AI vs. The Dash: A Code Replication Challenge
Here we embark on a decisive AI test and comparison.
The rules of this experiment are simple.
We tasked three major AI models—Gemini, Claude Sonnet, and GPT—along with a bonus challenger, Grok, to replicate the core mechanics of the popular rhythm-based platformer, Geometry Dash, using only three simple prompts.
The goal was to see which model could produce the most accurate and, critically, the most playable result.
The Challenger: Gemini
Gemini: Best Score Calculation, Most Playable
Gemini's output stood out immediately. The resulting levels were noted as being quite repetitive. However, the key victory was its singular, functional game mode.
Crucially, it was the only one that was genuinely playable. The mechanics were solid enough to be considered even a bit addictive. It also implemented the most robust and accurate score calculation, tracking player progress best.
The Contender: Claude Sonnet
Claude Sonnet: Randomness and Complexity
Claude Sonnet showed ambition by producing three distinct game modes. It handled level generation well, creating genuinely random levels, which was a nice feature.
However, the extra complexity introduced bugs. The "ship" mode required a quick fix to make the flying mechanics function correctly. The "wave" mode remained problematic, with movement that was "still too wavy" and imprecise.
The Underperformer: GPT
GPT: Random Collision, Strictly Unplayable
GPT struggled significantly with the core physics replication. The game suffered from random collision issues. It produced only one very strict level layout.
Ultimately, the result was deemed almost unplayable.
The Bonus Challenger: Grok
Bonus Grok: Playable and Addictive
As a bonus entry, the code generated by Grok surprised the testers. It managed to produce a game that was genuinely playable.
The resulting code was somehow addictive, demonstrating a better understanding of mechanics than expected.