We asked four AI coding agents to rebuild Minesweeper—the results were explosive

Agent 1: Mistral Vibe
Overall rating: 4/10
This version got many of the basics right but left out chording and didn’t perform well on the small presentational and “fun” touches.

Agent 2: OpenAI Codex
Overall: 9/10
The implementation of chording and cute presentation touches push this to the top of the list. We just wish the “fun” feature was a bit more fun.

Agent 3: Anthropic Claude Code
Overall: 7/10
The lack of chording is a big omission, but the strong presentation and Power Mode options give this effort a passable final score.

Agent 4: Google Gemini CLI
Overall: 0/10 (Incomplete)

Final verdict
OpenAI Codex wins this one on points, in no small part because it was the only model to include chording as a gameplay option. But Claude Code also distinguished itself with strong presentational flourishes and quick generation time. Mistral Vibe was a significant step down, and Google CLI based on Gemini 2.5 was a complete failure on our one-shot test.

While experienced coders can definitely get better results via an interactive, back-and-forth code editing conversation with an agent, these results show how capable some of these models can be, even with a very short prompt on a relatively straightforward task. Still, we feel that our overall experience with coding agents on other projects (more on that in a future article) generally reinforces the idea that they currently function best as interactive tools that augment human skill rather than replace it.

I've found that AI coding agents are good at building new projects from scratch. Even better if they're building a smallish project with features remixed from known projects, presumably in their training set.

Where they've fallen apart for me is when working in existing, large, projects. When adding new features, or especially when fixing, non trivial, bugs.

Could be skill issue with writing prompts on my part. But since I have the same prompting skills when starting new projects and fixing bugs, I feel like it's an issue within the choosing agents.