ResearchTasksReal-world Query EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedWildBench+RL (Skywork-Reward-V2-Llama-3.1-8B)71.5WildBench Accuracy14Mar 4, 2026