Model family · Anthropic

What do Claude models pick? Their default stack

In October 2026, Claude models (Claude Opus 5.5, Claude Sonnet 5.5) gave 192 picks. Their most named tool differs from the all-model pick in 10 of 24 categories.

n = 192 picksMeasured 2026-10-19Method

Model pick, not a product recommendation. It shows what language models name when asked without any constraints. It is not a statement about quality, security, price or market share.

Models in this family

Claude models in the index. Fixed slugs, never an alias.
ModelSlugParsed picksParse rate
Claude Opus 5.5manual/claude-opus-5.596100%
Claude Sonnet 5.5manual/claude-sonnet-5.596100%

Default stack

The tool this family named most often in each category, against the most named tool across all models. Cells with few picks are indicative.

Most named tool per category for Claude models, October 2026.
CategoryClaudeSharenAll models
AuthenticationBetter Auth25%8Auth.js
DatabaseNeon25%8PostgreSQL
ORM and query layerDrizzle ORM63%8Prisma
HostingVercel50%8same
File storageCloudflare R238%8Amazon S3
Background jobsInngest50%8BullMQ
SearchPostgreSQL full-text search63%8Meilisearch
RealtimeSupabase Realtime25%8same
CachingNext.js caching25%8Redis
Scheduled jobsVercel Cron Jobs50%8same
PaymentsStripe88%8same
Transactional emailResend63%8same
Newsletter and marketing emailBrevo25%8Loops
Error monitoringSentry100%8same
Web analyticsPlausible75%8same
Product analyticsPostHog100%8same
Feature flagsPostHog88%8same
UI componentsshadcn/ui88%8same
FormsReact Hook Form75%8same
CMSSanity50%8same
Internationalisationnext-intl75%8same
AI SDKVercel AI SDK63%8same
Rate limiting and bot protectionArcjet38%8Upstash Ratelimit
Cookie consentCookieConsent38%8Klaro