List your company

Mathematical Reasoning on MR-GSM8K

92AccuracyToT
67.14473.59780.0586.503Oct 3, 2024

Evaluation results

MethodLinks
ToTBase Model=Claude 3.5 Sonnet2024.1092
DIDBase Model=Claude 3.5 Sonnet2024.1092
CoTBase Model=Claude 3.5 Sonnet2024.1091.3
ToTBase Model=GPT-4o2024.1089.1
DIDBase Model=GPT-4o2024.1087.7
CoTBase Model=GPT-4o2024.1085
ToTBase Model=GPT-3.5 Turbo2024.1074
DIDBase Model=GPT-3.5 Turbo2024.1073.3
CoTBase Model=GPT-3.5 Turbo2024.1068.1