Get the Agent OS + join 4,000+ founders inside the AI Profit Boardroom → Join AIPB ($59/mo)
Page

Aipbpromo

AIPB Promo — Remotion-style cinematic motion-graphics video advert for the AI Profit Boardroom, auto-playing scenes, animated stats, end CTA.

CategoryPage
Models tested24
Scored18/24
Avg score7.48/10
WinnerQwen 3.8

What I asked each model — the Aipbpromo prompt

Every model on this page got this exact prompt inside the Agent Operating System: AIPB Promo — Remotion-style cinematic motion-graphics video advert for the AI Profit Boardroom, auto-playing scenes, animated stats, end CTA.

Single HTML file out. No iteration. No examples in the system prompt. Whatever each model produced on the first run is what's on this page. 24 frontier models have attempted it so far: Claude Fable 5, Fusion, Gemini 3.6 Flash, GLM-5.2, GPT-5.6 Sol, Grok, Hy3, Inkling, Kimi K2.7, Kimi K3, MiniMax M3, Hermes MoA, Muse Spark 1.2, Opus 4.8, Claude Opus 5, Qwen 3.8, Qwen 3.7, Claude Sonnet 5, DeepSeek V4 Pro, DeepSeek V4 Flash, Fugu Ultra 1.1, Kimi K2.7 · Fast, Kimi K2.7 · No-Think, Kimi K2.7 · Quality.

Why this task matters. Aipbpromo is a textbook test of page-class capability — the kind of build that exposes whether a model is doing pattern-matching or actual reasoning. Shipping this cleanly is the floor for what I expect from a frontier model — every model on the leaderboard should at least attempt it.

How each model handled Aipbpromo

Ranked by my 0–10 score from the source comparison guides on agentos.guide. Click any to play the actual one-shot HTML the model produced.

Claude Fable 5 Anthropic
• 7.5/10

What I saw: One-shot: clean gold-on-aubergine auto-playing ad, count-up stats caught mid-animation, progress bar + scene dots, deterministic 30s loop. Eyeballed.

▶ Play Claude Fable 5's attempt →
Fusion OpenRouter
• 7.5/10

What I saw: 120KB · auto-plays clean (video ad, input n/a) · css timeline

▶ Play Fusion's attempt →
• 7.8/10

What I saw: Clean cinematic hero scene with polished gradient typography, working timeline/scene HUD, and playback controls at 00:04/00:22 confirming auto-play motion. The dead-black background lacks the promised Three.js visual richness in this frame and reads slightly generic versus the field's best.

▶ Play Gemini 3.6 Flash's attempt →
GLM-5.2 Zhipu / Z.ai
• 7.5/10

What I saw: 25KB · plays clean · plain

▶ Play GLM-5.2's attempt →
GPT-5.6 Sol OpenAI
🥈 8.3/10 · Cinematic scene player

What I saw: Polished cinematic intro with gorgeous gradient headline, orbit system, floating chips, and a real chapter timeline with play/pause/seek controls that reads distinctly Remotion-like. Slightly generic word-reveal motion and the paused-state overlay obscuring the hero text hold it just below a clear task win.

▶ Play GPT-5.6 Sol's attempt →
Grok xAI
• 7.0/10

What I saw: 11KB · plays clean · plain

▶ Play Grok's attempt →
Hy3 Tencent Hunyuan
• 7.4/10

What I saw: Clean multi-scene pipeline with animated count-up stats, gold/cyan cinematic palette, particle field and progress bar render correctly; but the stats appear left-clustered and off-center with only two of four visible mid-animation, feeling sparse rather than composed, keeping it solid-but-generic rather than a task winner.

▶ Play Hy3's attempt →
Inkling Thinking Machines
• 6.8/10

What I saw: Renders cleanly with a striking gradient logo, glowing 3D torus and polished glassmorphic stat cards, but it's a single static-ish scene—no multi-scene 'Remotion-style' sequencing, no count-up stat animation, and the ring visually clashes with the center CTA, falling short of the cinematic auto-playing video brief.

▶ Play Inkling's attempt →
Kimi K2.7 Moonshot AI
• 7.0/10

What I saw: 20KB · plays clean · plain

▶ Play Kimi K2.7's attempt →
Kimi K3 Moonshot AI
• 6.5/10

What I saw: The 3D wireframe starfield background renders beautifully and the HUD (progress bar, scene tags, dots, skip) is polished, but the screenshot captured a PAUSED state showing no actual scene content—no logo, stats, or CTA visible—leaving the core cinematic brief unproven in the render.

▶ Play Kimi K3's attempt →

The winner on Aipbpromo

Qwen 3.8 took gold on this task. cinematic promo reel.

What I saw: The cold-open scene renders beautifully — massive Bebas Neue headline with gold 'NO OFF HOURS' accent, typed monospace line, HUD framing, film grain and timeline bar all read as a polished Remotion-style reel; source confirms a full 4-scene timeline with animated count-up stats, montage chips and end CTA. Loses a touch since only scene 1 is visible and stats/CTA polish can't be verified in-frame, but the craft and on-brief cinematic direction clearly rival the field's best.

See Qwen 3.8's full model card: /models/qoder. Direct head-to-head against the runner-up: Qwen 3.8 vs GPT-5.6 Sol.

Every attempt — live, playable

Side by side. Click any tile to run that model's actual one-shot HTML in a new tab.

How I scored Aipbpromo — methodology

Three axes, 0–10 each, averaged. Runs: drop the .html in a browser; if it opens to a broken page, it scores zero. Hits the brief: did the model ship the thing the prompt asked for, or a different thing it found easier. Looks good: visual polish, motion, interactivity — where most of the gap between gold and silver lives.

My scores trace back to the source comparison guides on agentos.guide. See the full methodology page for data provenance, including which source guide each cell's score came from.

The same stack Julian uses

Run this stack yourself.

Every demo on this bench was built inside the Agent Operating System — one prompt, one shot, single HTML file out. The Agent OS, the prompts, the templates, the weekly walkthroughs and 4,000+ founders shipping with it every day all live inside the AI Profit Boardroom.

4,000+founders
258documented wins
38countries
$59/momonthly