List your company

Large Multi-modal Model Evaluation on LLaVA-Bench In-the-Wild v1

65.5Conversational ScoreLLaVA-Plus
29.72439.01248.357.588Nov 9, 2023

Evaluation results

MethodLinks
LLaVA-Plustool_usage=All Tools2023.1165.556.879.169.5
LLaVA-Plustool_usage=Fly2023.1145.250.472.659.1
LLaVA2023.1142.651.968.957.1
LLaVAevaluation_protocol=Tools in Test2023.1140.748.151.247.5
LLaVA-Plustool_usage=Fly, reasoning_thoughts=false2023.1138.839.859.848.7
GPT4Tools2023.1131.127.154.140.7