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

Mathematical Reasoning on AIME 2025 (Accuracy, AVG)

81.5Accuracy

Base

54.803261.734168.66575.5959Jan 15, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
81.583.6
2026.01
8083.34
2026.01
76.6780.42
2026.01
76.6780.42
2026.01
73.3378.33
2026.01
73.3378.33
2026.01
73.1376.57
2026.01
72.0876.77
2026.01
7074.9
2026.01
69.1773.75
2026.01
67.572.09
2026.01
67.0871.46
2026.01
66.6774.17
2026.01
65.8369.58
2026.01
64.1769.59
2026.01
55.8364.17