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

Mathematical Reasoning on AIME25 (Accuracy, C_mem, C_time)

0.14C_mem Ratio

DSC

0.10560.33780.570.8022Jan 29, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
0.140.984.35
2026.01
0.170.526.38
2026.01
0.170.5654.15
2026.01
0.212.445.99
2026.01
0.222.7850.23
2026.01
0.243.7652.97
2026.01
0.260.568.28
2026.01
0.262.4153.81
2026.01
0.280.978.89
2026.01
0.282.2553.86
2026.01
0.32265.3
2026.01
0.331.4510.02
2026.01
0.350.6810.32
2026.01
0.372.7567.79
2026.01
0.413.56.08
2026.01
0.412.1968.12
2026.01
0.662.839.94
2026.01
0.725.224.87
2026.01
0.753.5768.9
2026.01
0.781.8810.25
2026.01
1110.06
2026.01
116.57
2026.01
1168.67
2026.01
1154