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

xBench-DS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Data Science Agent tasksxBench-DS
Pass@173
31
Deep SearchXBench-DS v1.0 (test)
Success Rate68
22
Information-seekingXbench-DS
Success Rate75
18
Data Science Task AutomationxBench-DS
Score78
18
Web Browsing ResearchXBench-DS (XBD)
Pass@389
6
Showing 5 of 5 rows