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

Mathematical Reasoning on Math (Acc. (%), ∆ (%))

80.8Accuracy (%)

TRACELOCK

22.14437.37252.667.828May 11, 2026May 13, 2026May 15, 2026May 17, 2026May 19, 2026May 21, 2026May 23, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
80.8-
2026.05
80.7-
2026.05
80-
2026.05
79.9-
2026.05
79.9-
2026.05
79.8-
2026.05
79.46.6
2026.05
79.4-
2026.05
78.65.8
2026.05
78.45.6
2026.05
78.45.6
2026.05
78.3-
2026.05
77.44.6
2026.05
76.5-
2026.05
76.43.6
2026.05
76.4-
2026.05
76.23.4
2026.05
76-
2026.05
75.22.4
2026.05
74.9-
2026.05
74.8-
2026.05
74.8-
2026.05
74.4-
2026.05
74.21.4
2026.05
73.8-
2026.05
73.5-
2026.05
73.5-
2026.05
73.5-
2026.05
73.20.4
2026.05
73.2-
2026.05
730.2
2026.05
73-
2026.05
72.8-
2026.05
71.5-
2026.05
70.5-
2026.05
70-
2026.05
69.5-
2026.05
69.1-
2026.05
69.1-
2026.05
67.1-
2026.05
66.2-
2026.05
64.6-
2026.05
62.7-
2026.05
62.5-
2026.05
59.5-
2026.05
59.4-
2026.05
58.8-
2026.05
57.3-
2026.05
51.9-
2026.05
51.2-
2026.05
43.2-
2026.05
24.4-