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

Mathematical Problem Solving on MATH (Pass@1, Pass@16)

90.8Pass@1

MIXED-CUTS

65.964872.412478.8685.3076Apr 20, 2026Apr 24, 2026Apr 29, 2026May 3, 2026May 8, 2026May 12, 2026May 17, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.04
90.896.6
2026.04
89.995.7
2026.04
86.495.9
2026.04
85.195.3
2026.04
83.693.9
2026.04
82.693.2
2026.04
82.594.4
2026.05
78.99-
76.76-
2026.05
76.28-
2026.05
73.59-
2026.05
73.51-
2026.05
72.91-
2026.05
70.9-
2026.04
70.290.5
66.92-