List your company

Mathematical Reasoning on Math Base-9

92.7AccuracyCD-CoT
-2.56422.16846.971.632Oct 31, 2024

Evaluation results

MethodLinks
CD-CoTModel=Gemini-Pro2024.1092.7—————————
BTModel=Gemini-Pro2024.1082.4—————————
SCModel=Gemini-Pro2024.1080.3—————————
BaseModel=Gemini-Pro2024.1072.3—————————
CCModel=Gemini-Pro2024.1067.5—————————
CD-CoTModel=GPT-3.5-turbo2024.1060.7—————————
CCModel=GPT-3.5-turbo2024.1044.3—————————
SCModel=GPT-3.5-turbo2024.1036.6—————————
BTModel=GPT-3.5-turbo2024.1034.2—————————
BaseModel=GPT-3.5-turbo2024.1030.3—————————
CCModel=Mixtral 8x7B2024.1024.4—————————
SCModel=Mixtral 8x7B2024.1020—————————
BaseModel=Mixtral 8x7B2024.1016.3—————————
CD-CoTModel=Mixtral 8x7B2024.108.7—————————
SCModel=LLaMA2-70B2024.105—————————
BTModel=Mixtral 8x7B2024.104.1—————————
CD-CoTModel=LLaMA2-70B2024.104—————————
BaseModel=LLaMA2-70B2024.102.8—————————
BTModel=LLaMA2-70B2024.101.4—————————
CCModel=LLaMA2-70B2024.101.1—————————
Base2024.10—46.439.330.326.632.123.210.1613.1
BTAdditional Information=Noise Position2024.10—47.239.234.229.934.430.118.414.120.9
CCAdditional Information=Clean Demo2024.10—44.943.344.645.544.537.231.730.733.2
CD-CoTAdditional Information=Clean Demo2024.10—60.759.760.757.259.25458.748.453.7
SCOAdditional Information=Ground Truth2024.10—53.646.339.636.440.834.72217.724.8