Grok 4.5 vs Meta Muse Spark 1.1 vs Fable 5 vs GPT 5.6 Sol
Same prompt for all four:
"Build Minecraft, but it’s a modern AAA title built for playing in the browser. Focus on performance, complete functionality, and at least a 5 minute vertical slice that is playable. Punch trees, make planks, build crafting table, make wooden pickaxe, mine stone."
Results:
Claude was the best but took 1.5 hours, Grok fastest at 8m29s but also worst quality and functionality.
Full write-up and all 4 are playable in the link.
Any ideas on what to test next, or how to handle a controlled experiment with follow-up prompts?
If it benefits the software developer and this is what allows their business to work, then that benefits you. If it didn't then you wouldn't have the app.
I've been writing Rust for about 2 years, I read this and learned all kinds of stuff I still did not know. Fantastic job on this! I am now a bit upset that everything isn't taught this well :o