Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mathematical Reasoning on OmniMath (test)

0.446Top-1 Accuracy

Dele-SimKO

0.308720.344360.380.41564Jan 25, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
0.4460.5610.5920.5288,500
2026.01
0.4380.5680.6010.5287,000
2026.01
0.4350.5150.540.4918,600
2026.01
0.4310.5420.5710.5098,400
2026.01
0.4180.480.4980.4628,500
2026.01
0.4120.530.5580.4937,500
2026.01
0.3870.4980.5230.4626,000
2026.01
0.3140.4580.4890.4122,600