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

DiscoveryBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Collaborative Scientific DiscoveryDiscoveryBench archaeology tasks
Wtotal7.9
7
Open-ended scientific discoveryDiscoveryBench open-ended discovery (evaluation set)
ES4.91
5
Showing 2 of 2 rows