ResearchDatasetsAIME, GPQA, MMLU-Pro, ToolBenchAIME, GPQA, MMLU-Pro, ToolBenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsSingle-turn ReasoningAIME, GPQA, MMLU-Pro, ToolBench Aggregate65Average Score28