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
Best
At this stage I pick based on trust + explainability. Being able to trust the suggestions and understand the reasoning is more valuable than whichever one has the highest benchmark score.
I use Antigravity from google, and mainly use Sonnet and Opus. Its weird but on the same prompt and context, sometimes, Gemini models hallucinates and start rewriting the whole files
Report
Claude Opus 4.5 (Thinking) 32K ?
Report
Anthropic has a huge head start with their models. But to be precise, it's the models coupled with Claude Code that allow us to enter a new era and give superpowers to developers. The only downside to all this remains the price of tokens which are starting to become more and more uncontrollable.
I work a lot on this issue, particularly on token compression technology, which will allow us to better reduce, control, and make the ecosystem a bit more frugal... at least I hope so.
@fmerian Absolutely! That's what we do. @Edgee is a Token Compression technology which can save up to 50% of the token bill. And it works with Claude Code pro/max plan as well
For me personally: gpt-5.2-codex all the way. Dry as a brick, but the results speak for themselves.
Report
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.
Replies
At this stage I pick based on trust + explainability. Being able to trust the suggestions and understand the reasoning is more valuable than whichever one has the highest benchmark score.
Cursor or claude with blocpad
Phia
I use Antigravity from google, and mainly use Sonnet and Opus. Its weird but on the same prompt and context, sometimes, Gemini models hallucinates and start rewriting the whole files
Claude Opus 4.5 (Thinking) 32K ?
Anthropic has a huge head start with their models. But to be precise, it's the models coupled with Claude Code that allow us to enter a new era and give superpowers to developers.
The only downside to all this remains the price of tokens which are starting to become more and more uncontrollable.
I work a lot on this issue, particularly on token compression technology, which will allow us to better reduce, control, and make the ecosystem a bit more frugal... at least I hope so.
Humans in the Loop
@sachamorard - could @Edgee help us reduce the CC bill?
@fmerian Absolutely! That's what we do. @Edgee is a Token Compression technology which can save up to 50% of the token bill. And it works with Claude Code pro/max plan as well
Why have you missed the Opus 4.5?
Humans in the Loop
good point - can't edit the poll! +1 @Claude by Anthropic
Humans in the Loop
@iamasuperuser oooooh good point. I forgot to include Genie 2 by @Cosine in the list. heard great things about @cubic (currently using @OpenAI and @Claude by Anthropic according to their docs). great combo!
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