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

DataBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Tabular Data AnalysisDataBench
Accuracy35.6
20
STRINGDataBench
LLM Judge Accuracy77.9
9
Agentic Task SolvingDataBench
Pass@392.7
9
String ExtractionDataBench
Exact Match77.9
9
Showing 4 of 4 rows