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

Math Reasoning on GSM-H (held-out)

57.54Accuracy (%)

ENVISIONS

8.81621.465534.11546.7645Jun 17, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.06
57.5463.56
2024.06
53.9856.49
2024.06
53.3760.6
2024.06
52.0857.17
2024.06
50.5759.77
2024.06
48.5258.69
2024.06
47.8452.46
2024.06
47.0854.73
2024.06
46.6355.91
2024.06
44.8853.03
2024.06
41.2452.5
2024.06
31.6944.22
2024.06
28.9638.61
2024.06
10.6925.69