[impulser_]

Don't let the benchmarks fool you. Gemini models are completely useless not matter how smart they are. Google still hasn't figure out tool calling and making the model follow instructions. They seem to only care about benchmarking and being the most intelligent model on paper. This has been a problem of Gemini since 1.0 and they still haven't fixed it.

Also the worst model in terms of hallucinations.

[estearum]

Disagree.

Claude Code is great for coding, Gemini is better than everything else for everything else.

[johnfn]

What is "everything else" in your view? Just curious -- I really only seriously use models for coding, so I am curious what I am missing.

[impulser_]

Are you using Gemini model itself or using the Gemini App? They are different.

[amelius]

And mathematics?