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

Multiple Choice Question Answering on OBQA (dev)

86.1Accuracy

CPACE

53.23661.76870.378.832Apr 30, 2022Jul 2, 2022Sep 3, 2022Nov 5, 2022Jan 7, 2023Mar 11, 2023May 14, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.05
86.1
2023.05
83.2
2023.05
81.7
2023.05
72.5
2022.04
71.6
2023.05
71.6
2022.04
70.53
2023.05
70.5
2022.04
70.4
2022.04
67.8
2023.05
64.1
2022.04
62.07
2022.04
60.8
2022.04
59.2
2022.04
58.67
2022.04
54.53
2022.04
54.5