So Fable "won" but it cost $124.76 for marginal performance benefits over the $22.56 5.6 Sol run.
A really frustrating partial presentation, given an apparent lack of testing with a spread of efforts for each model.
Given that there's no reason to believe that Fable's xhigh is comparable to GPT-sol's xhigh, or Opus xhigh, for that matter, it would be far more useful to see the effort level where these tasks no longer achieved their goals.
These benchmarks are done with incorrectly and missing a lot of baselines. The article seems very vibe coded too.
It's kind of interesting this is already out of data as it's missing Kimi 3 and Opus 5.
Yeah, things are moving fast. Those benchmarks will be out soonish. Takes a while to run these things.
Seemed strange they would bench Terra and Luna but not Opus, Sonnet, and Haiku
They were all benchmarked, but not included in the post to try to keep the amount of data from being excessive. (Results are also not surprising — Opus good, Sonnet struggles, Haiku fails.)
Please forgive my naivety, but are world models (once they are in a consumer-ready form) expected to outperform any currently existing LLM on these sorts of tasks (i.e. of the physical world)?
From what I have seen "world models" are more like video models. The idea is: from a video clip, predict the next frame, like LLMs predict the next word/token from a bit of text.
The idea is that these models should be able to internalize the laws of physics and properties of objects just like LLMs do with grammar rules. To make training more efficient, frames from game engines with hardcoded physics are used. The application is mostly robotics, including autonomous vehicles.
This is a bit different, the idea is to write a physics engine, it means numbers: like for an airplane model, calculate the climb rate. The application is mostly science and engineering.
"world model" is, sadly, a new buzzword; most of the world models we are seeing are video generative models (like GPT-Image), they receive an action vector and previous frames and must generate the next frame. It's working of course.
The whole field of world models also have lighter approaches based on using latent representations as the target (and not pixel frames). LeWorldModel[0] and DINO-WM[1] are a good way to learn how these works.
Strangely, most of the startups in the space of world models are focused on video-generative world models.
A good application of world models is in robotics where an action policy generate a distribution of actions, you can then predict the future state of the world and use some reward policies to choose the "best" future state.
compare to opus-5 ?
Define "best" and "performs"
Google with apptronic should have good models soon
I'd expect google to do well here, since they were historically strong at multimodal and physics.
I wouldn't trust Gemini anywhere near my code.
However, it's pretty good at regurgitating textbook answers (classic Google...). This makes it an asset for circuit design. Try one of my real queries with Gemini Pro:
"Create a differential current splitter that splits a bias current Ib into a positive current Ipos = Ib/2 + ky*Vy and a negative current Ineg = Ib/2 - ky*Vy where Vy = Vy+ - Vy- is a differential voltage input Y."
Nice! It is missing Codex in the agent harnesses comparison IMO.
Yet another "benchmark to promote their own harness"
Honestly, I just hate the term "physical AI". They're robots. It's unfortunate that we had to adopt a term with the words AI in it, just to get investor's attention.