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

Mathematical Reasoning on MATH 500 (Sel-AUC, AUROC)

0.95Sel-AUC

StructU+Self-ConsU

Updated 1mo ago

Evaluation Results

Method	Links
StructU+Self-ConsU 2026.06		0.95	0.843
StructU+Self-ConsU 2026.06		0.948	0.831
StructU+Self-ConsU 2026.06		0.947	0.84
Self-ConsU 2026.06		0.942	0.816
StructU 2026.06		0.936	0.789
StructU+Self-ConsU 2026.06		0.936	0.784
StructU+Self-ConsU 2026.06		0.934	0.776
StructU 2026.06		0.932	0.801
StructU 2026.06		0.931	0.813
StructU+Self-ConsU 2026.06		0.927	0.767
Self-ConsU 2026.06		0.923	0.759
StructU+Self-ConsU 2026.06		0.91	0.718
StructU+Self-ConsU 2026.06		0.906	0.729
StructU+Self-ConsU 2026.06		0.897	0.715
VerbalizedU 2026.06		0.891	0.686
StructU 2026.06		0.89	0.64
StructU 2026.06		0.889	0.652
StructU+Self-ConsU 2026.06		0.889	0.882
StructU+Self-ConsU 2026.06		0.888	0.876
StructU+Self-ConsU 2026.06		0.887	0.873
StructU 2026.06		0.886	0.611
VerbalizedU 2026.06		0.886	0.645
StructU+Self-ConsU 2026.06		0.886	0.87
StructU 2026.06		0.885	0.529
VerbalizedU 2026.06		0.883	0.715
StructU+Self-ConsU 2026.06		0.882	0.853
StructU+Self-ConsU 2026.06		0.88	0.871
VerbalizedU 2026.06		0.88	0.684
SemanticU 2026.06		0.875	0.546
Self-ConsU 2026.06		0.871	0.694
Self-ConsU 2026.06		0.871	0.817
VerbalizedU 2026.06		0.87	0.603
StructU 2026.06		0.869	0.582
StructU 2026.06		0.868	0.596
SemanticU 2026.06		0.86	0.46
Self-ConsU 2026.06		0.86	0.839
StructU 2026.06		0.859	0.798
StructU 2026.06		0.834	0.747
StructU 2026.06		0.833	0.754
StructU 2026.06		0.821	0.687
SemanticU 2026.06		0.819	0.717
SemanticU 2026.06		0.81	0.695
SemanticU 2026.06		0.783	0.72
StructU 2026.06		0.78	0.608
StructU 2026.06		0.726	0.609