ResearchDatasetsAlpacaEval, MT-bench, Vicuna-benchAlpacaEval, MT-bench, Vicuna-benchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsInstruction FollowingAlpacaEval, MT-bench, Vicuna-bench95.3AlpacaEval Score13