Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Text-to-SQL on Spider (test dev)
Loading...
0.7168
Execution Accuracy
GPT-4
0.677384
0.687617
0.69785
0.708083
Feb 18, 2024
Execution Accuracy
Validation Execution Score
Updated 4d ago
Evaluation Results
Method
Method
Links
Execution Accuracy
Validation Execution Score
GPT-4
knowledge=w/ DELLM
2024.02
0.7168
0.7282
GPT-4
knowledge=w/o knowledge
2024.02
0.7002
0.7103
GPT-3.5-Turbo
knowledge=w/ DELLM
2024.02
0.696
0.7016
GPT-3.5-Turbo
knowledge=w/o knowledge
2024.02
0.6789
0.6833
Feedback
Search any
task
Search any
task