Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

MMRole

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal ConversationMMRole OOD
LLM-as-a-Judge Score91.6
20
Multimodal ConversationMMRole (ID)
LLM-as-a-Judge Score95.3
20
Showing 2 of 2 rows