List your company
ResearchFormerly WizWand

Multi-modal Vision-Language Understanding on MMBench (dev)

70.4ScoreASPO
21.10433.90246.759.498May 25, 2025
Updated 8mo ago

Evaluation results

MethodLinks
ASPOBase Model=LLaVA-v1.5, Model Scale=13B, Optimization Protocol=ASPO2025.0570.468.8
DPOBase Model=LLaVA-v1.5, Model Scale=13B, Optimization Protocol=DPO2025.0569.667.03
LLaVA-1.5-13BBase Model=LLaVA-v1.5, Model Scale=13B, Optimization Protocol=Base2025.0567.765.93
ASPOBase Model=LLaVA-v1.5, Model Scale=7B, Optimization Protocol=ASPO2025.0565.665.16
DPOBase Model=LLaVA-v1.5, Model Scale=7B, Optimization Protocol=DPO2025.0564.763.12
mPLUG-Owl2-7BBase Model=mPLUG-Owl2, Model Scale=7B, Optimization Protocol=Base2025.0564.5—
LLaVA-1.5-7BBase Model=LLaVA-v1.5, Model Scale=7B, Optimization Protocol=Base2025.0564.362.59
Qwen-VL-chat-7BBase Model=Qwen-VL-Chat, Model Scale=7B, Optimization Protocol=Base2025.0560.6—
IDEFICS-65BBase Model=IDEFICS, Model Scale=65B, Optimization Protocol=Base2025.0554.5—
IDEFICS-7BBase Model=IDEFICS, Model Scale=7B, Optimization Protocol=Base2025.0548.2—
Qwen-VL-7BBase Model=Qwen-VL, Model Scale=7B, Optimization Protocol=Base2025.0538.2—
LLaVA-7BBase Model=LLaVA, Model Scale=7B, Optimization Protocol=Base2025.0534.1—
ASPOBase Model=InstructBLIP, Model Scale=13B, Optimization Protocol=ASPO2025.0533.745.84
InstructBLIP-13BBase Model=InstructBLIP, Model Scale=13B, Optimization Protocol=Base2025.0533.543.86
DPOBase Model=InstructBLIP, Model Scale=13B, Optimization Protocol=DPO2025.0533.544.5
MiniGPT-4-7BBase Model=MiniGPT-4, Model Scale=7B, Optimization Protocol=Base2025.0523—