spb/llmindex Public
The discriminative, contamination-resistant, fully transparent LLM ranking — updated live.
TypeScript 77.9%
TeX 15.2%
Python 3.7%
SQL 1.4%
JavaScript 1.1%
Shell 0.5%
1/**2 * llmindex.io — e2e smoke tests (home, methodology, API health)3 * Author: Simon-Pierre Boucher4 * Contact: contact@spboucher.ai5 * License: Proprietary — © Simon-Pierre Boucher, all rights reserved6 */7import { expect, test } from '@playwright/test';89test('home renders leaderboard shell', async ({ page }) => {10 await page.goto('/');11 await expect(page.getByRole('heading', { name: /discriminative LLM index/i })).toBeVisible();12});1314test('methodology shows weights and IRT hyperparams', async ({ page }) => {15 await page.goto('/methodology');16 await expect(page.getByText('Sub-metric weights', { exact: false })).toBeVisible();17 await expect(page.getByText('accuracy_irt')).toBeVisible();18});1920test('API health responds with maintainer credit', async ({ request }) => {21 const res = await request.get('/api/v1/health');22 const body = await res.json();23 expect(body.maintainer).toContain('Simon-Pierre Boucher');24});2526test('API methodology exposes weights, never answer keys', async ({ request }) => {27 const res = await request.get('/api/v1/methodology');28 expect(res.ok()).toBeTruthy();29 const body = await res.json();30 expect(body.submetric_weights).toBeDefined();31 expect(JSON.stringify(body)).not.toContain('answerKey');32});33