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

EgoDex and DreamDojo-HV

Benchmarks

Task NameDataset NameSOTA ResultTrend
Human Preference EvaluationEgoDex and DreamDojo-HV novel out-of-distribution (eval)
Physics Correctness73.5
3
Showing 1 of 1 rows