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

Bird-Critic

Benchmarks

Task NameDataset NameSOTA ResultTrend
DebuggingBIRD-Critic
Execution Accuracy64.2
4
Text-to-SQLBird-Critic PostgreSQL
Pass@146.16
4
Showing 2 of 2 rows