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

Mathematical Reasoning on MATH500 1.0 (test)

96.9Accuracy

A3PO

20.428840.281960.13579.9881Sep 26, 2025Nov 3, 2025Dec 11, 2025Jan 18, 2026Feb 25, 2026Apr 4, 2026May 12, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2025.12
96.9
2025.12
96.2
2025.12
95.8
2025.12
95.7
2025.12
95.5
2025.12
95.2
2025.12
91.3
2025.12
90.4
2025.12
87.4
2025.12
87.3
2025.12
87.1
2025.09
87.05
2025.12
86.9
2025.12
86.8
2025.12
86.2
2025.12
85.4
2025.12
84.5
2025.12
83.8
2025.09
83.47
2025.12
82.3
2025.09
79.95
2025.09
78.68
2026.04
64.94
2026.04
63.2
2026.04
62.46
2026.04
61.2
2026.04
57.89
2026.04
53.12
2026.02
51.9
2026.02
51.6
2026.02
50.8
2026.02
50.4
2026.02
49.6
2026.02
48.4
2026.02
47.6
2026.02
47.2
2026.02
46.6
2026.02
44.3
2026.02
42.7
2026.02
42.6
2026.02
42.5
2026.05
42.4
2026.02
41.7
2026.05
41.6
2026.05
41.1
2026.05
39.8
2026.05
39.8
2026.05
37.4
2026.02
37.2
2026.02
35
2026.05
32.4
2026.04
26.71
2026.04
26
2026.04
25.26
2026.04
24.43
2026.04
24.31
2026.04
23.37