BAA-chmark
BAA-chmark — sheep-herding arcade
A short 3D game about herding sheep. Different models received the same prompt; results range from fully playable games to outputs that cannot be launched.
- 36 results
- 35 demos
- Top-ranked Claude Opus 5
Marek Dubovsky · software developer
I test models on the same assignments and publish their original outputs and runnable demos. I also use Dubovsky Labs to present selected projects.
Model benchmarks
Each benchmark preserves the original model outputs, screenshots, practical evaluation, and playable demos.
BAA-chmark
A short 3D game about herding sheep. Different models received the same prompt; results range from fully playable games to outputs that cannot be launched.
GTA
A more demanding browser open world with a city, cars, pedestrians, police, and missions. Seven models, one assignment, and sharply different quality.
Blog
Longer write-ups about software development, local models, and experiments tested on real projects.
Projects
A new-build property search engine for Slovakia. It tracks more than 600 active residential development projects and updates them through automated data collection.
A toolkit for building terminal UI applications. Python and C++ versions for macOS are in progress; the goal is to make text interfaces for developer tools easier to build.
About
I am a software developer working across desktop, mobile, and web, mainly with C/C++, Python, and JavaScript. I enjoy experimenting and building a wide range of applications, tools, and prototypes. Dubovsky Labs is where I publish projects that can be inspected or tried directly.