SFT CodeS-15B + SQLFixAgent

Reported on 2 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Semantic ParsingonBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
Execution Accuracy % (Dev)
64.62
best: 74.32 (DSAIR + GPT-4o)
Text-To-SQLonBIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQL Evaluation)
Execution Accuracy % (Dev)
64.62
best: 74.32 (DSAIR + GPT-4o)