Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Program-aided math reasoning on TabMWP

75.3Accuracy

DeepSeek-Coder-Base

28.18840.41952.6564.881Jan 25, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.01
75.3
2024.01
69.8
2024.01
67.9
2024.01
60.3
2024.01
52.9
2024.01
45
2024.01
44.6
2024.01
30