Banja Lab / Benchmarks / Test
The same task, run on 28 models. Compare the outputs side by side, or open any one in a popup to inspect it.
Top result: claude-opus-4-8 (low reasoning) at 100.0% composite. Lowest: claude-sonnet-4-6 at 99.1%. 28 models compared on this task.
Build a self-contained FAQ accordion as a single HTML file (`index.html`) that renders with no build step and no network calls (inline all CSS and JS). Requirements: - at least three FAQ items, each with a question header and an answer panel, - each header is a real button exposing accessible state with aria-expanded, starting collapsed (aria-expanded="false") with its panel hidden, - clicking a header expands that item: its aria-expanded flips to "true" and its answer panel becomes visible; clicking again collapses it. Use plain, readable, accessible markup. No external fonts or scripts.