Re:Gemini: Google's most capable AI model yet
by KaoruAoiShiho on Wednesday December 06, 2023 @11:08AM
(#38545736)
Ehhh not really, it even loses to 3.5 on 2/8 tests. For me it feels pretty lackluster considering I'm using GPT-4 probably close to 100 times or more a day and it would be a huge downgrade.
[ Parent
| on HN ]
Re:Gemini: Google's most capable AI model yet
by glenstein on Wednesday December 06, 2023 @11:38AM
(#38546184)
Pro is approximately in the middle between GPT 3.5 and GPT 4 on four measures (MMLU, BIG-Bench-Hard, Natural2Cod, DROP), it is closer to 3.5 on two (MATH, Hellaswag), and closer to four on the remaining two (GSM8K, HumanEval). Two one way, two the other way, and four in the middle.
So it's a split almost right down the middle, if anything closer to 4, at least if you assume the benchmarks to be of equal significance.
Re:Gemini: Google's most capable AI model yet
by daveguy on Wednesday December 06, 2023 @12:15PM
(#38546711)
> at least if you assume the benchmarks to be of equal significance.
That is an excellent point. Performance of Pro will definitely depend on the use case given the variability between 3.5 to 4. It will be interesting to see user reviews on different tasks. 2Q lead time for Ultra means it may as well not be announced. A lot can happen in 3-6 months.