siegelz/core-bench download history

siegelz/core-bench is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 340 times (95 in the last 7 days), and 6,246 times in total. It ranks #44,527 among datasets by monthly downloads.

Dataset Card for CORE-Bench CORE-Bench is a benchmark evaluating the ability of agents to computationally reproduce scientific papers. It comprises 270 tasks from 90 papers across computer science, social science, and medicine, written in

Open siegelz/core-bench on Hugging Face