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

Human Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
In-the-wild model generalizationHuman Bench Average
NSE Score57.9
14
In-the-wild model generalizationHuman Bench Text-based Demo
NSE23.4
14
In-the-wild model generalizationHuman Bench Vision-based Demo
NSE15.5
14
Showing 3 of 3 rows