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

LiveSQLBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Predicting code correctnessLiveSQLBench SQLite
Brier Score0.129
55
Code correctness classificationLiveSQLBench SQLite
AUROC0.842
55
GenerationLiveSQLBench
Execution Accuracy50.7
4
Showing 3 of 3 rows