News for hackers. Stuff that matters.

A comment on Gemini 3 Pro Model Card. Parent comment

Re:Gemini 3 Pro Model Card by HardCodedBias on Tuesday November 18, 2025 @11:02AM (#45968023)
What? The 4.5 and 5.1 columns aren't thinking in Google's report?

That's a scandal, IMO.

Given that Gemini-3 seems to do "fine" against the thinking versions why didn't they post those results? I get that PMs like to make a splash but that's shockingly dishonest.

[ Parent | on HN ]
Re:Gemini 3 Pro Model Card by mountainriver on Tuesday November 18, 2025 @12:50PM (#45969632)
Every single time
[ Parent | on HN ]
Re:Gemini 3 Pro Model Card by iosjunkie on Tuesday November 18, 2025 @01:43PM (#45970264)
It that true?

> For Claude Sonnet 4.5, and GPT-5.1 we default to reporting high reasoning results, but when reported results are not available we use best available reasoning results.

https://storage.googleapis.com/deepmind-media/gemini/gemini_...

[ Parent | on HN ]