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

SampleQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Factuality Question AnsweringSampleQA
Accuracy (%)3.21
32
Factual ReasoningSampleQA
Accuracy3.21
8
Scientific Reasoning & QASampleQA
Accuracy3.31
7
Showing 3 of 3 rows