Category

AI Sim benchmarks

11 sim tasks where every frontier AI model gets the same one-shot prompt. Live, playable demos. Real 0–10 scores from Julian Goldie.

Top model in this category
Opus 4.8 →

What I'm testing in the Sim category

Simulation tasks are where the cinematic gap shows. A great fluid sim, particle galaxy, or N-body orbit isn't about whether the model writes correct math — every frontier model can do that. It's about whether the model picks the right colour palette, the right damping, the right camera angle on the first try. The Sim category usually surfaces which models 'have taste' versus which models just execute the prompt literally.

How I score Sim tasks

Same three axes as the rest of the bench: runs (does the .html open to a working page), hits the brief (is the thing I asked for what came back), looks good (visual polish, motion, attention to detail). 0–10 each, averaged. Highest score on each task earns gold; second silver; third bronze. Models without a 0–10 verdict are listed as unranked on the leaderboard.

Source guides for the Sim category: see the methodology page for full data provenance.

Related

Other categories: Game, Page, Visual · all tasks · all models

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