List your company

Mathematical Reasoning on MATH (test) (Accuracy, Speed-up)

24.9Final Test AccuracyVinePPO
18.86820.4342223.566Feb 17, 2025

Evaluation results

MethodLinks
VinePPOLILO Integration=true2025.0224.93.2
VinePPOLILO Integration=false2025.0222.8—
PPOLILO Integration=true2025.0221.82.5
PPOLILO Integration=false2025.0219.1—