RUN 20260725-codex-smoke (design + open note)
A benchmark in which language models design roller coasters that RollerCoaster Tycoon 2 builds, tests, and rates.
design mode — models build from scratch
| model | score | intensity | nausea | similarity | best | tokens / cost | |
|---|---|---|---|---|---|---|---|
| 1st | openrouter_openai_gpt-5-nano | no successful coaster | 134k in / 4k out · $0.00 | ||||
score = excitement, scaled down when similarity to a stock library design exceeds 0.5 (an exact or mirrored copy scores 0)
Round 1 build failed trace (11) →
track program (0 pieces)
{
"pieces": [],
"ride_type": 51,
"start": {
"dir": 0,
"x": 0,
"y": 0
}
}