Agreed. I noticed a quick flyby of a bad “reasoning smell” in the baseball World Series simulation, though - it looks like it pulled some numbers from polymarket, reasoned a long time, and then came back with the polymarket number for the Dodgers but presented as its own. It was a really fast run through, so I may be wrong, but it reminds me that it’s useful to have skeptics on the safety teams of these frontier models.
That said, these are HUGE improvements. Providing we don’t have benchmark contamination, this should be a very popular daily driver.
On coding - 256k context is the only real bit of bad news. I would guess their v7 model will have longer context, especially if it’s better at video. Either way, I’m looking forward to trying it.
Either they overtook other LLMs by simply using more compute (which is reasonable to think as they have a lot of GPUs) or I'm willing to bet there is benchmark contamination. I don't think their engineering team came up with any better techniques than used in training other LLMs, and Elon has a history of making deceptive announcements.
They could still have trained the model in such a way as to focus on benchmarks, e.g. training on more examples of ARC style questions.
What I've noticed when testing previous versions of Grok, on paper they were better at benchmarks, but when I used it the responses were always worse than Sonnet and Gemini even though Grok had higher benchmark scores.
Occasionally I test Grok to see if it could become my daily driver but it's never produced better answers than Claude or Gemini for me, regardless of what their marketing shows.
They could still have trained the model in such a way as to focus on benchmarks, e.g. training on more examples of ARC style questions
That's kind of the idea behind ARC-AGI. Training on available ARC benchmarks does not generalize. Unless it does... in which case, mission accomplished.
Seems still possible to spend effort of building up an ARC-style dataset and that would game the test. The ARC questions I saw were not of some completely unknown topic, they were generally hard versions of existing problems in well-known domains. Not super familiar with this area in general though so would be curious if I'm wrong.
ARC-AGI isn't question- or knowledge-based, though, but "Infer the pattern and apply it to a new example you haven't seen before." The problems are meant to be easy for humans but hard for ML models, like a next-level CAPTCHA.
They have walked back the initial notion that success on the test requires, or demonstrates, the emergence of AGI. But the general idea remains, which is that no amount of pretraining on the publicly-available problems will help solve the specific problems in the (theoretically-undisclosed) test set unless the model is exhibiting genuine human-like intelligence.
Getting almost 16% on ARC-AGI-2 is pretty interesting. I wish somebody else had done it, though.
This is not hard to build datasets that have these types of problems in them, and I would expect LLMs to generalize this well. I don’t see how this is any different really than any other type of problem LLMs are good at given they have the dataset to study.
I get they keep the test updated with secret problems, but I don’t see how companies can’t game this just by investing in building their own datasets, even if it means paying teams of smart people to generate them.
The other question is if enough examples of this type of task are helpful and generalizable in some way. If so, why wouldn't you integrate that dataset into your training pipeline of an LLM.
I use Grok with repomix to review my code and it tends to give decent answers and is a bit better at giving actual actionable issues with code examples than, say Gemini 2.5 pro.
But the lack of a CLI tool like codex, claude code or gemini-cli is preventing it from being a daily driver. Launching a browser and having to manually upload repomixed content is just blech.
With gemini I can just go `gemini -p "@repomix-output.xml review this code..."`
As I said, either by benchmark contamination (it is semi-private and could have been obtained by persons from other companies which model have been benchmarked) or by having more compute.
I still dont understand why people point to this chart as any sort of meaning. Cost per task is a fairly arbitrary X axis and in no way representing any sort of time scale.. I would love to be told how they didn't underprice their model and give it an arbitrary amount of time to work.
That said, these are HUGE improvements. Providing we don’t have benchmark contamination, this should be a very popular daily driver.
On coding - 256k context is the only real bit of bad news. I would guess their v7 model will have longer context, especially if it’s better at video. Either way, I’m looking forward to trying it.