Mtok)

Input$10$5
Output$50$25
Cached input$1$0.5
Batch input$5$2.5
Free tierNoNo

Speed

Output speed (tok/s)54.6
Time to first token (s)23.85
Latency tierslowslow

Trust & deployment

Trains on inputsNoNo
LicenseProprietaryProprietary
CloudsBedrock, Vertex AI, Azure AI FoundryBedrock, Vertex AI, Azure AI Foundry
ComplianceSOC2, HIPAA, GDPR, ISO27001SOC2, HIPAA, GDPR, ISO27001

AI Panel scoring

Unified score9.59
Decision Maker9.59
Domain Strategist9.59
Finance Lead78
Domain Practitioner9.59.5
Power User98.5
Skeptic7.57.5
Value score6.57.5

Benchmarks

GPQA Diamond94.2
SWE-bench Verified9587.6
MMMU91.5
Terminal-Bench8869.4
Humanity's Last Exam54.7
LMArena Elo1503
LMArena Coding Elo1554
Artificial Analysis Index57

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