>> My sense is that the OIA/Anthropi/Google frontier models are pretty similar in their capabilities.
How did you gain this sense? Do you use all of them interchangeably on tasks that are similar in size and complexity?
I exclusively chat in a chat room with the latest frontier models at the same time. It's because first of all I can afford it, second I don't want to miss a single nice idea.
For the most part the majority say the same thing but with different wording.
Only model that I have found that has, what I describe, "humanly creative takes" has been opus 5.5 so far.
But that was until gemini carbon came along, and I've decided to bench all the other frontier models for the time being, well except Astra 6.2, I've just added it in the room.
In Cursor, I used to switch to Anthropic models (mainly Opus), when I ran into a problem that I could not solve with other models. This was my way of working for many months. Since Argon was released, I used Opus twice, and one was to run a comparison.
I used Claude for a couple reasonably complicated projects a while ago and I use OpenAI at work. They seems pretty much on par. I assume Google is similar, though I have less experience with it.
I think "they're all pretty much the same" is a good working hypothesis due to the intense level of competition between these three companies. When someone says "OAI suck; Claude is good" or the opposite (as you very often see in these threads), I think that's likely rationalization at work rather than a meaningful comparison.