Back
Claude

Claude Opus 4.8

Anthropic, United States186/191 correctLast updated Jun 1, 2026Website

Claude Opus 4.8 by Anthropic achieved an overall score of 97.1% on Appwrite Arena, ranking #3 of 14 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 186 of 191 questions correctly across categories including Auth, TablesDB, Functions, Storage, and CLI. During the benchmark it consumed 1,188,261 tokens costing $6.8555, averaging 39.6 tokens per second over 19m 15s. Compare Claude Opus 4.8 with other LLMs on the Appwrite Arena leaderboard.

Total tokens
1,188,261Input: 1,142,553 Output: 45,708
Total duration
19m 15s
Avg speed
39.6 tok/s
Total cost
$ 6.8555
Cost/1MOverallFoundationAuthTablesDBFunctionsStorageSitesMessagingRealtimeCLI
$5.00Input: $5.00/1M tokens
Output: $25.00/1M tokens		97.1%100%99.3%96.1%95%94.3%100%100%99.2%92.5%
Deterministic17/17 correct
AI-Judged100% average score