What's the best AI model for coding?
New AI models pop up every week. Some developer tools like @Cursor, @Zed, and @Kilo Code let you choose between different models, while more opinionated products like @Amp and @Tonkotsu default to 1 model.
Curious what the community recommends for coding tasks? Any preferences?
3K views
Replies
Voted for Sonnet 4.5 Been testing different models for a few months now. Here's what I've noticed:
• Sonnet 4.5 hits the sweet spot between speed and accuracy for coding tasks
• GPT-5.2 is powerful but slower and more expensive
• Gemini 3 is improving fast but still catching up on complex codebases
The 71% vote makes sense - it's not just hype. Sonnet actually delivers for day-to-day development work. Curious what others think about the cost-performance tradeoff. Are you sticking with one model or switching based on task complexity?