ResearchTasksTokenization EfficiencyTokenization EfficiencyFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updated1.5-million sentence evaluation corpus EnglishDeepSeek V37,904,670Other Tokens Count3Mar 27, 20261.5-million sentence evaluation corpus HindiOpenAI (o200k)18,394,075Other Tokens3Mar 27, 20261.5-million sentence evaluation corpus (Sinhala)OpenAI (o200k)17,360,196Other Token Count3Mar 27, 2026PreviousPage 3 of 3Next
1.5-million sentence evaluation corpus (Sinhala)OpenAI (o200k)17,360,196Other Token Count3Mar 27, 2026