Appwrite Arena
Benchmark AI models on their understanding of Appwrite services
Sorted by
| Model | Cost/1M | Overall | Fundamental | Auth | Databases | Functions | Storage | Sites | Messaging | |
|---|---|---|---|---|---|---|---|---|---|---|
| Claude Opus 4.6 | $5.00 | 99.9% | 100% | 100% | 100% | 100% | 99.5% | 100% | 100% | |
| GPT 5.3 Codex | $1.75 | 99.2% | 100% | 97.5% | 99% | 98.5% | 100% | 100% | 99.5% | |
M | Kimi K2.5 | $0.45 | 99.2% | 100% | 98.5% | 99.5% | 99.5% | 100% | 100% | 97% |
| Gemini 3.1 Pro (Preview) | $2.00 | 98.1% | 100% | 97% | 98.5% | 100% | 99% | 92% | 100% |
Last update: Mar 2, 2026Scores combine auto-scored MCQs and AI-judged free-form questions