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

In-Domain Evaluation

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question Answering CalibrationIn-Domain Evaluation NQ, TQ, HQ, 2Wiki, Pararel
Calibration Error (NQ)0.05
11
Showing 1 of 1 rows