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

GOAT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Animal Activity Recognitiongoat dataset
Accuracy93.17
7
Visual NavigationGOAT-Core (val)
SR75
6
VQAGoAT (test)
Volume63
6
Goal LocalizationGOAT-Core
Average Goal Localization70.8
2
Multimodal Safety EvaluationGOAT (test)
Misogyny Accuracy56.9
2
Showing 5 of 5 rows