Back
OpenAI

GPT 5.3 Codex

OpenAI, United States182/191 correctLast updated Mar 13, 2026Website

GPT 5.3 Codex by OpenAI achieved an overall score of 94.4% on Appwrite Arena, ranking #2 of 10 benchmarked models. The benchmark tests how well AI models understand Appwrite - the open-source backend platform for authentication, databases, storage, functions, and more. This model answered 182 of 191 questions correctly across categories including Auth, Databases, Functions, Storage, and CLI. During the benchmark it consumed 840,349 tokens costing $3.2731, averaging 49.2 tokens per second over 49m 51s. Compare GPT 5.3 Codex with other LLMs on the Appwrite Arena leaderboard.

Total tokens
840,349Input: 693,211 Output: 147,138
Total duration
49m 51s
Avg speed
49.2 tok/s
Total cost
$ 3.2731
Cost/1MOverallFoundationAuthDatabasesFunctionsStorageSitesMessagingRealtimeCLI
$1.75Input: $1.75/1M tokens
Output: $14.00/1M tokens		94.4%94.2%99.2%83.9%93.2%94.3%99%99.7%96%92.1%
Deterministic17/17 correct
AI-Judged62% average score