Same prompt, different Geneva

Each AI model got the same short prompt, once. No location hints, no tool guidance, every model run in isolation. Click a card to open what the model built.

Old Town · Lakeside · Cornavin · UN · Place de Neuve · Bastions

T2

Drone flight over Geneva

PromptMake a 3D video flying a drone view over Geneva's Old Town, lakeside, central station, UN, Place de Neuve, and Bastions. (original prompt in Korean)

Max reasoning effort per model · non-interactive run · finished models only

Claude Opus 5.5 result preview

Claude Opus 5.5

297 min · effort max · Renders real swisstopo 3D buildings and aerial imagery with CesiumJS (not hand-modeled) · Resumed after interruption (host restart killed it at 23:45; same session continued) · time estimated · API ~$97 (Anthropic console, incl. $66.76 for the resume)

GPT-6.1 Sol result preview

GPT-6.1 Sol

22 min · effort xhigh · Renders real swisstopo 3D buildings and aerial imagery with CesiumJS (not hand-modeled)

DeepSeek 4.1 Flash result preview

DeepSeek 4.1 Flash

106 min · effort max · API $1.23 via Venice · Resumed after interruption (host restart killed it at 23:45; same session continued) · time estimated

Gemini 3.8 Flash result preview

Gemini 3.8 Flash

8 min · effort high · agy has no max, so high · used image generation tool · first run hit a 3D init error · one fix in the same session (6 min 41 s) included · image paths cleaned at deploy

GLM 5.3 result preview

GLM 5.3

30 min · effort max · Z.AI coding plan · GLM 5.3 Flash attached as vision helper · video only, no web page (1280×720, 45 s)

Grok 4.7 result preview

Grok 4.7

75 min · effort xhigh · Grok CLI subscription · Resumed after interruption (host restart killed it at 23:45; same session continued) · time estimated

GLM 5.3 Flash result preview

GLM 5.3 Flash

84 min · effort max · Z.AI coding plan

T1

Geneva in LEGO

The same six places, shown in LEGO style

Reasoning effort high · interactive run · 3 models

Gemini 4 Argon result preview

Gemini 4 Argon

~30 min · 77.5k output tokens

Claude Opus 5.5 result preview

Claude Opus 5.5

~33 min · 186k output tokens · Press play to start

GPT-6.1 Sol result preview

GPT-6.1 Sol

10 min 3 s · 26.7k output tokens · Scroll to view