Back
OpenAI

GPT 5.6 Luna

OpenAI, United States182/191 correctLast updated Aug 24, 2026Website

GPT 5.6 Luna by OpenAI achieved an overall score of 95.2% on Appwrite Arena, ranking #18 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 182 of 191 questions correctly across categories including Auth, TablesDB, Functions, Storage, and CLI. During the benchmark it consumed 340,868 tokens costing $0.1649, averaging 75.9 tokens per second over 21m 14s. Compare GPT 5.6 Luna with other LLMs on the Appwrite Arena leaderboard.

Total tokens
340,868Input: 244,157 Output: 96,711
Total duration
21m 14s
Avg speed
75.9 tok/s
Total cost
$ 0.1649
Cost/1MOverallFoundationAuthTablesDBFunctionsStorageSitesMessagingRealtimeCLI
$0.20Input: $0.20/1M tokens
Output: $1.20/1M tokens		95.2%99.2%94.3%91.3%99.3%95%100%100%94.8%86.8%
Deterministic17/17 correct
AI-Judged95% average score