List your company
ResearchFormerly WizWand

Multimodal Understanding and Reasoning on MME

78.7MME ScoreLLaVA-NeXT
59.87664.76369.6574.537Jan 28, 2026
Updated 8mo ago

Evaluation results

MethodLinks
LLaVA-NeXTLLM=Vicuna-1.5-13B, #Sample=1.3M, #Param=≥7B2026.0178.7
VILA-7BLLM=LLaMA-7B, #Sample=50M, #Param=≥7B2026.0176.7
LLaVA-1.5-7BLLM=Vicuna-1.5-7B, #Sample=1.2M, #Param=≥7B2026.0175.5
LLaVA-FA-7BLLM=InternLM-2-20B, #Sample=5M, #Param=≥7B2026.0174.5
Qwen-VL-ChatLLM=Qwen-7B, #Sample=1450M, #Param=≥7B2026.0174.4
Bunny-3BLLM=Phi-2-2.7B, #Sample=2.7M, #Param=∼3B2026.0174.4
Deepseek-VL-7BLLM=DLLM-7B, #Sample=2000M, #Param=≥7B2026.0173.4
Imp-3BLLM=Phi-2-2.7B, #Sample=1.6M, #Param=∼3B2026.0172.3
VILA-3BLLM=LLaMA-2.7B, #Sample=51M, #Param=∼3B2026.0172.1
MobileVLMv2LLM=MLLaMA-2.7B, #Sample=3.6M, #Param=∼3B2026.0172
CogVLMLLM=Vicuna-7B, #Sample=1500M, #Param=≥7B2026.0171.8
MoE-LLaVA-3BLLM=Phi-2-2.7B, #Sample=2.2M, #Param=∼3B2026.0171.1
LLaVA-FA-3BLLM=LLaMA-3-8B, #Sample=5M, #Param=∼3B2026.0171
MiniCPM-V-2LLM=MiniCPM-2.4B, #Sample=570M, #Param=∼3B2026.0170.5
MiniCPM-VLLM=MiniCPM-2.4B, #Sample=570M, #Param=∼3B2026.0168.9
Mini-Gemini-2BLLM=Gemma-2B, #Sample=2.7M, #Param=∼2B2026.0167
LLaVA-FA-2BLLM=Qwen-2.5-7B, #Sample=5M, #Param=∼2B2026.0166.6
DeepSeek-VL-1.3BLLM=DLLM-1.3B, #Sample=2000M, #Param=∼2B2026.0165.3
Imp-2BLLM=Qwen-1.5-1.8B, #Sample=1.6M, #Param=∼2B2026.0165.2
Bunny-2BLLM=Qwen-1.5-1.8B, #Sample=2.7M, #Param=∼2B2026.0165
BLIP-2LLM=Vicuna-13B, #Sample=129M, #Param=≥7B2026.0164.7
MoE-LLaVA-2BLLM=Qwen-1.5-1.8B, #Sample=2.2M, #Param=∼2B2026.0164.6
MobileVLMLLM=MLLaMA-2.7B, #Sample=1.3M, #Param=∼3B2026.0164.4
LLaVA-FA-1BLLM=Qwen-2.5-3B, #Sample=5M, #Param=∼1B2026.0163.3
SPHINX-TinyLLM=TLLaMA-1.1B, #Sample=15M, #Param=∼1B2026.0163.1
InstructBLIPLLM=Vicuna-13B, #Sample=130M, #Param=≥7B2026.0160.6