Hacker News Reader

Uhh... It's on the 13-th place in rankings. And way behind in most benchmarks?

#6 in usage by tokens. It obviously has some use case. My experience is that Gemini is much more token efficient than other models. Measuring tokens is like measuring distance travelled by measuring fuel consumption.

I mostly use Codex though, I can't be bothered to have more than one subscription.

Agreed Gemini maybe not the best, but it is still pretty good. And their research was the foundation of others (Attention is all you need paper).

Gemini tends to be faster and the Flash and Flash Lite models outperform ChatGPT's equivalent models.