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

CulturalVQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Question AnsweringCulturalVQA (test)
ECE33.7
19
Human EvaluationCulturalVQA OOD (test)
Faithfulness7.66
6
Visual Question AnsweringCulturalVQA
ECE0.354
6
Showing 3 of 3 rows