Why such an old benchmark?

I always do!

Everytime I've opened Hackernews front page there is always "x breached" this week.

Gemini models are so, so much better in this regard. Their outputs are actually readable.

Gemini tends to glaze you though. I now believe I’m a genius at pretty much everything after trying it a little.

Every model has done this. And sometimes the makers go the other way to compensate, and then you get Opus 5 who answered like it was possessed by the ghost of stack overflow.

Not really, Gemini is at a different level, it will naturally burst out compliments and honorable nickname to provide emptional values. My last company was iterally destroyed because the old boss (successful boomer who had no idea how software industry work) believe everything his Gemini told him and gives us all kinds of unrealistic assignments and force us to use whatever tools/services Gemini suggested.

Agreed. In my experience it gets to the heart of information faster rather than so much filler. Also better information and more comprehensive in general.

The main issues seem to be glazing that sibling mentions and also it seems to play a bit loser with facts and reality and makes up more stuff.

I have a touchscreen Yoga laptop and only use it for studying. I don't see myself using the touch screen at all after my time in University is done.

Meta is a privacy nightmare but at least with them it's E2E encrypted. With an MCP running on cloudflare I'm guessing it's processed plainly.