Vibe coding

Vibe coding

Best AI for vibe coding: pick the model and the tool together

Claude, GPT, Gemini or an open model: which AI works best for vibe coding, why the tool around it matters just as much, and how to test it yourself.

AI Vibe Coding LLM Claude GPT Gemini Harness Claude Code Cursor

A leaderboard that isn't about your code

Search for the AI that codes best and you'll find a new leaderboard every month. It measures a model in one setup, on tasks that aren't yours.

Model and tool as one choice

The same model performs differently in a different tool. So pick a combination of model and tool, and test it on a real task from your own work.

A choice you can check yourself

After an afternoon of testing you know which combination works best in your codebase, and you don't have to chase every new leaderboard.

The short answer

For vibe coding, the top models from Anthropic (Claude) and OpenAI (GPT) currently work best. Google’s Gemini is close behind and cheaper. Open models such as Qwen3-Coder and Devstral run on your own machine, but stall sooner on large tasks.

The model is only half the choice. The other half is the tool around it: Claude Code, Codex CLI, Cursor or an app builder like Lovable. The same model writes better code in one tool than in another. So choose a combination, and test it on your own work.

Why “the best model” is only half the answer

A language model predicts text. To build code with it, you need software that lets the model read files, run commands, feed errors back and keep track of what it’s doing. That software is called a harness. Claude Code, Codex CLI, Gemini CLI and Cursor are harnesses. What that means exactly is explained in what is an AI harness.

The harness decides how much of your project the model gets to see, when it stops to ask and how it recovers from a mistake. That’s why a Claude model does different things in Cursor than the same model in Claude Code. The leaderboards you find online usually test a model in one fixed setup, so they say little about how it performs in your tool and your codebase.

The model decides what’s possible. The tool decides how much of it ends up in your code.

The models that matter

A new version ships every few months and the top spot changes hands. The families stay, and their character barely shifts.

🟠

Claude, by Anthropic

Strong on long tasks that touch many files, and good at following the instructions in your repo. The default for many developers who build with agents, and the model behind Claude Code.

⚫

GPT, by OpenAI

Strong at reasoning and at tricky, well-defined problems. Works best in Codex CLI or ChatGPT, and is an option in most editors.

🔵

Gemini, by Google

A large context window, so lots of code in view at once, and a low price. You can try it for free with a Google account in Antigravity CLI, the successor to Gemini CLI.

🔓

Open models

Qwen3-Coder, Devstral and gpt-oss run locally, so your code never leaves your machine. Good for well-scoped tasks, less so for long tasks across many files.

Model and tool side by side

Every model maker has its own harness, tuned to its models. That’s usually the best place to try a model.

Claude GPT Gemini Open model
Own tool Claude Code Codex CLI Gemini CLI or Antigravity CLI OpenCode or Aider
Where you already have it Claude Pro and Max ChatGPT Plus and up Free with a Google account On your own machine, via Ollama
Strong at Long tasks across many files Tricky, well-defined problems Keeping lots of code in view Privacy and fixed costs
Watch out for Sometimes does more than you asked Needs a clear brief Less consistent on long tasks Stalls on large tasks

In Cursor and Cline you pick a model per task. App builders like Lovable, Bolt and v0 choose the model for you, so there you compare the tools, not the models. Which tool fits which situation is covered in vibe coding tools: which one should you use.

Which AI fits your situation

💡

You're building an app from an idea, without reading code

Pick an app builder like Lovable or Bolt and leave the model to the tool. You'll notice the difference between tools more than between models.

🖱️

You work in an editor and read along

Use Cursor and switch per task: a Claude model for work that touches many files, a GPT model for a tricky standalone problem.

⚡

You let an agent work on its own

Use the model with its own harness: Claude with Claude Code, or GPT with Codex CLI. They're tuned to each other, and you notice that most on long tasks.

🔒

Your code can't leave your machine

Use an open model via Ollama, with OpenCode or Aider. Give it at least 32K of context and keep the tasks small.

How to test it yourself

A leaderboard is no substitute for an afternoon of testing. Pick a real task from your own work, something you need to build this week anyway. Give it to two model-and-tool combinations with the same brief. Then look past whether it works: how much did you have to steer, and do you still understand the code?

Put your conventions in an instruction file in your repo, such as CLAUDE.md or AGENTS.md. Both combinations then get the same rules, and they come with you when you switch later. How to set a tool up properly for your own code is covered in harness engineering. For the full list of harnesses, see the best AI harness for coding.

What no model solves

Whichever AI you choose, they’re all built to get you to something that works as fast as possible. Whether it’s secure, whether it scales and whether anyone still understands it a year from now, no model checks that for you. A better model makes those mistakes less often, not never.

If you want to put what you built with AI live, read how to make a vibe-coded app production-ready. We’re seven independent senior developers from Rotterdam who work with these models every day. In a vibe coding audit we read through your code and tell you what it needs before it can go live.

Frequently Asked Questions

What is the best AI for vibe coding?

Right now the top models from Anthropic (Claude) and OpenAI (GPT) work best for vibe coding, with Google's Gemini close behind and cheaper. But the model is only half of it: the tool around it, such as Claude Code, Codex CLI or Cursor, decides how much you get out of it. Pick a combination of model and tool and test it on a real task from your own work.

Is Claude or ChatGPT better for coding?

Both are strong. Claude is especially good at long tasks that touch many files and at following instructions. GPT is strong at reasoning and tricky, well-defined problems. For coding, use each in its own tool: Claude in Claude Code, GPT in Codex CLI. In Cursor you can switch per task.

What's a good free AI model for vibe coding?

Google's Antigravity CLI, the successor to Gemini CLI, works for free within limits with a Google account and is a good place to start. If you don't want to pay per use at all, run an open model such as Qwen3-Coder or Devstral locally via Ollama, with OpenCode or Aider. Local models are weaker on large tasks, though.

Which AI model do Lovable and Bolt use?

App builders like Lovable, Bolt and v0 choose the model themselves and switch when a better one comes along. You don't need to pick a model there. With those tools, compare what they deliver and how much control you keep over the code.

Why does the same model give different results in different tools?

Because the tool decides what the model gets to see and what it's allowed to do. One tool reads more files before it starts, another asks for permission more often or keeps the conversation shorter. That software around the model is called the harness, and it often makes as much difference as the model itself.

Should I switch when a new model comes out?

Only if it performs better on your own work. Test a new model on the same task as your current combination. Keep your instructions in a file in your repo, such as CLAUDE.md or AGENTS.md, and switching takes an afternoon.

Built something with AI and want to put it live?

We read through your code and tell you what it takes to get it safely into production, whichever model wrote it.

Let's discuss your project

From AI prototypes that need to be production-ready to strategic advice, code audits, or ongoing development support. We're happy to think along about the best approach, no strings attached.

010 Coding Collective free consultation
free

Free Consultation

In 1.5 hours we discuss your project, challenges and goals. Honest advice from senior developers, no sales pitch.

1.5 hours with senior developer(s)
Analysis of your current situation
Written summary afterwards
Concrete next steps