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

Mathematical Reasoning on Minerva (ACC, mean@8)

66.78ACC

Base model

15.206428.595741.98555.3743Apr 15, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.04
66.7866.78
2026.04
48.6248.62
2026.04
48.0248.02
2026.04
47.7547.75
2026.04
47.7547.75
2026.04
47.5647.56
2026.04
44.7644.76
2026.04
44.5344.53
2026.04
44.3944.39
2026.04
44.3444.34
2026.04
43.1143.11
2026.04
39.6539.65
2026.04
37.5937.59
2026.04
37.5537.55
2026.04
36.9536.95
2026.04
35.9435.94
2026.04
24.8224.82
2026.04
17.1917.19