Parachute
Parachute Drop — jump from a plane, freefall, pull the chute, steer to land in a jungle clearing.
What I asked each model — the Parachute prompt
Every model on this page got this exact prompt inside the Agent Operating System: Parachute Drop — jump from a plane, freefall, pull the chute, steer to land in a jungle clearing.
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 1.1, Fusion, Gemini 3.6 Flash, GLM-5.2, GPT-5.6 Sol, Grok, Grok 4.6, Hy3, Inkling, Kimi K2.7, Kimi K3, MiniMax M3, Hermes MoA, Muse Spark 1.2, Opus 4.8, Claude Opus 5, 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. Parachute is a textbook test of game-class capability — the kind of build that exposes whether a model is doing pattern-matching or actual reasoning. A model that ships this in one shot is usually safe to wire into your agent loop for harder tasks of the same shape.
How each model handled Parachute
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: One-shot: spread-eagle articulated skydiver over jungle canopy + river, wind streaks, altimeter tape + vspeed HUD, auto-jump demo. Cloud sprites read flat from above. Eyeballed.
What I saw: Strong deployed-chute skydiver over a jungle canopy with a polished HUD (altitude, dist-to-H, score) plus active drone enemies, flare combat, and 'THREAT DOWN' kill feedback — it delivers the full jump/steer/land loop AND working combat, edging past a bland walking sim.
What I saw: SHOWCASE BUILD (threejs-game-director): cargo-bay interior + jump light, articulated skydiver w/ 7 pose sets, 9-cell ram-air canopy w/ lines, 11.5k instanced trees + carved river, ring-target landing scoring, analog altimeter HUD, auto-demo lands inner ring. Eyeball-gate passed.
What I saw: Strong 3D scene with a well-rendered deployed canopy, articulated diver with suspension lines, layered clouds, jungle terrain and a slick functional HUD (altitude/descent/compass/distance). Slightly held back by the drone-combat framing feeling tacked-on and no enemies visible in this shot, but visually it competes near the top of the field.
What I saw: Strong, clean 3D render with a convincing open chute, rigged skydiver, jungle canopy and a proper HUD showing altitude/fall speed/target and CHUTE OPEN state — polished and clearly on-brief. Slightly held back by the chute filling most of the frame and an empty freefall/plane phase not shown, so it lands solid-shippable but just shy of the field's best.
What I saw: One-shot score. Beautiful freefall: multi-part skydiver in a spread, volumetric clouds, speed streaks, terrain far below and a live altimeter counting 2398m down. But SPACE did nothing across a full 30s descent, the SPACE - DEPLOY prompt never cleared and descent stayed pinned at 052 m/s, so the canopy phase was unreachable. Fed that exact evidence back and Grok 4.6 repaired it itself, and the live demo here is its own fix, with the canopy opening and descent dropping to 005 m/s.
What I saw: Renders cleanly with a detailed articulated skydiver (helmet, suit, arms, boots — not a bare capsule), clean HUD with altitude/distance/phase, and a lush jungle canopy of blobs with a visible river below; but the canopy overhead reads as a flat pink slab rather than a parachute, and the world feels more static/decorative than dynamic mid-drop, keeping it below the field's best.
What I saw: Renders cleanly with cohesive jungle scene, glowing target ring, jumper, and parachute plus a working land-in-clearing state; but the chute sits detached above the figure (ropes disconnected) and the flat green-monochrome palette reads generic rather than winning.
The winner on Parachute
Fusion took gold on this task. showcase · game-director.
What I saw: SHOWCASE BUILD (threejs-game-director): cargo-bay interior + jump light, articulated skydiver w/ 7 pose sets, 9-cell ram-air canopy w/ lines, 11.5k instanced trees + carved river, ring-target landing scoring, analog altimeter HUD, auto-demo lands inner ring. Eyeball-gate passed.
See Fusion's full model card: /models/fusion. Direct head-to-head against the runner-up: Fusion vs Fugu Ultra 1.1.
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 Parachute — 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 game benchmarks: all tasks in the Game category · See the best AI model for Parachute · 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.