Neonracer
Neon Racer — fullscreen neon racer with vapor-trail particle effects.
What I asked each model — the Neonracer prompt
Every model on this page got this exact prompt inside the Agent Operating System: Neon Racer — fullscreen neon racer with vapor-trail particle effects.
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. 25 frontier models have attempted it so far: Claude Fable 5, Fugu Ultra, Fugu Ultra 1.1, 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. Neonracer 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 Neonracer
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 strong on-brief neon aesthetic — glowing pink/cyan road edges, retro grid, colorful pylons and dashes create a convincing synthwave scene. Weaknesses: the vapor trail particles aren't clearly visible in the shot and the player car is a bit blocky, keeping it just shy of the top.
What I saw: Ultra v2 — top-down neon racer. Smoke-test PASS.
What I saw: Strong neon vaporwave scene with detailed craft, gradient sky, retro sun stripes, and a polished HUD showing 9 enemies to hunt; the vapor-trail particle effects aren't visible in this static shot and no enemies are yet in frame, keeping it just shy of the field's best.
What I saw: Top-down neon racer with vapor trails. Smoke-test PASS.
What I saw: Top-down neon racer with vapor-trail particles, synthwave aesthetic, drift physics, lap timer, procedural track. 22KB.
What I saw: Strong synthwave aesthetic with glowing neon grid, retro sun/skyline, polished HUD, and a detailed ship with vapor-trail particles; enemies (8 hostiles) are present with combat wired in but appear small/distant, keeping it just shy of the field's best.
What I saw: Strong synthwave scene renders beautifully — retro sun with scanlines, glowing neon arches, layered city skyline, and a clean 3D car with cohesive HUD (nitro, speed, brand). Only nit is the vapor-trail particles aren't visible in this static frame, but the overall polish and on-brief execution clearly top the field.
What I saw: Top-down neon racer with vapor trails, synthwave aesthetic, drift, lap timer, procedural track. 22KB.
What I saw: Strong neon aesthetic with glowing title, cyan/pink pillars and a clear car, and the code has a working follow-cam, boost and vapor particles; but the screenshot shows almost no visible particle trail and the pillars float/scatter awkwardly, leaving it polished-looking but generic rather than a standout racer.
The winner on Neonracer
Claude Opus 5 took gold on this task. neon vaporwave racer.
What I saw: Gorgeous vaporwave 3D scene with glowing vapor-trail particles, neon road edges, radar with tracked threats, and rich HUD — the vapor plume behind the craft is exactly on-brief and the twin-moon/skyline backdrop sells the atmosphere. Enemies/threats are present (radar shows 5, triangles ahead) and combat systems are wired up, edging past the field's best.
See Claude Opus 5's full model card: /models/opus5. Direct head-to-head against the runner-up: Claude Opus 5 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.
▶ LIVE
▶ 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 Neonracer — 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 Neonracer · 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.