ResearchDatasetsBBH, GPQA, and MMLU-ProFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSelective PredictionBBH, GPQA, and MMLU-Pro Pooled (test)1,384N0/N Count8