Back
GPT 5.4
OpenAI, United States183/191 correctLast updated Mar 13, 2026Website
GPT 5.4 by OpenAI achieved an overall score of 95.1% on Appwrite Arena, ranking #1 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 183 of 191 questions correctly across categories including Auth, Databases, Functions, Storage, and CLI. During the benchmark it consumed 1,361,565 tokens costing $6.2237, averaging 54.9 tokens per second over 68m 29s. Compare GPT 5.4 with other LLMs on the Appwrite Arena leaderboard.
Total tokens
1,361,565Input: 1,135,986
Output: 225,579Total duration
68m 29sAvg speed
54.9 tok/sTotal cost
$ 6.2237| Cost/1M | Overall | Foundation | Auth | Databases | Functions | Storage | Sites | Messaging | Realtime | CLI |
|---|---|---|---|---|---|---|---|---|---|---|
| $2.50Input: $2.50/1M tokens Output: $15.00/1M tokens | 95.1% | 98.5% | 98.8% | 85.7% | 98.8% | 94.3% | 94% | 100% | 96% | 92.5% |
Deterministic17/17 correct
AI-Judged90% average score