ResearchTasksFederated Domain-Specific Fine-tuningFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHumanEval, MBPP, MedQA, MedMCQA, FinEval, FinanceIQ, GSM8K, MATH In-Domain (test)FedSRD61.19Average In-Domain Performance16Mar 26, 2026
HumanEval, MBPP, MedQA, MedMCQA, FinEval, FinanceIQ, GSM8K, MATH In-Domain (test)FedSRD61.19Average In-Domain Performance16Mar 26, 2026