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

BLADE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Automated Data ScienceBLADE reading
BLADE Average Score9.3
8
Open-ended scientific discoveryBLADE open-ended discovery (evaluation set)
Expert Score4.8
5
Showing 2 of 2 rows