ResearchDatasetsScientific Reasoning SuiteScientific Reasoning SuiteFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsScientific ReasoningScientific Reasoning Suite Aggregate: OlympicArena, MMLU-Redux, MMLU-Pro, GPQA, SuperGPQA61.4Mean@12
Scientific ReasoningScientific Reasoning Suite Aggregate: OlympicArena, MMLU-Redux, MMLU-Pro, GPQA, SuperGPQA61.4Mean@12