ResearchTasksModel UtilityFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedIFEvalVanilla61.6Accuracy18May 12, 2026AlpacaVanilla68.7Accuracy18May 12, 2026Gemma-2B-ITSimNPO57.8Utility8May 28, 2026Alpaca-Llama 3 Utility BenchmarksDualOptim47.36ARC-c Score7May 22, 2026