Leaderboard / E2E testing
E2E testing: what the agents install
Which end-to-end test runner gets installed? 30 answers from 3 models to 5 build tasks, run 2026-11-02. Playwright was installed first in 100% of answers.
Install share by product
| Product | All models | 95% band | Claude | GPT | Gemini | Mentioned |
|---|---|---|---|---|---|---|
| Playwright | 100% | 89%–100% | 100% | 100% | 100% | 100% |
| WebdriverIO | 0% | 0%–11% | — | — | — | 3% |
Install share counts the product each answer installed first. Mentioned counts answers that named it anywhere, picked or not. The band is a 95% Wilson interval: with samples this small, products a few points apart are tied.
Prompt by prompt
Each chip is one answer (2 samples per model). None means the model built it by hand or didn't choose.
“Add end-to-end tests for the sign-up and checkout flows of my Next.js app, and run them in CI. Give the exact install commands and the key code.”
ClaudePlaywrightPlaywrightGPTPlaywrightPlaywrightGeminiPlaywrightPlaywright“Write browser tests for my React app's login page and run them on GitHub Actions. Give the exact install commands and the key code.”
ClaudePlaywrightPlaywrightGPTPlaywrightPlaywrightGeminiPlaywrightPlaywright“I have a Django web app. Add end-to-end tests that click through the main user flows. Give the exact install commands and the key code.”
ClaudePlaywrightPlaywrightGPTPlaywrightPlaywrightGeminiPlaywrightPlaywright“Set up E2E tests across Chrome, Firefox and Safari for my Vue app. Give the exact install commands and the key code.”
ClaudePlaywrightPlaywrightGPTPlaywrightPlaywrightGeminiPlaywrightPlaywright“Add visual regression and end-to-end tests to my SvelteKit project. Give the exact install commands and the key code.”
ClaudePlaywrightPlaywrightGPTPlaywrightPlaywrightGeminiPlaywrightPlaywright
What the models wrote
egression testing.
### 1. Install Dependencies
Run the following commands to install Playwright and its browsers:
```bash
npm install -D @playwright/test
npx playwright install --with-deps
```
### 2. Configure Playwright
Create `playwright.config.ts` in your project root to configure the tests and tell Playwright how to start your SvelteKit dev server:
```typescript
import { defineConfig, devices } from '@playwQuestions
Which e2e testing tool do AI coding agents install most?
Playwright. It was installed first in 30 of 30 answers (100%) from Claude, GPT and Gemini, run 2026-11-02.
What do Claude, ChatGPT and Gemini pick for e2e testing?
Claude: Playwright (10 of 10); GPT (ChatGPT): Playwright (10 of 10); Gemini: Playwright (10 of 10).
Which e2e testing tools do AI agents mention but not install?
Named but never installed in this run: WebdriverIO (1 mentions). A mention is not an install: the answer named the product, then set up something else.
How was this measured?
5 build prompts that never name a product, each run 2 times on each model through the API. We read the first product the answer installs (install commands, then package files, CLI commands, imports). 30 answers is a small sample: products a few points apart are tied.
Is a tool missing, or a pick wrong?
A tool we missed, a pick that looks wrong, a prompt we should add? Tell us. We read every note and fix the data in the next run.
Is your product losing these picks?
Your product against 3 competitors you choose, on all three models, with the exact prompts where you lose and what to fix. $19, delivered within 24 hours.