Share your thoughts, 1 month free Claude Pro on usSee more

Physical Reasoning on PROST

29.6Accuracy

GPT-NeoX

Updated 1mo ago

Evaluation Results

Method	Links
GPT-NeoX 2022.04		29.6
GPT-3 2022.04		28.8
FairSeq 2022.04		27.2
GPT-3 2022.04		27
GPT-J 2022.04		26.7
GPT-3 2022.04		26.7
FairSeq 2022.04		25.7
FairSeq 2022.04		25.7
GPT-3 2022.04		25.4
FairSeq 2022.04		25.2
FairSeq 2022.04		23
FairSeq 2022.04		21.5