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

Mathematical Reasoning on SAT-Math (Pass@1)

100Pass@1

MT

38.22454.26270.386.338Apr 14, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.04
100
2026.04
81.2
2026.04
81.2
2026.04
78.1
2026.04
68.8
2026.04
65.6
2026.04
43.8
2026.04
40.6