What a win it is for open source that qwen and kimi show up on this at all.
Show HN: State of the Art of Coding Models, According to Hacker News Commenters
41–50 of 96 posts
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#42Earlier quoted context omitted.
It's well priced but does that have much relevance for "state of the art coding models", specifically? I wouldn't use Gemini 3 Flash or GPT 5.4 mini for anything except the most trivial work, although both are useful for basic exploratory work. So I'm using a heavy model for the bulk of the work and the cost of that so far outweighs the light model that the light model cost is effectively irrelevant.
It's so interesting to see the wild pendulum swings of LLM sentiment here. If one likes a model then it's capable of one-shotting entire apps. Otherwise it's "only suitable for the most trivial tasks". Never in between.
You're confusing "different people with different opinions" with "wild pendulum swings".
Personally my opinion in this regard is highly consistent over time.
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#43This is awesome data! I've been wanting to measure how closely hype aligns to our results at https://gertlabs.com/rankings
Subjectively, it seemed like DeepSeek V4 Pro had the highest hype/performance ratio (meaning high hype for lower performance). Whereas MiMo V2.5 Pro didn't get much attention despite being the top dog in the open weights world, not even an honorable mention in your chart :( ...
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#44Interpreting these metrics is quite interesting. One thing for sure is that while Claude is currently taking the #1 spot in mentions, it carries a lot of negative sentiment due to API pricing policies and frequent server downtime. On the other hand, the runner-up, GPT-5.5, actually seems to have more positive feedback. Personally, my experience with Codex wasn't as good as with Claude Code (Codex freezes on Windows m…
Yeah, I think we are pretty past an idea of "better" and are at the point where it needs qualification as "better at". "Claude writes, Codex reviews, and Gemini doesn't get installed" is my go-to, although I go to Gemini whenever I want an advanced graphical calculator, or data extraction of any type.
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#45[dead]
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#46Interpreting these metrics is quite interesting. One thing for sure is that while Claude is currently taking the #1 spot in mentions, it carries a lot of negative sentiment due to API pricing policies and frequent server downtime. On the other hand, the runner-up, GPT-5.5, actually seems to have more positive feedback. Personally, my experience with Codex wasn't as good as with Claude Code (Codex freezes on Windows m…
Yeah, I think we are pretty past an idea of "better" and are at the point where it needs qualification as "better at". "Claude writes, Codex reviews, and Gemini doesn't get installed" is my go-to, although I go to Gemini whenever I want an advanced graphical calculator, or data extraction of any type.
Mostly my experience, but “Gemini crunches data” would be my replacement there.
If I have a task that requires parsing through swathes of irregular data that traditional ml would choke on (or require an intermediate training step ala bigquery), I have gotten much better results from Gemini than the other two.
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#47Interpreting these metrics is quite interesting. One thing for sure is that while Claude is currently taking the #1 spot in mentions, it carries a lot of negative sentiment due to API pricing policies and frequent server downtime. On the other hand, the runner-up, GPT-5.5, actually seems to have more positive feedback. Personally, my experience with Codex wasn't as good as with Claude Code (Codex freezes on Windows m…
I know its subjective, but I tried different models with my OpenRouter subscription and VSCode Roocode plugin. I evaluated them based on cost and code quality. I liked gemini-3-flash-preview.
Its really a cost effective model.
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#48Interpreting these metrics is quite interesting. One thing for sure is that while Claude is currently taking the #1 spot in mentions, it carries a lot of negative sentiment due to API pricing policies and frequent server downtime. On the other hand, the runner-up, GPT-5.5, actually seems to have more positive feedback. Personally, my experience with Codex wasn't as good as with Claude Code (Codex freezes on Windows m…
I think it's decidedly preliminary to compare models using the same .md file, since they respond quite differently to the same input. I try to narrow to the top 2-3 and then refine inputs for each one. For me it's unfortunately not much better than an intuitive process of trial and error. Gemini is not at all unusable. It is quite usable for the tasks it excels at - to the point that it is the top pick for many tasks…
What are your prompting and general tips for using Gemini effectively?
And what use cases do you think it’s best suited for?
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#49This is awesome data! I've been wanting to measure how closely hype aligns to our results at https://gertlabs.com/rankings Subjectively, it seemed like DeepSeek V4 Pro had the highest hype/performance ratio (meaning high hype for lower performance). Whereas MiMo V2.5 Pro didn't get much attention despite being the top dog in the open weights world, not even an honorable mention in your chart :( ...
There is one mention of Mimo V2.5 Pro in the data by... you! In the UserRatings tab in the sheet, if you want to have a look.
Searching for it on HN shows very few results, that's why it's not showing up in the analysis yet. But it might in the future, once it gains traction.
I'll keep an eye on it, thanks for bringing it up!
Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters
#50Interpreting these metrics is quite interesting. One thing for sure is that while Claude is currently taking the #1 spot in mentions, it carries a lot of negative sentiment due to API pricing policies and frequent server downtime. On the other hand, the runner-up, GPT-5.5, actually seems to have more positive feedback. Personally, my experience with Codex wasn't as good as with Claude Code (Codex freezes on Windows m…
Yeah, I think we are pretty past an idea of "better" and are at the point where it needs qualification as "better at". "Claude writes, Codex reviews, and Gemini doesn't get installed" is my go-to, although I go to Gemini whenever I want an advanced graphical calculator, or data extraction of any type.
"Gemini researches" has been my go-to for awhile (although GPT seems to have gotten better recently in this category?).
Essentially, I use it when I truly only need an "Advanced Google" to find lots of document or website references based on only some partial understanding of "X". I don't like having it do anything with those things. Only when I need to find those things.
Claude, especially, seems to absolutely hate doing research when there are major ambiguities in your question. It's the only one of the major models that keeps playing 20 questions with me when I neither know nor care what the answers to those questions are.