AI Showdown Part 2: Bolt.New vs Replit vs Same.dev

Testing the exact same prompt I used for the AI Lovable Showdown

Jun 22, 2025

∙ Paid

Start writing today. Use the button below to create a Substack of your own

Intro

In the past article, I tested a prompt on Lovable with different inference providers (OpenAI vs Gemini vs Anthropic) to create a Japanese Language Learning game called Kanjimon.

Check out the post for the motivation, methodology, and ideas on practical evaluations for Large L…

Keep reading with a 7-day free trial

Subscribe to Practical AI to keep reading this post and get 7 days of free access to the full post archives.