Kimi K3.1 Pro and K3.1 Pro Highspeed

shaohua

"We Must Pace the Frontier"?

SomeonesAccount

No AA scores yet.

Jowsey

Tech blog and benchmark scores now available here: https://www.kimi.ai/blog/kimi-k3-1-pro It appears to be generally frontier-level.

rafaelero

That's nuts.

rudolftheone

Hallu Bench Hard: K3 at 23.4%, K3.1 at 8.3% which is very nice improvement!

volf_

That's quite an impressive jump

brianritz

Maybe this was why the “AI trade” was weak this week.

throwa356262

Ah, the version available to us mortals is nerfed in cybersecurity just like the US models :(

Aboutplants

If those are true then wow

TuxSH

> For the open-weight release of K3.1 Pro, we identified and removed cyber-related data from both training stages, while retaining the general-purpose coding tasks needed for model usefulness. We will continue to apply appropriate controls at every training stage, of which cyber-related data identification and restriction is one example. Lame.

moecables

Great! next week we'll get Astra 6.1 and Fable 5.2

wolttam

It's a bit fascinating to me how all of these labs have rolled their own (it sounds like) completely unique RL environments. I wonder how much the industry will centralize around a few key patterns, and if we'll start to see some RL framework projects gain traction and be used by the bigger labs P.S. weights by November 4th

rudolftheone

That's something which caught my attention: > First, we aim not to release open weights that would extend the absolute frontier of cyber capability. K3.1 Pro's offensive cyber capability is, by design, below what our pipeline can produce, and remains behind that of frontier proprietary models. Second, we intend to progressively raise the cyber capability available in open weights. So they admit that they could do more, but they won't?

Super3000

I'll wait for the pelican benchmark.

cesarvarela

I wish Opus 5.5 had an alternative just for the sake of not having a monopoly, but I have yet to see a model live up to its benchmark scores except for Fable and Opus; there is something about Anthropic that no other lab has.

rvz

This is a frontier level model and is at worst 1 month behind Anthropic and OpenAI.

throwa356262

Looking at their pricing page for China, K3.1 seems to be about 30% cheaper than K3. -- Model K3.1 Pro K3.1 Pro Highspeed. K3 Input ¥13.00 ¥26.00 ¥20.00 Output ¥68.00 ¥136.00 ¥100.00 Cache hit ¥1.30 ¥1.30 ¥2.00 Cache write ¥13.00 ¥26.00 ¥20.00

mixtureoftakes

looks extremely impressive, the full benchmark table isn't opening for some reason though so do we really have agi if small important things like that keep breaking?

wkcheng

It would be super useful to have more specific analyses of what areas the model is good at. I'd like to know when I should reach for this model instead of Anthropic's or OpenAI's. For example, Opus 5.5 is better at UI design than Sol. Anyone who has used both models knows that, but it's not something you can look up anywhere. I'm sure that there's a need for this kind of benchmarking, not just for coding.

cosmojg

The announcement page is very extra: https://www.kimi.ai/blog/kimi-k3-1-pro