ResearchTasksCreative Writing EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedEQ-Bench Creative (OOD)GPT-5.41,911Elo Rating14Jun 4, 2026EQ-Bench CreativeGPT-5.484.6S Score14Jun 4, 2026EQ-Bench Creative Writing v3GPT-4o83.8EQ-Bench6Apr 14, 2026