Back
OpenAI

GPT 5.5

OpenAI, United States187/191 correctLast updated May 7, 2026Website

GPT 5.5 by OpenAI achieved an overall score of 97.7% on Appwrite Arena, ranking #1 of 11 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 524,351 tokens costing $4.5100, averaging 38.0 tokens per second over 33m 5s. Compare GPT 5.5 with other LLMs on the Appwrite Arena leaderboard.

Total tokens
524,351Input: 448,823 Output: 75,528
Total duration
33m 5s
Avg speed
38.0 tok/s
Total cost
$ 4.5100
Cost/1MOverallFoundationAuthTablesDBFunctionsStorageSitesMessagingRealtimeCLI
$5.00Input: $5.00/1M tokens
Output: $30.00/1M tokens		97.7%100%98.5%96.5%99.5%94.3%100%100%100%92.9%
Deterministic17/17 correct
AI-Judged100% average score