Back
Claude

Claude Fable 5

Anthropic, United States184/191 correctLast updated Jun 10, 2026Website

Claude Fable 5 by Anthropic achieved an overall score of 95.9% on Appwrite Arena, ranking #8 of 16 benchmarked models. The benchmark tests how well AI models understand Appwrite - the open-source backend platform for authentication, TablesDB, storage, functions, and more. This model answered 184 of 191 questions correctly across categories including Auth, TablesDB, Functions, Storage, and CLI. During the benchmark it consumed 1,423,477 tokens costing $16.2651, averaging 22.1 tokens per second over 38m 13s. Compare Claude Fable 5 with other LLMs on the Appwrite Arena leaderboard.

Total tokens
1,423,477Input: 1,372,718 Output: 50,759
Total duration
38m 13s
Avg speed
22.1 tok/s
Total cost
$ 16.2651
Cost/1MOverallFoundationAuthTablesDBFunctionsStorageSitesMessagingRealtimeCLI
$10.00Input: $10.00/1M tokens
Output: $50.00/1M tokens		95.9%100%98.5%87.4%100%94.3%95%100%88%99.8%
Deterministic17/17 correct
AI-Judged100% average score