RE: LeoThread 2024-11-13 03:36
You are viewing a single comment's thread:
New secret math benchmark stumps AI models and PhDs alike
FrontierMath is a new mathematics benchmark that contains hundreds of expert-level problems which leading AI models are able to solve less than 2% of the time.
#technology #artificialintelligence #ai #mathematics #frontiermath
0
0
0.000
0 comments