List your company

Multimodal Reasoning and Tool-use on MM-Vet

44.7MM-Vet Tool-use ScorePPLLAVA
21.50827.52933.5539.571Jul 22, 2024Aug 8, 2024Aug 26, 2024Sep 12, 2024Sep 30, 2024Oct 17, 2024Nov 4, 2024

Evaluation results

MethodLinks
PPLLAVAResolution=336*3362024.1144.7
LLaVA-Next-VideoResolution=336*3362024.1144
LLaVA-Next-7BResolution=672*6722024.1143.9
LLaVA-1.5 + MMInstructLLM=Vicuna-13B2024.0737.9
LLaVA-1.5-13BResolution=336*3362024.1136.3
LLaVA-1.5LLM=Vicuna-13B2024.0735.4
LLaVA-1.5 + MMInstructLLM=Vicuna-7B2024.0734.4
VideoLLaVAResolution=336*3362024.1132
LLaVA-1.5LLM=Vicuna-7B2024.0730.5
Chat-Univ-1.5Resolution=336*3362024.1128.3
InstructBLIPLLM=Vicuna-7B2024.0726.2
InstructBLIPLLM=Vicuna-13B2024.0725.6
BLIP-2LLM=Vicuna-13B2024.0722.4