ResearchDatasetsSTEM-BenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsStreaming Long-context Question AnsweringSTEM-Bench The Office0.304Time14Streaming Long-context Question AnsweringSTEM-Bench Friends0.318Time14Streaming Long-context Question AnsweringSTEM-Bench The Big Bang Theory0.4Time (s)14