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

Mathematical Reasoning on MATH (AUROC, AUARC)

0.7121AUROC

MATU

0.6178760.6423380.66680.691262Apr 9, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.04
0.71210.6518
2026.04
0.69660.8585
2026.04
0.66750.6439
2026.04
0.66020.8291
2026.04
0.65810.6225
2026.04
0.65060.8212
2026.04
0.64770.6065
2026.04
0.63960.8119
2026.04
0.63590.6133
2026.04
0.6340.6059
2026.04
0.63390.6008
2026.04
0.63140.8081
2026.04
0.63080.6115
2026.04
0.62610.7982
2026.04
0.62260.607
2026.04
0.62150.5953