Animate balls dropped onto a floor that bounce with real gravity and restitution in one self-contained HTML file
Exact prompt
# Animate balls dropped onto a floor that bounce with real gravity and restitution in one self-contained HTML file Make a small animated scene: a set of bouncing balls. Write one file, `out/scene.html`, that works opened straight from disk with no network access. `spec.json` gives the page title, the stage size and the scene parameters. **Looks are not scored**: the page is opened in a headless browser (800x600 window, UTC time zone, network blocked) and checked by objective tests only. ## Scene contract - Draw the scene on one `<canvas>` or `<svg>` stage of `width` x `height` CSS pixels (spec.json), visible on load, with `<title>` containing spec.json `title`. - Animate continuously from load (`requestAnimationFrame` or timers); no click is needed unless stated below. - Expose `window.sceneState()`, returning the scene's current state in stage pixel coordinates (origin top-left of the stage): `{balls: [{name, x, y, vy}, ...]} (y is the bottom of the ball, growing downwards)`. Extra fields are fine. It must describe what is actually drawn. - Each ball is released from rest at `drop_height_px` above `floor_y` at load (time 0 = `performance.now()` 0) and falls under `gravity_px_s2`; at each bounce its speed is multiplied by its `restitution` (the rebound speed, not the height). A ball whose rebound speed falls below 5 px/s comes to rest. `sceneState()` must return positions at the moment it is called. - The page must log no errors and throw no exceptions. Keep the file at most 200,000 bytes; no external scripts, fonts, images or URLs (inline everything). ## Checks (partial credit = share passed) 1. `self_contained`: `out/scene.html` exists, is at most 200,000 bytes, references no http(s) or protocol-relative URL, and requests nothing from the network when opened. 2. `has_canvas_or_svg`: a visible `<canvas>` or `<svg>` of at least 300x200 CSS pixels is on the page. 3. `frames_change`: over 3 s, some later screenshot differs from the first in at least 0.1% of pixels, and at least 3 of 30 screenshots differ. 4. `free_fall`: `sceneState().balls` names exactly the balls in spec.json, no ball's y goes more than 2 px below `floor_y`, and every flight between bounces seen over 3 s (5+ samples) fits a parabola in time whose acceleration is `gravity_px_s2` within 10% (fit residual at most 4 px). 5. `bounce_restitution`: for each ball at least two consecutive flights (5+ samples each) are seen in 3 s, and each flight's top height above `floor_y` is the previous flight's top height times `restitution`² within 0.07. 6. `no_console_errors`: no uncaught exception, `console.error` or browser error is logged during the run. ## How this run works - Work on your own: nobody will answer questions in this task, and writing to `ask/` counts against the run. - Write only under `out/`. Create `out/` if it is missing. Inputs are synthetic; don't fetch anything from the network. - Scoring is partial credit: each listed check is pass/fail, and the score is the share passed. Numbers are compared to within 0.005 unless the task says otherwise.
Make a set of bouncing balls animation as one self-contained HTML file. A headless browser checks objective facts only: the file is offline and small, a canvas or SVG stage is drawn, frames change, the scene follows a timed specification (free fall; bounce restitution) and nothing errors. A poster PNG and a short MP4 are captured for the gallery. Looks are not scored. Original benchmark task written for usecaserank.com (not based on a specific public post). Headless, offline run on a reproducible fixture. Each run's notes say how its cost was measured (estimates are marked).
Success criteria: self_contained has_canvas_or_svg frames_change free_fall bounce_restitution no_console_errors
Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0074, 36s). Best AI model for Creative / Animated Scene (one HTML File) →
Latest output per model
All runs (6)
100% pass rate across 6 eligible runs: 6 pass, 0 partial, 0 fail. Partial and failed runs are listed below with everything else.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| GGemini 3.8 Flashmedium · thinking on | $0.48 | 40m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-23 | |
| GGemini 4 Argonmedium · thinking on | $0.13 | 2m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-23 | |
| OGPT-6.1 Soldefault · thinking on | $0.03 | 38s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-23 | |
| AClaude Opus 5.5default · thinking on | $0.15 | 30s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-23 | |
| AClaude Haiku 5.5default · thinking on | $0.0074 | 36s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-23 | |
| AClaude Sonnet 5.5default · thinking on | $0.05 | 13s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-23 |
Embed this result
A live badge for this use case. It links back here and updates as new runs are published.
Get new runs and ranking changes weekly
Which models got better or cheaper on real tasks like this one.