Appwrite Arena (With Skills): leaderboard
Questions about Appwrite services across areas such as auth, databases, functions, storage and messaging; the August 2026 run used 191 questions, 165 multiple choice and 26 free form. Here the model can call a tool that returns Appwrite SDK documentation. Multiple choice is auto scored and free form is judged by another model, giving an overall percentage where higher is better. Source: github.com/appwrite/arena.
Metric: Overall Score (%). Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 24 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 4.6 | 97.8 | #26 |
| 2 | Muse Spark 1.2 | 97.8 | #62 |
| 3 | GPT-5.5 | 97.7 | #31 |
| 4 | Claude Opus 5 | 97.4 | #12 |
| 5 | Claude Opus 4.7 | 97.1 | #49 |
| 6 | Claude Opus 4.8 | 97.1 | #37 |
| 7 | GPT-5.6 Sol | 96.9 | #19 |
| 8 | Kimi K3 | 96.9 | #30 |
| 9 | Grok Build 0.1 | 96.7 | #117 |
| 10 | Qwen 3.6 Plus | 96.5 | #120 |
| 11 | Kimi K2.6 | 96.3 | #104 |
| 12 | DeepSeek V4 Flash | 96.1 | #137 |
| 13 | Gemini 3.7 Flash | 96 | #23 |
| 14 | Claude Fable 5 | 95.9 | #16 |
| 15 | GLM-5.1 | 95.8 | #97 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=appwrite-arena-with-skills · How It Works · Data refreshed daily, snapshot 2026-10-20.