Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

thinkpol.ca

Post reply on HN
Print view View original

181–190 of 235 posts

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#181

Post by zozbot234 »

adrian_b wrote: post #166
walrus01 wrote: post #49

People thinking to self-host Kimi K2.6 had better be prepared for how big it is. Q8 K XL quantization for instance is around 600GB on disk. I would bet about 700GB of VRAM needed. Quantizations lower than Q8 are probably worthless for quality. Or 2.05TB on disk for the full precision GGUF. https://huggingface.co/unsloth/Kimi-K2.6-GGUF If you can afford the hardware to run Kimi K2.6 at any decent speed for more than 1…

While most people would not be able to run Kimi K2.6 fast enough for a chat, as a coding assistant the low speed matters much less, especially when many tasks can be batched to progress during a single pass over the weights. If you run it on your own hardware, you can run it 24/7 without worrying about token price or reaching the subscription limits and it is likely that you can do more work, even on much slower hard…

DeepSeek V4 Pro is way more effective at batching multiple tasks together since the KV cache is so much lighter - a max of ~10GB at full 1M context, and in a linear proportion with context according to the DeepSeek V4 release paper. That's extremely impressive, it unlocks batching, agent swarms etc. even on severely memory-constrained platforms, especially at smaller max context.

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#182

Post by arvid-lind »

PunchyHamster wrote: post #156
chvid wrote: post #129

Earlier quoted context omitted.

Or maybe it is a pretty good thing for the American economy that you can get AI at cost rather than monopoly pricing. You know, for the rest of the economy that is not big tech.

It's not good for current administration. The American AI growth is only thing that keeps the GDP not looking terrible. And investor pumping money in US AI circular money flow just makes innovation everywhere else slower. If not for the GPU/Memory drought running stuff locally (or just in competition cloud) would be far cheaper

> It's not good for current administration

I don't know where to begin if you're leading with that. Anything approaching reality is not good for the current administration.

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#183

Post by zozbot234 »

nelox wrote: post #179
pjerem wrote: post #102

Earlier quoted context omitted.

The news is not in the way to compare models, it’s that Kimi K2.6 (and I’d add Deepseek v4 Pro) are more or less equivalent to Opus and that’s already pretty big. They are open source and cost waaaay less per token than American models. I’m using them right now on the $20 Ollama cloud plan and I can actually work with them on my side projects without reaching the limits too much. With Claude Pro $20 plan my usage can…

That is the very reason the open source models exist. Prestige and soft power to influence interest away from American models and hopefully slow down their progress.

DeepSeek and other Chinese model makers are massively accelerating progress in AI not slowing it down. They're the only ones who still come up with real technical innovations while the proprietary model makers are stagnating.

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#185

Post by Sammi »

zozbot234 wrote: post #183
nelox wrote: post #179

Earlier quoted context omitted.

That is the very reason the open source models exist. Prestige and soft power to influence interest away from American models and hopefully slow down their progress.

DeepSeek and other Chinese model makers are massively accelerating progress in AI not slowing it down. They're the only ones who still come up with real technical innovations while the proprietary model makers are stagnating.

I'm as happy to see cheap open weight models any anyone is, and I'm in Europe and certainly not cheering the US on, but that's a bunch of unfounded hyperbole you just said.

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#186

Post by darkoob12 »

zozbot234 wrote: post #183
nelox wrote: post #179

Earlier quoted context omitted.

That is the very reason the open source models exist. Prestige and soft power to influence interest away from American models and hopefully slow down their progress.

DeepSeek and other Chinese model makers are massively accelerating progress in AI not slowing it down. They're the only ones who still come up with real technical innovations while the proprietary model makers are stagnating.

Can you name some tangible AI idea that came out of Chinese labs?

I can name thousands that came out western universities.

I see a lot of rhetoric that only the Chinese labs are contributing to AI while companies like Google and Microsoft are still pulishing their research.

Unfortunately the domain of scientific papers is cluttered with AI slop but still occasional serious paper that i find are from western labs particularly Google Research or Microsoft Research

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#188

Post by Sammi »

mpeg wrote: post #103
slashdave wrote: post #16

I was surprised by the ranking, until I read what the test was. Not horribly relevant for coding. The current ranking of all tests makes more sense (well, except for how well Gemini does) https://aicc.rayonnant.ai

If you look at the ranking breakdown though, Kimi K2.6 has only participated in the last 5 challenges (claude dominated before then) and if you only count those it would be in first place

It also has a DNF. So it has a high ceiling but also unfortunately a low floor. So using Kimi means accepting high variability of the output.

Personally what I've found that has made coding agents more and more useful over the last year is that they have gotten a higher and higher floor, not that they have gotten a higher and higher ceiling. They were already plenty smart a year ago, it was just that they failed so often and so spectacularly that it made them a liability. Now they have become much more reliable, which is the key thing that has transitioned them into being actually useful. For the most part I don't use them to work on really intellectually difficult tasks. I mostly use them to work on very boring and labor intensive tasks. Most commercial software development work is just boring drudgery like this. Certainly the bulk of what I need them for is. I need them to just not crap their pants all the time while they're at it.

So I'm kinda wary seeing the poor reliability of Kimi.

Re: Kimi K2.6 just beat Claude, GPT-5.5, and Gemini in a coding challenge

#189

Post by satvikpendem »

darkoob12 wrote: post #186
zozbot234 wrote: post #183

Earlier quoted context omitted.

DeepSeek and other Chinese model makers are massively accelerating progress in AI not slowing it down. They're the only ones who still come up with real technical innovations while the proprietary model makers are stagnating.

Can you name some tangible AI idea that came out of Chinese labs? I can name thousands that came out western universities. I see a lot of rhetoric that only the Chinese labs are contributing to AI while companies like Google and Microsoft are still pulishing their research. Unfortunately the domain of scientific papers is cluttered with AI slop but still occasional serious paper that i find are from western labs part…

Any of DeepSeek's recent papers which are more about efficiency and that's how their inference costs can be so low.
Post reply on HN