List your company
ResearchFormerly WizWand

Multi-modal Vision-Language Understanding on MMVet

81.3ScoreInternVL3
5.3825.0944.864.51May 25, 2025Jun 18, 2025Jul 12, 2025Aug 5, 2025Aug 29, 2025Sep 22, 2025Oct 16, 2025
Updated 8mo ago

Evaluation results

MethodLinks
InternVL3LLM=Qwen2.5-7B, # Data=>6B / 100M / 22M, Model Scale=8B, Architecture Category=Modular, Reinforcement Learning=true2025.1081.3—
Qwen2.5-VLLLM=Qwen2.5-7B, # Data=- / - / -, Model Scale=8B, Architecture Category=Modular, Reinforcement Learning=true2025.1067.1—
InternVL2.5LLM=InternLM2.5-7B, # Data=>6B / 50M / 4M, Model Scale=8B, Architecture Category=Modular, Reinforcement Learning=false2025.1062.8—
InternVL3LLM=Qwen2.5-1.5B, # Data=>6B / 100M / 22M, Model Scale=2B, Architecture Category=Modular, Reinforcement Learning=true2025.1062.2—
Qwen2-VLLLM=Qwen2-7B, # Data=- / - / -, Model Scale=8B, Architecture Category=Modular, Reinforcement Learning=false2025.1062—
Qwen2.5-VLLLM=Qwen2.5-3B, # Data=- / - / -, Model Scale=2B, Architecture Category=Modular, Reinforcement Learning=true2025.1061.8—
InternVL2.5LLM=InternLM2.5-1.8B, # Data=>6B / 100M / 16M, Model Scale=2B, Architecture Category=Modular, Reinforcement Learning=false2025.1060.8—
Encoder-BasedLLM=Qwen3-8B, # Data=>6B / 40M / 4M, Model Scale=8B, Architecture Category=Modular, Reinforcement Learning=false2025.1060—
Mono-InternVL-1.5LLM=InternLM2-1.8B, # Data=400M / 150M / 7M, Model Scale=2B, Architecture Category=Native, Reinforcement Learning=false2025.1054—
NEOLLM=Qwen3-8B, # Data=345M / 40M / 4M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1053.6—
NEOLLM=Qwen3-1.7B, # Data=345M / 40M / 4M, Model Scale=2B, Architecture Category=Native, Reinforcement Learning=false2025.1049.6—
Qwen2-VLLLM=Qwen2-1.5B, # Data=- / - / -, Model Scale=2B, Architecture Category=Modular, Reinforcement Learning=false2025.1049.5—
SAILLLM=Mistral-7B, # Data=512M / 86M / 6M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1046.3—
EVEv2LLM=Qwen2.5-7B, # Data=77M / 15M / 7M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1045—
HoVLELLM=InternLM2-1.8B, # Data=550M / 50M / 7M, Model Scale=2B, Architecture Category=Native, Reinforcement Learning=false2025.1043.8—
OneCATLLM=Qwen2.5-1.5B, # Data=436M / 70M / 13M, Model Scale=2B, Architecture Category=Native, Reinforcement Learning=false2025.1042.4—
ASPOBase Model=LLaVA-v1.5, Model Scale=13B, Optimization Protocol=ASPO2025.0541.268.8
Mono-InternVLLLM=InternLM2-1.8B, # Data=1.2B / 143M / 7M, Model Scale=2B, Architecture Category=Native, Reinforcement Learning=false2025.1040.1—
BREENLLM=Qwen2.5-7B, # Data=13M / 0M / 4M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1038.9—
DPOBase Model=LLaVA-v1.5, Model Scale=13B, Optimization Protocol=DPO2025.0538.867.03
Encoder-BasedLLM=Qwen3-1.7B, # Data=>6B / 40M / 4M, Model Scale=2B, Architecture Category=Modular, Reinforcement Learning=false2025.1037.4—
Emu3LLM=from scratch, # Data=- / - / -, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1037.2—
mPLUG-Owl2-7BBase Model=mPLUG-Owl2, Model Scale=7B, Optimization Protocol=Base2025.0536.2—
LLaVA-1.5-13BBase Model=LLaVA-v1.5, Model Scale=13B, Optimization Protocol=Base2025.0535.465.93
ASPOBase Model=LLaVA-v1.5, Model Scale=7B, Optimization Protocol=ASPO2025.0535.365.16
VoRALLM=Qwen2.5-7B, # Data=30M / 0M / 0.6M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1033.7—
DPOBase Model=LLaVA-v1.5, Model Scale=7B, Optimization Protocol=DPO2025.0533.363.12
LLaVA-1.5-7BBase Model=LLaVA-v1.5, Model Scale=7B, Optimization Protocol=Base2025.0530.562.59
SOLOLLM=Mistral-7B, # Data=44M / 0M / 2M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1030.4—
ASPOBase Model=InstructBLIP, Model Scale=13B, Optimization Protocol=ASPO2025.052745.84
LLaVA-7BBase Model=LLaVA, Model Scale=7B, Optimization Protocol=Base2025.0526.7—
DPOBase Model=InstructBLIP, Model Scale=13B, Optimization Protocol=DPO2025.0526.144.5
EVELLM=Vicuna-7B, # Data=33M / 0M / 1.8M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1025.7—
InstructBLIP-13BBase Model=InstructBLIP, Model Scale=13B, Optimization Protocol=Base2025.0525.643.86
BLIP-2-7BBase Model=BLIP-2, Model Scale=7B, Optimization Protocol=Base2025.0522.4—
MiniGPT-4-7BBase Model=MiniGPT-4, Model Scale=7B, Optimization Protocol=Base2025.0522.1—
FuyuLLM=Persimmon-8B, # Data=- / - / -, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.1021.4—
ChameleonLLM=from scratch, # Data=1.4B / 0M / 1.8M, Model Scale=8B, Architecture Category=Native, Reinforcement Learning=false2025.108.3—