Gtadrive

What I asked each model — the Gtadrive prompt

Every model on this page got this exact prompt inside the Agent Operating System: GTA Drive — open-city driving sandbox: steal cars, outrun cops, traffic, wanted level, minimap.

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. 7 frontier models have attempted it so far: Fusion, GLM-5.2, Grok, Kimi K2.7, MiniMax M3, Opus 4.8, Qwen 3.7.

Why this task matters. Gtadrive 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 Gtadrive

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.

The winner on Gtadrive

GLM-5.2 took gold on this task.

What I saw: 47KB · plays clean · three, webgl

See GLM-5.2's full model card: /models/glm.

How I scored Gtadrive — 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 Gtadrive · Back to the leaderboard