List your company

Mathematical Reasoning on AIME 2024 (Acc, Cost)

40AccuracyCOPE
1.863211.764121.66531.5659Jun 13, 2025

Evaluation results

MethodLinks
COPEShot=Zero, Train=×2025.0640478
LargeShot=Zero, Train=×2025.0633.3502
ABCShot=Zero, Train=×2025.0633.3485
FrugalGPTShot=Few, Train=✓2025.0633.3513
Cascade (verify)Shot=Few, Train=×2025.0626.6570
Cascade (vote)Shot=Few, Train=×2025.0623.3568
Small (majority)Shot=Zero, Train=×2025.066.67—
Small (single)Shot=Zero, Train=×2025.063.33—