Open-source AI benchmark

Which AI model knows
Appwrite best?

Last update: Mar 7, 2026
Above 85% is recommended, below 50% is not advised

Beyond the leaderboard

A closer look at how each model performs across every dimension we test.

Loading charts...

Ask

We ask each model 191 questions across 9 Appwrite services to highlight AI's impact on projects.

Answer

10 models respond with and without Appwrite docs, testing both raw knowledge and assisted intelligence.

Score

Answers are scored deterministically using multi-choice and by an AI judge for open-ended questions.

Evaluation modes

Context changes everything

We test each model with and without Appwrite's docs. The gap reveals how well it leverages context.

Without Skills.md

How do I create a document?

Sure, here's an example code how you can create a document in Appwrite Databases:

import Appwrite from 'appwrite';

const appwrite = new Appwrite();
appwrite.setEndpoint('https://cloud.appwrite.io/v1');

// Removed in Appwrite 1.0
await appwrite.database.createDocument(
  'collectionId', { title: 'Hello' }
);
Cannot read properties of undefined 'createDocument'
Param "databaseId" is not optional.
Project is not accessible in this region.
With Skills.md

How do I create a document?

Great question! Here's how to create a row - newer replacement of a document, using the Appwrite's web SDK:

import { Client, TablesDB, ID } from 'appwrite';

const client = new Client()
  .setEndpoint('https://<REGION>.cloud.appwrite.io/v1')
  .setProject('<PROJECT_ID>');

const tables = new TablesDB(client);
await tables.createRow({
  databaseId: '<DATABASE_ID>',
  tableId: '<TABLE_ID>',
  documentId: ID.unique(),
  data: { title: 'Hello', content: 'World' }
});
built in 743ms

Benchmarking the full Appwrite platform

Every question is drawn from actual Appwrite platform usage, covering all the services.

Image

Foundation

Core concepts, SDKs, permissions, and platform basics

Image

Auth

Authentication methods, user management, and sessions

Image

Databases

Collections, documents, queries, and relationships

Image

Functions

Serverless functions, runtimes, and execution

Image

Storage

File uploads, buckets, and file management

Image

Sites

Static site hosting, domains, and deployments

Image

Messaging

Push notifications, SMS, email, and providers

Image

Realtime

WebSocket subscriptions, channels, and live events

Image

CLI

CLI installation, configuration, and deployment workflows

Scoring methods

Fair and predictable scoring

We score every answer twice, once for accuracy, once for quality.

Deterministic (MCQ)

Each model answers 165 multiple-choice questions, one correct answer, no room for interpretation.

Fully reproducibleNo judge biasFactual recall only

AI-Judged (Open-ended)

26 open-ended questions scored 0–1 by an AI judge against a rubric and reference answer.

Tests reasoningReal-world usageSlight variance

Fully open source

Every question, answer, and score is public.
Fork it, run it, improve it.

View on GitHub