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?
2.6K views
Replies
Sometime Grok for a good outline and Sonnet 4.5 for the detail work using Cursor as the IDE
Humans in the Loop
@johannkrugell any experiences with Composer 1?
relayd
I prefer Opus 4.5 more than Sonnet. Even though Opus maybe be a tad bit slower but it provides better reasoning and context understanding. I personally feel Opus provides a balance in that sense.
Humans in the Loop
@Claude by Anthropic family (Sonnet, Opus) is definitely leading the way
Hands down Sonnet 4.5 for me. Doing okay with Gemini 3 (Flash), but I don't feel GPT 5.2 and I will become a team. It's just it feels like Sonnet really knows e.g. TS in real detail. But then maybe I just like how the others behave in VSCode....
Community Figma MCP server
Where is Opus?
Humans in the Loop
+1 @Claude by Anthropic
I don't think there are big gaps between those models; it depends on the problems I am trying to solve. I usually start with Sonnet 4.5 and try others if it fails to resolve my problem. In cursor, they allow you to run multiple models in parallel, actually
Humans in the Loop
@flyaway have you experimented with Composer 1? any feedback/thoughts?
@fmerian No, actually. But will try and keep u posted ;)
Humans in the Loop
@flyaway looking forward to your thoughts!
I've tried different models over the course of one year, and I fell in love with anthropic, I feel it's the best model when it comes to complex coding and understanding.
Humans in the Loop
@Claude by Anthropic is leading the way
I thought Claude was top contender, but I've had bugs all day there and it freezes on me. Maybe I'm just used to ChatGPT now.
Definetly opus 4.5, but also shotout to MiniMax M2, thing is Opus is just soo good, and claude code harness is just amazing to work with
Humans in the Loop
@nicoeft never experimented with @Minimax M2 tbh. it's available for free on @Kilo Code -- might give it a spin. thanks!
I lean toward Sonnet 4.5 for correctness—it rarely messes up. Same time, Gemini sometimes surprises me with really smart suggestions.