ResearchDatasetsARC, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K, IFEvalFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsPost-training EvaluationARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT, IFEval-PT (test)51.27Average Score7
Post-training EvaluationARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT, IFEval-PT (test)51.27Average Score7