Re:GPT-5.2
by tikotus on Thursday December 11, 2025 @03:24PM
(#46236642)
Here's someone else testing models on a daily logic puzzle (Clues by Sam): https://www.nicksypteras.com/blog/cbs-benchmark.html
GPT 5 Pro was the winner already before in that test.
[ Parent
| on HN ]
Re:GPT-5.2
by thanhhaimai on Thursday December 11, 2025 @03:30PM
(#46236715)
This link doesn't have Gemini 3 performance on it. Do you have an updated link with the new models?
I've also tried Gemini 3 for Clues by Sam and it can do really well, have not seen it make a single mistake even for Hard and Tricky ones. Haven't run it on too many puzzles though.
Re:GPT-5.2
by crapple8430 on Thursday December 11, 2025 @03:39PM
(#46236827)
GPT 5 Pro is a good 10x more expensive so it's an apples to oranges comparison.