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

SQL Semantic Validation on BIRD

80.36AUPRC

Prompt

53.080860.162967.24574.3271Dec 28, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
80.3679.25
2025.12
75.8776.15
2025.12
73.5673.45
2025.12
71.1864.17
2025.12
67.3961.51
2025.12
67.3961.51
2025.12
67.163.48
2025.12
66.7161.38
2025.12
64.760.44
2025.12
64.3960.56
2025.12
64.2955.49
2025.12
62.759.25
2025.12
62.6659.23
2025.12
61.0155.31
2025.12
60.8557.25
2025.12
60.8557.25
2025.12
60.3657.65
2025.12
57.6754.4
2025.12
56.5951.43
2025.12
56.2852.37
2025.12
55.0250.46
2025.12
54.7950.53
2025.12
54.7249.84
2025.12
54.1348.47