Flappy Bird Prompt Test

A side-by-side one-shot coding comparison of Flappy Bird clones across frontier models.

Description

A demonstration of the one-shot coding capabilities of several frontier AI models using the simple prompt "Flappy Bird". The comparison showcases generated clones from GPT 5.2, Grok 4.1, Gemini 3.0 Preview, and Blackbox Pro, highlighting differences in visual assets, physics, and UI execution.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.

Details

Why this is interesting: A direct comparison of unreleased or brand-new frontier models on a classic one-shot coding challenge.
Attributed to: @damnGruz
Built with: GPT-5.2 Thinking
Links: app.blackbox.ai
View tweet
Tags: #coding #benchmark #comparison

Discovered: X
First posted: X · Dec 13, 2025
Listed: Added just now
Build: Moderate
Models: Strong