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

Amazon Mechanical Turk

Benchmarks

Task NameDataset NameSOTA ResultTrend
Image AlignmentAmazon Mechanical Turk (AMT)
Human Preference Score63.27
5
Text AlignmentAmazon Mechanical Turk (AMT)
Human Preference81.85
5
Showing 2 of 2 rows