ResearchDatasetsevaluation promptsevaluation promptsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-shot Video Generation20 evaluation prompts 1.0 (User Study)4.15Temporal Consistency Score7Text-to-score generation238 evaluation prompts3.48Prompt Adherence3Language ModelingEvaluation Prompts21.45Perplexity (Evaluation Prompts)3