[00:02]
named Kibitz showed up randomly on Chapot Arena performing at the frontier level. Kibitz is the Yiddish word for that guy standing behind you at a chess blunder your queen, which to be honest is the perfect analogy for a coding
[00:14]
behind this mystery model from the of this word are a dead giveaway. Everybody knew it was Kimmy. Then right on Q last Friday, Moonshot dropped Kimmy K3.1, officially giving us a new three
[00:28]
trillion parameter openweight model that will be fully downloadable on November 4th. Or so they say. And just when you thought the AI bubble was popping and possibly get any better, Kimmy made them better.
[00:40]
>> In today's video, we'll find out why Kimmy K3.1's performance should be impossible and put it to the test on the only benchmark that matters, the building 3D horses with 3JS. It is October 26, 2026, and you're watching
[00:53]
the Code Report. Earlier this year, Anthropic accused Moonshot AI, the company behind Kimmy, alongside a bunch of other Chinese companies like Deep Seek and Miniax of running large-scale distillation attacks against Claude by
[01:05]
sending swarms of fake users to steal Claude's output and reasoning tokens, open models that they give to us for free. And now, I believe distillation is companies have literally distilled a collective human brain. but by taking
[01:19]
our internet web blogs, our GitHubs, our scientific papers, and they even destructively scanned our books without asking. Just Google Project Panama. But OpenAI and Anthropic don't really see distillation as a human right like I do.
[01:31]
And they've invested millions and millions of dollars into stopping it. it pretty much solved the distillation problem with 90 to 99% of distillation attacks from China now being blocked.
[01:44]
And over at OpenAI, they've proved that their tech can even stop small-scale distilleries like PewDiePie. But if that's true, that means an open Chinese model with Kimmy's performance should not be possible. Because for years, Big
[01:56]
AI has insinuated that the reason Chinese models get so good so fast is that they steal Big AI's outputs. But if we can trust this Trust Me Bro would mean that these Trust Me Bro benchmarks from Kimmy should not be
[02:09]
possible. like Kimmy K 3.1 is within one point of opus 5.5 on terminal bench 4.0. That's pretty crazy. And no other open model is remotely close. And we might even be able to actually trust these numbers because artificial analysis ran
[02:23]
it independently and got 67% which is the highest score of any model they tested. But one thing to keep in mind is that the harness plays a big role here. harnesses will produce huge differences in benchmark results. In addition, Kimmy
[02:37]
also wins on S. marathon, which is a test for multi-our software requirements, or in other words, jobs that would take humans weeks of work to pretty impressive, but there is one big caveat when it comes to coding and
[02:50]
specifically cyber security. Moonshot deliberately ripped out a bunch of cyber security data from its training data set, where the goal was to make the software. >> I'm a genius, dude. And it worked
[03:02]
because internally at Moonshot, an unfiltered checkpoint solved 90.5% of their illegal exploit tests. But the final release model only solves 81%. And part because just a few days ago, the US banned China's Deepseek model from
[03:17]
government use, including all federal civilian agencies. And they would just love a good reason to ban all Chinese models across the board to hand Open AAI and Anthropic a huge win and make all the insiders even more unbelievably rich
[03:29]
Moonshot really has no choice but to lobomtomize its hacking capabilities. But despite that, Kimmy still performed on top of all publicly available models on the new cyber index at artificial analysis. Although that's mostly because
[03:42]
Claude and GBT6 declined every prompt on safety grounds and just took the L. But nowadays, the only AI capability that I really care about is how well it can generate a 3D horse with 3JS. And to analyze the skill objectively and
[03:54]
scientifically, I use a formal benchmark. It's a state-of-the-art eval I've developed after thousands of hours of research, which I call thoroughbench. into the chat window and type create a realistic interactive 3D horse with 3JS
[04:08]
and then press enter. From there, I rank them from 0 to 10 based on a proprietary loss function I keep in my brain. Using this technique, Google Argon achieved a this technique, Google Argon achieved a 0.69. GPT6 Astra achieved a 5.21 and
[04:22]
Opus achieved a 6.39. But now it's time to try Kimmy K3.1. I tried to be cheap and use the free tier, but got denied. So now I'm paying 250 yuan per month to show you guys this demo. It was worth it though because Kimmy produced what is
[04:35]
sample. Its coloring is spot-on. It looks realistic. And most importantly, its copulatory organ is a reasonable size. I was blown away by its beauty at first glance, but then I pushed play on the animation and found a problem. The
[04:49]
we look closely, you can see it achieves the animation by simply warping the original mesh, which is a very unsophisticated and half-assed way to animate a 3D object. If we compare that to Claude, the horse itself may not look
[05:02]
as beautiful, but it actually built a mesh with 95,000 vertices with each shape tied to one of 35 bones, and all those bones are animated independently. Even Gemini Argon used bones, but for some reason, it added an extra one. The
[05:15]
skeletal animation is more difficult, but it's why the horse doesn't look like when it walks. So, the final score for Kimmy K 3.1 on Thoroughbench is a 4.20, still behind the other Frontier models. But if you really want to build an
[05:31]
amazing 3D horse or user interface, you need to check out Mobin, the sponsor of today's video. I've been using Mobin for over 5 years and its MCP server now lets your coding agent study its library of 600,000 real UI screens before it
[05:45]
designs anything. So instead of asking for a login page and getting the same purple gradient vibe slop, you start by telling Claude Code, Cursor, or Codeex to study how the best apps built that complete user flow. It'll use Mobin to
[05:57]
gather references and build a visual report of the patterns they all share. Then it'll recreate that flow and adapt it to your app. Every result points back check the source and after you connect Mobin, everything your agent designs
[06:11]
will feel like it has actual taste. But try Mobin for free today and get a 20% been the code report. Thanks for watching and I will see you in the next watching and I will see you in the next one.