AI Model Reviewer

Claude Opus 5.5 in a raw API call

raw API baseline

← Open in the gallerySame prompt, all models

Zoom, inline player and more ways to view
Poster frame of Claude Opus 5.5's page
Open the original page

The model's own page, run in a sandboxed frame only when you ask (a page that needs its own origin opens in a new tab on a separate demo site). Phones get a full-screen player capped at 1.5x pixel density (2x on larger screens) so it stays smooth; the original page runs uncapped. Tap inside for sound.

Recorded from the live demo. Preview video recorded by this site from the live demo. The moving picture above is that preview; the button runs the real page.

OKHow an AI model race works: 35-second animated explainer (HTML)n/a effortRaw baseline

Wall time 10m 49sCost not recorded: the run's token counts were never reported, so there is no estimate

Review

No verdict yet.

The full review

OK. finish=end_turn

Scores

AI judge

Not scored

No rubric for this prompt

Visitor votes and reviewer grades are not available yet.

AI judge
AI judge: the test runner (model claude-opus-5-5), scoring by visual review of the 1600 px render against the pre-registered rubric. No AI-judge score exists for this result: there is no rubric for this prompt, so no score is shown and none is made up.
Visitors
Public voting with a blind reveal is coming: you score the output first, then see the other scores.
Reviewer
The reviewer's own grade appears here once it is added.

Scores compare results for the same prompt only. AI-judge boards rank runs within one prompt, equal totals sharing a rank; scores from different prompts are never averaged.

Downloads

Files actually published for this run. Original output, site-made previews and post-run conversions are labelled separately.

The exact prompt

raw API call, 2,027 characters. Every result for this prompt

Create a single self-contained HTML file (inline CSS and JavaScript only; SVG and/or canvas; no external libraries, fonts, images or network requests) that plays a polished 35-second animated explainer video in the browser, like a studio motion-design piece. It plays once from start to finish and then holds on the final frame.

Topic: "How an AI model race works" — how one prompt is sent to four AI models and their results are compared fairly.

Scenes and timing (total 35 s):
1. 0-5 s: Hook. Big kinetic headline "One prompt. Four AIs." builds letter by letter; a glowing prompt card slides in.
2. 5-11 s: The prompt card splits into four copies that fly into four lanes labelled Model A, Model B, Model C, Model D.
3. 11-18 s: Each lane builds something: blocks of code stream in, a small preview window fills with a different mini artwork per lane (a wave, a chart, a planet, a city skyline), and a stopwatch per lane ticks at a different speed.
4. 18-25 s: A camera icon records each preview; the four previews line up side by side like a film strip, and one lane stalls with a friendly "error" wobble before recovering.
5. 25-31 s: Judging: score bars grow under each preview, a checklist ticks ("same prompt", "no edits", "timed", "saved"), and a folder icon swallows the four results labelled "receipts".
6. 31-35 s: Outro: all elements collapse into a single line: "Same prompt. Real receipts." and hold.

Style:
- Brand colours: deep navy background #0B1020, electric teal #19E3B1 as the main accent, warm amber #FFB547 as the secondary accent, white text.
- Clean geometric shapes, expressive easing (overshoot, staggered delays), smooth transitions between scenes (no hard blank frames), large readable text for a phone screen.
- Portrait 4:5 layout, scaled to fit the browser window and centred.
- Drive all animation from one timeline using requestAnimationFrame and performance.now; the first motion is visible within the first half second; no user interaction needed.

Reply with only the complete HTML file.

How it was made

Wall time 10m 49s

No transcript was delivered with this result.

Cost breakdown

No cost figure: the run's tokens were never reported, so there is nothing to estimate from.

Tokens by typeTokens$ per 1MCost
Input (uncached)not recordedn/an/a
Cache writenot recordedn/an/a
Cache readnot recordedn/an/a
Outputnot recordedn/an/a
Total computed from tokens
unknown
Total reported by the harness
none