ResearchTasksHuman Subjective EvaluationFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedNarrative Detective Stories Human Subjective Evaluation (test)Llama 3.1-8B3.96Surprise Score14May 13, 2026
Narrative Detective Stories Human Subjective Evaluation (test)Llama 3.1-8B3.96Surprise Score14May 13, 2026