Cloth
Cloth — physical cloth simulation draping over an object.
What I asked each model — the Cloth prompt
Every model on this page got this exact prompt inside the Agent Operating System: Cloth — physical cloth simulation draping over an object.
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. 23 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 K3, MiniMax M3, Hermes MoA, Opus 4.8, Claude Opus 5, Qwen 3.8, Qwen 3.7, Claude Sonnet 5, DeepSeek V4 Pro, DeepSeek V4 Flash, Kimi K2.7, Kimi K2.7 · Fast, Kimi K2.7 · No-Think, Kimi K2.7 · Quality.
Why this task matters. Cloth is a textbook test of sim-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 Cloth
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: Strong Verlet cloth with structural+shear constraints draping convincingly over the sphere, nice gradient texture and folds visible in the render; loses a touch to slight harsh specular blowout and the cloth not fully settling/pooling at the floor for a cleaner drape.
What I saw: Ultra v2 — verlet cloth sim, drag to deform. Smoke-test PASS.
What I saw: Mini gap-fill — verlet cloth. Smoke-test MAYBE (0.1% diff) — needs drag-on-mesh which generic input didn't replicate.
What I saw: Verlet-integrated cloth on three.js + WebGL with OrbitControls. Pin corners, drag any point. Real-time physics, not a billboard.
What I saw: Polished UI and solid Verlet physics code, but the screenshot shows only a dark sphere with a shadow and NO visible cloth draping — the core deliverable appears missing/off-screen, making it a broken render despite the good scaffolding.
What I saw: Renders cleanly with a convincing draped cloth showing real folds and creases over a polished sphere, gradient fabric coloring and clean UI (gust/reset controls, orbit hint) all shipping-quality. Verlet sim with structural/shear/bend constraints and sphere collision is solid, though the drape looks slightly stiff/faceted and the cloth folds are a touch chaotic rather than settling elegantly, keeping it just shy of the top.
What I saw: Verlet-integrated cloth simulation, pin corners, drag to deform. 14KB.
What I saw: Renders cleanly with polished typography/UI, but the core brief fails: the 'cloth' sits as a flat plane hovering entirely above the sphere with no actual draping, and the sphere is fully visible rather than covered — it's a sine-wave sheet, not physical cloth simulation with real constraints or drape.
What I saw: Strong render: the checkered cloth drapes convincingly over the sphere with realistic folds, soft shadows, and clean UI; loses a touch because the underlying pedestal/sphere object is fully hidden and the scene reads slightly flat rather than showing the object being draped.
The winner on Cloth
Qwen 3.8 took gold on this task. Elegant draped cloth.
What I saw: Gorgeous, dramatic drape with visible weave texture, corner-pinned peaks and the teal sphere reading clearly through the fabric — cinematic lighting and vignette elevate it above the field; only minor nit is the cloth resolution/collision looks slightly coarse at the sphere contact.
See Qwen 3.8's full model card: /models/qoder. Direct head-to-head against the runner-up: Qwen 3.8 vs Hermes MoA.
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
▶ LIVEHow I scored Cloth — 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 sim benchmarks: all tasks in the Sim category · See the best AI model for Cloth · 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.