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

BabyVision

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vision ReasoningBabyVision
FD Score94.1
15
Multimodal ReasoningBabyVision (test)
Accuracy49.7
13
Multimodal PerceptionBabyVision
Accuracy34.51
13
Visual ReasoningBabyVision
Accuracy31.7
12
Visual PerceptionBabyVision
Accuracy44.6
5
Multimodal Vision EvaluationBabyVision
Accuracy43.23
2
Showing 6 of 6 rows