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

PuzzleVQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual Puzzle ReasoningPuzzleVQA
Accuracy46.8
12
Multimodal ReasoningPuzzleVQA
Accuracy81.95
8
Visual Question AnsweringPuzzleVQA
Accuracy61
4
Showing 3 of 3 rows