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

UROBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Time-controlled instruction-followingUROBench long (30s–1min)
MAE6.13
8
Time-controlled instruction-followingUROBench short (10s–30s)
MAE3.71
8
Showing 2 of 2 rows