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

Dial-Nav

Benchmarks

Task NameDataset NameSOTA ResultTrend
Human-agent cooperation navigationDial-Nav unseen (val)
Success Rate44
4
Human-agent cooperation navigationDial-Nav seen (val)
Success Rate73.1
4
Showing 2 of 2 rows