Comment by gertlabs
1 hour ago
We've been really impressed with the performance of ~30B parameter class models and how close they are to the frontier from ~6-12 months ago, which begs the question, are the frontier labs really serving 10T parameter models? Seems unlikely.
If these Gemini 3.5 numbers are accurate, then I'd wager GPT 5.5 and Opus 4.7 are a lot smaller than people have speculated, too. It's not that frontier labs can't create a 5T+ parameter model, but they don't have the data to optimize a model of that size.
Gemini 3.5 Flash is really smart in one-shot coding reasoning, btw. Near the frontier. But it doesn't do so well in long horizon agentic tasks with arbitrary tool availability. This is a common theme with Google models, and the opposite of what we see with Chinese models (start dumb, iterate consistently toward a smart solution).
Data at https://gertlabs.com/rankings
I exclusively use gemini models and this has been my experience.
I mitigate it by creating dense planning docs for everything and executing iteratively.
Lot's of time wasted on procedure unfortunately
We know from NVIDIA's public Vera Rubin inference engine marketing materials that the frontier lab models are ~1-2T total.
Mythos is an exception that's larger.