ResearchTasksGeneral LLM CapabilityFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedGeneral Capability Suite MMLU, AlpacaEval, GSM8K, MATH, HumanEvalBFPO71.86MMLU56Jun 2, 2026