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

Mathematical Reasoning on MATH 500 (Top-1 Accuracy)

90Top-1 Accuracy

Hi-CoT (format-relaxed)

54.43263.66672.982.134Oct 7, 2025Nov 7, 2025Dec 9, 2025Jan 10, 2026Feb 10, 2026Mar 14, 2026Apr 15, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.03
90
2026.03
88.8
2026.03
88.8
2026.03
87.4
2026.03
86.2
2026.04
85.14
2026.04
85.14
2026.03
82.6
2026.04
82.43
2026.03
80.8
2026.04
79.73
2026.04
79.1
2026.04
78.6
2026.03
78.4
2026.03
78.2
2026.04
77.6
2026.03
77.2
2026.04
77.03
2026.03
76.8
2026.03
76.8
2026.04
76.7
2026.03
76.6
2026.03
76.2
2026.03
76.2
2026.03
76
2026.04
75.68
2026.03
75.6
2026.03
75.2
2026.03
75.2
2026.04
74.7
2026.03
74.6
2026.04
74.32
2026.03
74.2
2026.04
74.2
2026.04
74.1
2026.04
74
2026.04
73.6
2026.03
73.2
2026.03
73
2026.03
72.2
2026.03
72.2
2026.03
72
2026.03
71.8
2026.04
71.62
2026.03
71.4
2025.10
71.28
2026.03
71
2026.04
71
2026.03
70.6
2025.10
70.45
2026.03
70.4
2026.03
70
2026.03
69.8
2026.03
69.2
2026.04
68.92
2026.04
68.92
2026.04
68.92
2025.10
67.82
2026.03
67.6
2026.03
67.6
2026.03
66.6
2026.03
66.4
2025.10
66.31
2025.10
66.21
2026.03
66
2025.10
65.43
2026.03
65.2
2026.03
65
2026.04
64.86
2026.04
64.86
2026.04
64.86
2026.03
64.8
2026.03
63.8
2026.03
63.8
2026.03
63.4
2026.03
63.2
2026.03
63
2026.03
63
2026.03
62.8
2026.03
62.4
2025.10
62.34
2026.03
62
2026.03
62
2026.03
61.8
2025.10
60.84
2026.04
60.81
2025.10
60.28
2026.03
60
2026.03
58.8
2026.03
58.6
2026.03
58.2
2026.04
58.01
2025.10
57.91
2026.03
57
2026.03
56.8
2026.04
56.76
2026.03
56.4
2026.03
56.2
2026.04
56.2
2026.04
55.8
Showing 100 of 112 rows