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

SQL Semantic Validation on Spider

63.21AUPRC

Prompt

31.937240.056148.17556.2939Dec 28, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
63.2175.81
2025.12
53.5269.78
2025.12
51.9267.32
2025.12
51.9267.32
2025.12
51.1169.26
2025.12
50.3967.82
2025.12
50.0367.29
2025.12
49.7366.19
2025.12
49.2861.15
2025.12
48.9159.97
2025.12
48.7265.8
2025.12
47.6866.37
2025.12
46.8162.73
2025.12
43.962.84
2025.12
40.8658.94
2025.12
40.8658.94
2025.12
39.5850.98
2025.12
38.0954.78
2025.12
35.7750.18
2025.12
34.2849.96
2025.12
34.2649.75
2025.12
34.2549.78
2025.12
34.1350.65
2025.12
33.1446.63