Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#1

Post by yunusabd » Sat, May 02, 2026, 9:25 PM UTC

Hello HN,

I was away from my computer for two weeks, and after coming back and reading the latest discussions on HN about coding assistants (models, harnesses), I felt very out of the loop. My normal process would have been to keep reading and figure out the latest and greatest from people's comments, but I wanted to try and automate this process.

Basically the goal is to get a quick overview over which coding models are popular on HN. A next iteration could also scan for harnesses that people use, or info on self-hosting or hardware setups.

I wrote a short intro on the page about the pipeline that collects and analyzes the data, but feel free to ask for more details or check the Google Sheet for more info.

https://hnup.date/hn-sota

Show HN: State of the Art of Coding Models, According to Hacker News Commenters
hnup.date

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#2

Post by jdw64 » Sat, May 02, 2026, 9:36 PM UTC

Interpreting 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 more often than you'd expect), so this is a bit surprising. That said, the more defensive GPT is definitely better in terms of sheer code-writing capability. However, GPT actually has quite a few issues with text corruption when generating in Korean or Chinese—something English-speaking users probably don't notice. In terms of model capabilities, when given the same agent.md (CLAUDE.md) file, I think GPT is better at writing code, while Claude is better at writing text during code reviews.

Looking at the bottom right, Qwen and DeepSeek are open-source, so they are largely mentioned in the context of guarding against vendor lock-in, which drives positive sentiment. Considering that Hacker News occasionally shows negative sentiment toward China, the fact that they are viewed this positively—unlike US models—shows that being open-source is a massive advantage in itself.

Anyway, one thing for sure is that Gemini is pretty much unusable.

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#3

Post by Jabbles » Sat, May 02, 2026, 9:51 PM UTC

Please fix your graph so the names of the models are readable

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#4

Post by yakkomajuri » Sat, May 02, 2026, 9:52 PM UTC

"Prompts an LLM" -> which LLM?

I saw you're using Gemini for the sentiment rating (which I guess you picked because it's not often mentioned and thus "neutral"? lol)

But would be interesting to get more details overall

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#5

Post by yunusabd » Sat, May 02, 2026, 10:02 PM UTC

Jabbles wrote: post #3

Please fix your graph so the names of the models are readable

Sorry about that, the embedded graph from Sheets doesn't let me do that. I think I'll have to fetch the data and render the graph myself.

In the meantime, you can hover or tap the columns to see the full model names.

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#6

Post by marcuskaz » Sat, May 02, 2026, 10:10 PM UTC

Jabbles wrote: post #3

Please fix your graph so the names of the models are readable

Also, the stacked graph only allows you to quickly see total mentions, really hard to compare negative or positive sentiment across models at a glance.

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#7

Post by ranger_danger » Sat, May 02, 2026, 10:12 PM UTC

Just FYI this article seems to define "start of the art" as "popular", as measured by "total mentions and user sentiment", without any bearing on the technical abilities or actual usage of the model.

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#8

Post by mellosouls » Sat, May 02, 2026, 10:24 PM UTC

ranger_danger wrote: post #7

Just FYI this article seems to define "start of the art" as "popular", as measured by "total mentions and user sentiment", without any bearing on the technical abilities or actual usage of the model.

That's pretty much exactly what the title says.

The technical abilities and usage are derived from the commenters usage reflections.

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#9

Post by yunusabd » Sat, May 02, 2026, 10:49 PM UTC

yakkomajuri wrote: post #4

"Prompts an LLM" -> which LLM? I saw you're using Gemini for the sentiment rating (which I guess you picked because it's not often mentioned and thus "neutral"? lol) But would be interesting to get more details overall

It's actually ChatGPT at the moment for the first filtering step, for no other reason than having a code snippet ready that I could point Cursor at (I know, so 2025). The Gemini call is using batch processing, so it's handled differently.

Re: Show HN: State of the Art of Coding Models, According to Hacker News Commenters

#10

Post by yunusabd » Sat, May 02, 2026, 10:54 PM UTC

marcuskaz wrote: post #6

Jabbles wrote: post #3

Please fix your graph so the names of the models are readable

Also, the stacked graph only allows you to quickly see total mentions, really hard to compare negative or positive sentiment across models at a glance.

Yep, a toggle to scale all columns to the same height could solve this. I'll look into it when I do the custom graph.

Edit: Done