List your company

Mathematical Reasoning on Omni-MATH (Accuracy and CoT Deltas)

32.2Accuracy (Omni-MATH)OctoTools
26.79228.19629.631.004Feb 16, 2025

Evaluation results

MethodLinks
OctoToolsBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Mathematical, Visual Understanding=false, Numerical Calculation=true, Knowledge Retrieval=true, Multi-step Reasoning=true2025.0232.25.22.9
OctoToolsbaseBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Mathematical, Visual Understanding=false, Numerical Calculation=true, Knowledge Retrieval=true, Multi-step Reasoning=true2025.0230.2——
CoTBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Mathematical, Visual Understanding=false, Numerical Calculation=true, Knowledge Retrieval=true, Multi-step Reasoning=true2025.0229.3——
0-shotBackbone=gpt-4o-2024-08-06, Modality=Text, Domain=Mathematical, Visual Understanding=false, Numerical Calculation=true, Knowledge Retrieval=true, Multi-step Reasoning=true2025.0227——