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
I've been using Opus 4.5 via Claude Code. Full disclosure, I've been quite skeptical about AI development, but have been consulting for an Anthropic partner and have been using it for some internal tooling. It can be pretty powerful if used correctly, although it still makes a lot of questionable decisions and mistakes, and needs decent oversight.
A few tips:
👉 You want to stay within about 40% of the context window. It's the sweet spot to get the best results.
👉 I first plan, and ask CC to create a feature spec, ideally broken down into stages.
👉 ALWAYS start with a clean working tree
👉 I start a new session, and ask it to read through the feature spec and implement stage 1
👉 Review the diff and make any necessary changes.
👉 Commit, and start a new session.
👉 Repeat.
I also try to stay away from very indepth claude.md instructions. They tend to confuse it and overload it with instructions and it skips instructions. I also keep a directory with feature definitions (generated by CC) as well as a folder for specific todos. (Basically skills, but let's be real. Agents and skills are just prompt text files). Like this at the start of a new session I can point it to a specific feature definition without it having to read through the codebase to figure out how the feature works, heavily saving on context size.
@nxnze can confirm about context: once you start stuffing the whole repo into the model, the quality of the solutions drops, especially with backend code..
MUBR
They say it's Claude but in Cursor I never see the difference - especially because ChatGPT has bigger context window.
Humans in the Loop
@ilichev any thoughts on Composer 1?
@ilichev but it also about speed of development, try to use Composer instead of chatGPT, when you have 5 agents coding at the same time it gives you significant productivity boost without quality loss
Hyperaide
Opus 4.5?
Humans in the Loop
@dynamo my favorite. to quote @rauchg, Opus is "on a different level, unreasonably good at @Next.js" - source
@dynamo its the best, but also the most expensive
Tonkotsu
For @Tonkotsu, we use Sonnet 4.5 under the covers (though we're always evaluating the best model) as we've found it's got the right mix of strong agentic coding performance while being relatively fast. Other models are also quite good but tend to have very high latency and go heads-down for a long time.
What we've learned from our users is that while they want to operate at a high level, they also want to see granular progress from the agents — classic manager behavior. Sonnet has the right mix of capability and speed for this.
Humans in the Loop
@derekattonkotsu Oh I like the reasoning, i.e. finding a balance between speed and capabilities.
What would be the close 2nd? And if we look at the capabilities only, what would be the best model from your POV? Also, why not Opus 4.5!?
Tonkotsu
@fmerian Opus is definitely a contender. It's more expensive but very capable and at least in my experience not terribly slower. I've found Codex to be quite smart but it likes to go "heads-down" for a long time before coming back with an answer -- which doesn't fit with the pattern of usage that we see from our users.
SEMrush
Does the pricing also count as a criteria? 😅 Sonnet is quite expensive. Running glm 4.7 and codex 5.2 full-time is only a few percent behind sonnet and costs 3–7x less
Humans in the Loop
@alina_petrova3 Absolutely, cost matters a lot.
In cursor, I have tried Opus 4.5 and GPT 5.2 in the plan mode, and personally, I prefer the former. However, I’m still torn on the best setup for fixing bugs. What are your preferences for debug mode? Do you stick with the same model or switch to a new one?
@yuanyuan_zhang0104 For debugging, nothing beats GPT-5.2x High right now
Humans in the Loop
@brightmirror oh good to know! thanks for the suggestion
In cursor, we use Opus 4.5... I couldn't find a better model than that. Too bad it's not on the list.
Humans in the Loop
@atomer any experiences with Composer 1?
Humans in the Loop
@atomer @Claude by Anthropic ftw haha
Humans in the Loop
great question! definitely ping @aidanhornsby from @Layercode on this - they are the experts here
Opus 4.5. The only downside is it consumes very quickly. So my second choice is sonnet 4.5
Humans in the Loop
@Claude by Anthropic ftw!