List your company

GSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQA

Benchmarks

TaskDatasetSOTA resultTrendResults
GSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQA USMLE
30.65Math Accuracy
24