A benchmark to evaluate the quality of different LLM coding harnesses. Same model, same prompt, different tools.
9 agents · same prompt · different results
Ship Sim
Import maps, modular Three.js, day/night cycle with wave controls.
Open Sea
Self-contained single HTML with inline Three.js bundle. Keyboard sailing controls.
Voyager
Clean vanilla JS with verification scripts. Minimal and focused approach.
Ship Simulator
Enhanced variant with bun-built bundle. Polished visual effects.
Sunset Sails
Second iteration with refined aesthetics. Static JS, no build step.
Adrift
Vendored Three.js, minimal vanilla implementation with orbit controls.
Drift
Vite-built with custom fonts, time-of-day slider, and ambient sound.
Sunset Sail
Vendored Three.js with OrbitControls, straightforward implementation.
A Quiet Sea
TypeScript + Vite. Seagulls, splashes, wave audio, ambient soundscapes.