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

Text-to-SQL on Text-to-SQL Multi-sharded

60.7Functional Accuracy

RPOTD+replay

16.81228.20639.650.994Oct 7, 2025
Updated 9d ago

Evaluation Results

MethodLinks
2025.10
60.747.754.2
2025.10
56.140.828.9
2025.10
55.138.820.4
2025.10
52.847.754.2
2025.10
52.336.816.9
2025.10
52.337.617.5
2025.10
51.433.3-
2025.10
46.747.754.2
2025.10
45.938.820.4
2025.10
45.837.617.5
2025.10
43.940.828.9
2025.10
40.233.3-
2025.10
40.247.754.2
2025.10
39.727.215.7
2025.10
38.340.828.9
2025.10
38.347.754.2
2025.10
37.436.816.9
2025.10
34.638.820.4
2025.10
33.636.816.9
2025.10
33.640.828.9
2025.10
33.238.820.4
2025.10
31.833.3-
2025.10
31.827.215.7
2025.10
31.836.816.9
2025.10
31.840.828.9
2025.10
30.837.617.5
2025.10
29.937.617.5
2025.10
2936.816.9
2025.10
2937.617.5
2025.10
2538.820.4
2025.10
24.127.215.7
2025.10
22.433.3-
2025.10
2227.215.7
2025.10
20.633.3-
2025.10
18.527.215.7