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

Bongard-OpenWorld

Benchmarks

Task NameDataset NameSOTA ResultTrend
Visual ReasoningBongard-OpenWorld 500-sample
Overall Score93.6
12
Concept AnsweringBongard-OpenWorld
AAUC73.1
7
Showing 2 of 2 rows