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

SeeTRUE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual faithfulness evaluationSeeTRUE
F1 Score82
15
Image-Text AlignmentSeeTRUE
Winoground63.5
14
Binary ClassificationSeetrue (test)
Macro F1 Score83.67
5
Showing 3 of 3 rows