CritPt-Benchmark/CritPt download history
CritPt-Benchmark/CritPt is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 2,520 times (300 in the last 7 days), and 22,953 times in total. It ranks #9,507 among datasets by monthly downloads.
Probing the Critical Point (CritPt) of AI Reasoning: a Frontier Physics Research Benchmark |๐ Website | GitHub | ๐ Paper | Dataset description CritPt (Complex Research using Integrated Thinking โ Physics Test; reads as "critical point") is the first benchmark designed t