ResearchTasksGeneral LLM CapabilityGeneral LLM CapabilityFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGeneral Capability Suite MMLU, AlpacaEval, GSM8K, MATH, HumanEvalBFPO71.86MMLU56Jun 2, 2026