ResearchDatasetsAIME, GPQA, MMLU-Pro, ToolBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsSingle-turn ReasoningAIME, GPQA, MMLU-Pro, ToolBench Aggregate65Average Score28