Of all models I like to write with Gemini the most. The language appears much more natural and elegant than what even Opus 5.5 or Astra do. Also, they give 5TB of cloud storage and discounts, it’s a steal for what you get.

The code is bad though.

Claude has particularly bad prose. Somewhat improved in 5.5, but it has historically clearly been the most annoying prose among major models because is had so many obvious tics that made it clear it was Claude rambling. Still extremely verbose.

They all ramble, they're all allergic to getting to the point. But, Gemini historically has pretty good prose. Even the self-hosted Gemma models have pretty nice, inoffensive prose. I wouldn't want to read a novel written by any of them, but I tend to ask Gemini questions in chat more often than Claude or GPT, because it has good prose and is good at using the web to research.

Gemini models lie too much. Prentending something wrong to be right. You gotta treat Gemini models with disrepect, and even threaten to make it work.

Or else it say, here is the result. (but no it didn't do no research, and tells me, sorry I forgot to search).

It's got balls to lie straight at my face.

Yeah rumor ahead of release was also that some Googlers were anxious about the known subpar coding given modern trends.

Agreed. It's much better at working with stuff (like documents and presentations) in other languages too. It feels like it's trained in multiple languages from the ground up rather than as an afterthought.

Same, gemini for writing is the strongest. Qwen was also surprisingly good last time I did a shootout

Interesting tidbit but TFA and discussion are about Gemini 4

Argon code is bad? Did you already come to that conclusion?

Agreed from my experience 3.8 Flash writes better prose than Opus 5.5