←back to thread

GPT-5.2

(openai.com)
1019 points atgctg | 3 comments | 11 Dec 25 18:04 UTC | HN request time: 0.587s | source
Show context
Tiberium ◴[11 Dec 25 18:35 UTC] No.46235157[source]▶
The only table where they showed comparisons against Opus 4.5 and Gemini 3:

https://x.com/OpenAI/status/1999182104362668275

https://i.imgur.com/e0iB8KC.png

replies(1): >>46235285 #
varenc ◴[11 Dec 25 18:45 UTC] No.46235285[source]▶
100% on the AIME (assuming its not in the training data) is pretty impressive. I got like 4/15 when I was in HS...
replies(1): >>46236186 #
1. hellojimbo ◴[11 Dec 25 19:44 UTC] No.46236186[source]▶
The no tools part is impressive, with tools every model gets 100%
replies(1): >>46238952 #
2. varenc ◴[11 Dec 25 23:41 UTC] No.46238952[source]▶
If I recall, the AIME answers are always 4 digits numbers. And most of the problems are of the type where if you have a candidate number it's reasonable to validate its correctness. So easy to brute force all 4 digit ints with code.

tl;dr; humans would do much better too if they could use programming tools :)

replies(1): >>46240606 #
3. Davidzheng ◴[12 Dec 25 03:36 UTC] No.46240606[source]▶
uh no it's not solved by looping over 4 digit numbers when it uses tools