Orbit

What I saw: Renders cleanly with a glowing sun, colored planets, starfield and solid 3D orbit/zoom/spawn controls plus real N-body physics with softening and substeps; however the screenshot shows no visible orbital trails and a somewhat sparse, static-looking layout, keeping it strong-but-generic rather than a task winner.

What I saw: 26KB inner-solar-system orbit map with a glassmorphic info panel, kicker badge, blurred backdrop, hover cards. Cleaner UI than Fusion's same-task attempt — beats it on polish.

What I saw: Inner-system orbit map with hover info. Smoke-test PASS.

What I saw: Top-down inner-system map: Mercury / Venus / Earth / Mars orbiting the sun with accurate relative speeds. Per-planet colour palette, info card on hover, controls bar at bottom with speed slider and play/pause. Solid hit on the brief, ties with GLM on the same task.

What I saw: Strong 3D presentation with glowing sun, orbiting planets, gravity-well grid, and a full control suite (presets, G/time/trail sliders, launch mode); however FPS reads only 9 which signals a performance issue that dampens the sim's smoothness.

What I saw: Opus nailed the brief — labelled planet orbits, a real NEO / close-pass panel, a sim clock. GLM went for drama: a glowing nebula swirl that's gorgeous but reads more galaxy than orbit map. Kimi's is accurate but dim and sparse.

What I saw: Strong 3D render with glowing sun, ringed body, orbital trails, polar grid, and a clean glassy UI with live stats, energy drift, inspector, and comet/reset controls—clearly on-brief and shippable. Minor caveat: it's a curated N-body-flavored system rather than a chaotic true N-body demo, but the polish and completeness edge it to task-winner level.

What I saw: A proper inner solar system now — a glowing Sun, four planets riding clean elliptical rings, a starfield, a data HUD and play/speed controls. The vague first sentence drew blurry circles; this one reads instantly.

What I saw: Clean render with polished title, colorful glowing bodies, starfield and working 3D orbit/spawn interactions; but the physics uses non-symplectic Euler with a hard bounds hack, no orbital trails, and the scattered layout doesn't visually read as gravitational clustering—competent but generic versus the field's best.

What I saw: Opus nailed the brief — labelled planet orbits, a real NEO / close-pass panel, a sim clock. GLM went for drama: a glowing nebula swirl that's gorgeous but reads more galaxy than orbit map. Kimi's is accurate but dim and sparse.