ResearchDatasetsOnline Chinese conversation dataFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsConversation evaluationOnline Chinese conversation data 500 multi-turn proprietary dialogues (test)79.4Win Rate vs GPT42
Conversation evaluationOnline Chinese conversation data 500 multi-turn proprietary dialogues (test)79.4Win Rate vs GPT42