Two stealth models just appeared on the leaderboard, both ahead of Fable 5.2

105 points by cheptsov 9 hours ago on hackernews | 33 comments

_s_a_m_ | 7 hours ago

some obscure design benchmark

skinfaxi | 6 hours ago

"Random AI lab makes up a new benchmark that puts at least one of its models ahead of Fable 5.2"

jrflo | 5 hours ago

Yeah this is 100% an ad

cronin101 | 6 hours ago

Saying this when none of the gallery examples show the new model's output is the ultimate "trust me, bro" move.

[OP] cheptsov | 6 hours ago

Perhaps soon we will know. I think on of the reasons for such stealth benchmarks is testing the model before uncovering details

freecodeio | 6 hours ago

the benefit of the doubt some of you give to everyone else but just swallow anything anthropic/oai has to say is insufferable

akutlay | 6 hours ago

It is interesting that the Kimi model gets a very high “slop score” but “professional critiques” gave it a pretty high score. Do critiques have no taste or the “slop” is not slop anymore?

JMKH42 | 6 hours ago

Producing a work that looks and feels great but with a mess under the covers is a thing.

danielrearden | 5 hours ago

If slop score is mostly “looks like AI”, Kimi scoring high there while human designers rate it well isn’t that weird. Generic can still nail the brief.

alex7o | 6 hours ago

Glm 5.5 I bet, but still too early to tell

tmikaeld | 2 hours ago

I’d also guess that, considering their be massive approach to sourcing training data, it would make sense that it’s much less sloppified than anything before it

barrenko | 6 hours ago

This Thanksgiving period will be a cambrian explosion of capable models.

irthomasthomas | 6 hours ago

Deepseek V5 trained on Huawei Ascend?

gorgmah | 6 hours ago

I don't understand, where are those models available in stealth mode? Usually people do this on openrouter but I couldn't find any model called "gestalt". Does anyone know or is this just black hat marketing for this contralabs platform, and the model does not even exist?
Openrouter will have these from time to time

petesergeant | 6 hours ago

This is a clever bit of content marketing

gajus | 6 hours ago

To clarify, it is not two models. Its a single model (Gestalt). The other bar on the benchmark is a human created dataset. Suffice to say we didn't expect anyone to beat it, but here we are. And no, it is not Contra model.

curiousgeorge10 | 5 hours ago

Very curious to find out which model that is :O

alfiedotwtf | 5 hours ago

My money is on GLM 6

mapontosevenths | 5 hours ago

The name is probably a clue. I wonder if someone just bolted Fable to Astra in a loop? I do that when I'm stuck, and get great results that exceed what either can do alone... Though it is wickedly expensive.

metalliqaz | 3 hours ago

How do you have them interacting in a loop? Plan-execute-repeat? Execute-review-repeat?

mapontosevenths | 3 hours ago

Usually I do it when one of them is stumped on their own, or seems to be thrashing. I guess it's more like... adjacent to the main loop.

I'll spin up both TUI's in herdr, tell them both to run "hc --skill" and then talk to each other until they figure out a solution. Also, for really complex tasks I will give one of them the title "Advisor" and just leave it running in the background while the main agent runs. The main agent gets instructions to ask the Advisor when stuck. So far it's basically always worked.

Before herdr I had them use tmux and files to talk to each other. That works too, but with a little more fumbling.

TheAtomic | 5 hours ago

That web site is insufferable.

RunSet | 5 hours ago

Thanks for confirming the site is insufferable.

I closed it before it could finish loading because it was so slow. Which does speak to its insufferable nature.

bwood | 3 hours ago

I normally wouldn't even bother commenting on an insufferable site (just close the tab and move on), but this was so bad that I came to the comments looking for validation of my feelings.

Like, above the fold is a bunch of moving links to AI-generated pages that have apparently nothing to do with the page title. Perhaps it's relevant, but I find it non-obvious. The first one I clicked gave a bad gateway.

Then we get the leaderboard, then just more AI-generated projects with opaquely dense descriptions like "Real client briefs, each with its golden: the design set beside the models’ outputs as the bar.".

Just reading this makes me feel like I'm having a stroke.

</rant>

ForHackernews | 5 hours ago

"on the leaderboard [that we created so we could lead it]"

vonneumannstan | 5 hours ago

Why would this not be GPT 6.2 Astra?

radzserg | 5 hours ago

who is --John Galt-- Gestalt?
interesting! any model performing better than human created outputs is very unexpected. i wonder how fast these models are gonna get better, thinking about the progress we made in a year on coding, design would be soon too

barbacoa | 3 hours ago

It is possible that anthropic/open ai may no longer release their best models due to their massive size and cost of running, instead releasing distilled version for public use.

cyanydeez | 2 hours ago

its more possible the IPO signals the death of any significant training runs and the rest of the operations will be goto:

1. price discrimination.

2. inference discrimination

3. national security extortion racket.

basch | 2 hours ago

Google/Gemini just went to a Flash/Standard/Pro model where Standard is $20 a month and Pro is $100 a month. I would surmise there's no way their top model can be given out for that price.

algoth1 | 3 hours ago

The name gestalt indicates it’s probably a router model like paretto by unbiased