To diagnose the failures of current models and support research, we're releasing GSM8K, a dataset of 8.5K high quality linguistically diverse grade school math word problems. We find that even the ...

The task of solving Math Word Problems (MWPs) has received significant research attention in the past years. An MWP consists of a short Natural Language narrative that describes a state of the world ...

Emily Sharp and Kunal Nabar collaborate on a puzzle that’s greater than the sum of its parts.

The mathematics competition called the "Pražská střela" , organized by the Christian Doppler College Preparatory School, is ...

R1, an open-source reasoning AI model comparable to OpenAI’s o1 in performance at a fraction of the latter’s cost.