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

Mathematical Reasoning on MATH 500 (Accuracy@4 and Speedup)

78.2Accuracy (mean@4)

DUET

35.45646.55357.6568.747May 8, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.05
78.21.43
2026.05
76.72.38
2026.05
74.51
2026.05
74.40.75
2026.05
73.91.19
2026.05
73.20.63
2026.05
62.12.51
2026.05
61.61.62
2026.05
58.60.95
2026.05
58.41.3
2026.05
57.60.81
2026.05
56.81
2026.05
54.3-
2026.05
45.61.26
2026.05
45.31.13
2026.05
45.1-
2026.05
44.52.04
2026.05
44.41
2026.05
44.10.82
2026.05
43.60.95
2026.05
37.1-