ResearchTasksCross-domain LLM EvaluationCross-domain LLM EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedMMLU, GSM8K, MultiArith, SVAMP, AQuA, HumanEvalRADAR90.32Average Score21May 12, 2026