ResearchDatasetsGSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQAGSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-domain EvaluationGSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQA USMLE30.65Math Accuracy24
Multi-domain EvaluationGSM8K, MATH, HumanEval, MBPP, FinanceBench, ConvFinQA, PubMedQA, and MedQA USMLE30.65Math Accuracy24