Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

HumanEval, MBPP, MedQA, MedMCQA, FinEval, FinanceIQ, GSM8K, MATH

Benchmarks

Task NameDataset NameSOTA ResultTrend
Federated Domain-Specific Fine-tuningHumanEval, MBPP, MedQA, MedMCQA, FinEval, FinanceIQ, GSM8K, MATH In-Domain (test)
Average In-Domain Performance61.19
16
Showing 1 of 1 rows