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

Yes! Going forward I'm definitely doing that, once there is enough data. Might even backfill the data more into the past. I just want to stabilize the methodology before burning more tokens.

And it's probably a good idea to create a list of model release dates, so older comments can't accidentally map to models that weren't released yet.

I have forgotten to add the tendency of not owing problems and taking care and solve immediately but instead deflecting and saying it shouldn't be done now it's not my responsibility etc Just terrible

It's extra interesting because I think the model people should be talking about is actually not DeepSeek V4 Pro, but the Flash version. When accounting for cache hits, the input price (per OpenRouter) is effectively only 6 cents per million tokens (3 vs 14 cents hit/miss), and 28 cents on output. That's really good efficiency, and it's not a sale price like they are doing with V4 Pro, it's the normal price.

It's actually pretty difficult to find a good comparison model because there isn't one. Again, a 14/28 cent in/out model, ignoring cache, it scores just below GPT 5.4 Mini-xhigh (75/450) and Gemini 3 Flash (50/300) in intelligence. It's similar to Gemma 4 31B in some metrics (13/38) including cost, so it's not completely unheard of, but it's pretty notable that virtually everything else in the same region in most benchmarks are going to cost at least 5 times more (much, much more in very output-heavy contexts)

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 and I spend more money there than elsewhere. On the other hand it responds quite differently from the other major models - so that claude and gpt on one hand are similar and gemini requires a different approach. In my opinion people who think gemini is worthless have not learned how to prompt it correctly. Again, it's intuitive and watching concrete response difference due to small input changes, but if I had to summarize it shows its google books / google scholar roots.

I have started experimenting with qwen more than deepseek, but I have not had good results yet. Given the good press I presume I will learn how to interact with it for better results.

Curious if others have similar experiences in comparing models usefully, or if most don't bother with this, or do something else? I mainly use models for highly focused specialty tasks, so this fine tuning makes the difference between usable and unusable. I don't yet have the luxury of defining my preferred workflow and finding the tool for the task. Everything just breaks almost immediately if I try to shoehorn into my preferred flow.

more users = more complaints. negativity just means popularity.

kimi...?