Webos
Web-OS Desktop — a working desktop with windows, dock, Notes / Paint / Terminal apps.
What I asked each model — the Webos prompt
Every model on this page got this exact prompt inside the Agent Operating System: Web-OS Desktop — a working desktop with windows, dock, Notes / Paint / Terminal apps.
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, Fugu Ultra, Fugu Mini, Fusion, Gemini 3.6 Flash, GLM-5.2, GPT-5.6 Sol, Grok, 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, Kimi K2.7 · Fast, Kimi K2.7 · No-Think, Kimi K2.7 · Quality, DeepSeek V4 Pro, DeepSeek V4 Flash.
Why this task matters. Webos 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 Webos
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.
What I saw: Renders cleanly with a polished menubar, blurred glass dock with hover labels and running-app dots, and all three apps (Notes, Paint, Terminal) launched and cascading correctly with working traffic-light controls. Strong and shippable, but lacks a maximize/restore and the visuals are competent rather than standout versus the 9.0 top build, so it lands solidly in the strong-but-not-winning tier.
What I saw: Ultra v2 — desktop OS. Smoke-test MAYBE (0.3% diff) — static desktop until you open an app; expected for a UI-shell build.
What I saw: Mini gap-fill (round 2) — desktop OS shell. Smoke-test MAYBE (0.0% diff) — static until an app is opened; flagged for manual verification.
What I saw: A tiny working desktop OS in 24KB — wallpaper, taskbar dock with app icons, draggable resizable windows for Notes, Paint, Terminal (echo-only), Calculator. Apple-Sequoia aesthetic. Most ambitious application build on the bench.
What I saw: Strong, polished glassmorphic desktop with a 3D WebGL wireframe background, working top bar, dock (Terminal/Paint/Notes/Settings), and a functional-looking terminal with prompt; the visible Paint window appears empty (only toolbar/slider showing, no canvas content) which slightly undercuts the multi-app showcase. Clean and shippable but not quite topping the best.
What I saw: Strong, cohesive glassmorphic Web-OS with functional Notes and Terminal windows, a polished dock, desktop icons, topbar and helpful hints — clearly shippable and near the top of the field. Slightly short of the best since Paint isn't shown open and the desktop heading text is partly occluded, but overall a very refined, on-brief build.
What I saw: Web-OS desktop with wallpaper, dock, draggable resizable windows for Notes/Paint/Terminal/Calculator. 33KB — beats Fusion's 24KB attempt on density.
What I saw: Renders cleanly with polished dock, desktop icons, and a functional Terminal window with prompt; drag, close/minimize dots, Paint canvas and localStorage Notes all present per source. Weak point: the title banner is partially hidden behind the window and the empty terminal body looks sparse, making it feel slightly less finished than the top field entries.
What I saw: 30KB working desktop — wallpaper, dock, draggable windows.
The winner on Webos
Fusion took gold on this task. winner · most ambitious app.
What I saw: A tiny working desktop OS in 24KB — wallpaper, taskbar dock with app icons, draggable resizable windows for Notes, Paint, Terminal (echo-only), Calculator. Apple-Sequoia aesthetic. Most ambitious application build on the bench.
See Fusion's full model card: /models/fusion.
Every attempt — live, playable
Side by side. Click any tile to run that model's actual one-shot HTML in a new tab.
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVE
▶ LIVEHow I scored Webos — 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.
Related
More page benchmarks: all tasks in the Page category · See the best AI model for Webos · Back to the leaderboard
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.