Game

Raycaster

Raycaster Maze — build a Wolfenstein-style 3D maze you can walk through.

CategoryGame
Models tested3
Scored3/3
Avg score7.67/10
WinnerKimi K2.7

What I asked each model — the Raycaster prompt

Every model on this page got this exact prompt inside the Agent Operating System: Raycaster Maze — build a Wolfenstein-style 3D maze you can walk through.

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. 3 frontier models have attempted it so far: GLM-5.2, Kimi K2.7, Opus 4.8.

Why this task matters. Raycaster 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 Raycaster

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.

GLM-5.2 Zhipu / Z.ai
🥉 6.5/10

What I saw: Kimi nailed it — brick walls, a checkered floor, a clean minimap, textbook Wolfenstein, runs clean out of the box. Opus's is close and more atmospheric: warm fog and a vignette down a stone corridor (A/D to turn, W/S to move). GLM's engine is genuinely good — brick and mossy-stone walls, fog, a minimap — but its one-shot spawned the player buried inside a wall, dead on arrival; I nudged the start one cell so you can actually walk it. That spawn bug is why it scores lowest here, even though the e

▶ Play GLM-5.2's attempt →
Kimi K2.7 Moonshot AI
🥇 8.5/10 · winner · cleanest

What I saw: Kimi nailed it — brick walls, a checkered floor, a clean minimap, textbook Wolfenstein, runs clean out of the box. Opus's is close and more atmospheric: warm fog and a vignette down a stone corridor (A/D to turn, W/S to move). GLM's engine is genuinely good — brick and mossy-stone walls, fog, a minimap — but its one-shot spawned the player buried inside a wall, dead on arrival; I nudged the start one cell so you can actually walk it. That spawn bug is why it scores lowest here, even though the e

▶ Play Kimi K2.7's attempt →
Opus 4.8 Anthropic
🥈 8.0/10

What I saw: Kimi nailed it — brick walls, a checkered floor, a clean minimap, textbook Wolfenstein, runs clean out of the box. Opus's is close and more atmospheric: warm fog and a vignette down a stone corridor (A/D to turn, W/S to move). GLM's engine is genuinely good — brick and mossy-stone walls, fog, a minimap — but its one-shot spawned the player buried inside a wall, dead on arrival; I nudged the start one cell so you can actually walk it. That spawn bug is why it scores lowest here, even though the e

▶ Play Opus 4.8's attempt →

The winner on Raycaster

Kimi K2.7 took gold on this task. winner · cleanest.

What I saw: Kimi nailed it — brick walls, a checkered floor, a clean minimap, textbook Wolfenstein, runs clean out of the box. Opus's is close and more atmospheric: warm fog and a vignette down a stone corridor (A/D to turn, W/S to move). GLM's engine is genuinely good — brick and mossy-stone walls, fog, a minimap — but its one-shot spawned the player buried inside a wall, dead on arrival; I nudged the start one cell so you can actually walk it. That spawn bug is why it scores lowest here, even though the e

See Kimi K2.7's full model card: /models/kimi. Direct head-to-head against the runner-up: Kimi K2.7 vs Opus 4.8.

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 Raycaster — 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 3,600+ founders shipping with it every day all live inside the AI Profit Boardroom.

3,600+founders
258documented wins
38countries
$100k+/mocommunity MRR