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

Household

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringHousehold (full)
Accuracy80.2
25
Proactive AssistanceHousehold domain
Speedup19.1
10
ClusteringHousehold dataset
Macro-Recall85
3
Showing 3 of 3 rows