List your company

Mathematical Reasoning Skill Performance on MATH

56.4Overall PerformanceSKiC
30.08836.91943.7550.581Aug 1, 2023

Evaluation results

MethodLinks
SKiCModel=GPT4, Ensemble=✘2023.0856.479.743.629.574.658.236.655.924.3
ComplexCoTModel=GPT-4, Ensemble=PHP2023.0853.973.841.926.373.456.329.855.7—
VerificationModel=GPT-4, Ensemble=CSV2023.0851.876.238.625.370.45728.653.5—
CoT, ScratchpadModel=Minerva-540B, Ensemble=maj1@k2023.0850.371.14227.172.743.534.536.3—
ComplexCoTModel=GPT4, Ensemble=✘2023.0850.371.636.523.470.853.126.749.6—
CoTModel=PaLM-2, Ensemble=SC2023.0848.8————————
CoTModel=GPT4, Ensemble=✘2023.0842.2————————
SKiCModel=ChatGPT, Ensemble=✘2023.0840.66230.117.857.938.22335.514.9
ComplexCoTModel=ChatGPT, Ensemble=PHP2023.0836.557.725.417.149.133.716.135.1—
VerificationModel=ChatGPT, Ensemble=CSV2023.0834.758.92214.845.635.21333.5—
CoTModel=PaLM-2, Ensemble=✘2023.0834.3————————
ComplexCoTModel=ChatGPT, Ensemble=✘2023.0834.153.822.314.649.129.716.833.4—
CoT, ScratchpadModel=Minerva-540B, Ensemble=✘2023.0833.654.926.713.651.227.91821.2—
CoT, LtPModel=ChatGPT, Ensemble=✘2023.0831.152.322.516.949.630.216.329.8—