ResearchDatasetsMMRoleFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsMultimodal ConversationMMRole OOD91.6LLM-as-a-Judge Score20Multimodal ConversationMMRole (ID)95.3LLM-as-a-Judge Score20Multimodal Role-playingMMRole (out-of-domain)1.164IA17Multi-modal Role-playingMMRole in-domain1.199IA17