DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
Open paper
Benchmark
Model
Rank
Results
text-to-sql-on-bird
DIN-SQL + GPT-4
#5
Execution Accuracy % (Test): 55.90
Execution Accuracy % (Dev): 50.72
text-to-sql-on-spider
DIN-SQL + GPT-4
#4
Execution Accuracy (Test): 85.3
Exact Match Accuracy (Test): 60
Rank counts only results with a code link.