ResearchTasksPost-training EvaluationFor AI assistantsMarkdownContent indexPost-training EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT, IFEval-PT (test)Tucano2-qwen-3.7B-Think51.27Average Score7Mar 5, 2026
ARC-Challenge, ENEM, BLUEX, OAB Exams, BELEBELE, MMLU, GSM8K-PT, IFEval-PT (test)Tucano2-qwen-3.7B-Think51.27Average Score7Mar 5, 2026