ResearchDatasetsIFEval, EvalPlus, MATH, and GAIA2FollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAttribution Faithfulness EvaluationIFEval, EvalPlus, MATH, and GAIA2 60 failure cases1.7Average Tokens to Fix3
Attribution Faithfulness EvaluationIFEval, EvalPlus, MATH, and GAIA2 60 failure cases1.7Average Tokens to Fix3