Back
Claude

Claude Opus 5

Anthropic, United States187/191 correctLast updated Aug 24, 2026Website

Claude Opus 5 by Anthropic achieved an overall score of 97.4% on Appwrite Arena, ranking #4 of 24 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 187 of 191 questions correctly across categories including Auth, TablesDB, Functions, Storage, and CLI. During the benchmark it consumed 1,433,944 tokens costing $8.7390, averaging 40.5 tokens per second over 32m 20s. Compare Claude Opus 5 with other LLMs on the Appwrite Arena leaderboard.

Total tokens
1,433,944Input: 1,355,482 Output: 78,462
Total duration
32m 20s
Avg speed
40.5 tok/s
Total cost
$ 8.7390
Cost/1MOverallFoundationAuthTablesDBFunctionsStorageSitesMessagingRealtimeCLI
$5.00Input: $5.00/1M tokens
Output: $25.00/1M tokens		97.4%100%99.3%99.6%100%94.5%100%95%88.5%98.9%
Deterministic17/17 correct
AI-Judged100% average score