List your company
ResearchFormerly WizWand

Multimodal Evaluation on MME English

60.21ScoreFull Prec
7.159620.932334.70548.4777Aug 5, 2025
Updated 7mo ago

Evaluation results

MethodLinks
Full PrecModel=Qwen2.5-VL-32B-Instruct, Bit-width=Full Precision2025.0860.21
Full PrecModel=Qwen2.5-VL-7B-Instruct, Bit-width=Full Precision2025.0858.55
Full PrecModel=LLaVA-OneVision-7B, Bit-width=Full Precision2025.0857.39
Full PrecModel=Qwen2-VL-7B-Instruct, Bit-width=Full Precision2025.0857.3
VLMQModel=Qwen2-VL-7B-Instruct, Quantization Bit=INT42025.0855.88
GPTAQModel=Qwen2-VL-7B-Instruct, Quantization Bit=INT42025.0855.55
GPTQModel=Qwen2-VL-7B-Instruct, Quantization Bit=INT42025.0855.44
VLMQModel=Qwen2.5-VL-32B-Instruct, Bit-width=3-bit, Importance Factor Configuration=Default (ℓ1-norm)2025.0853.05
GPTAQModel=Qwen2.5-VL-32B-Instruct, Bit-width=3-bit2025.0852.13
GPTQModel=Qwen2.5-VL-32B-Instruct, Bit-width=3-bit2025.0851.77
VLMQModel=Qwen2-VL-7B-Instruct, Bit-width=3-bit, Importance Factor Configuration=Default (ℓ1-norm)2025.0850.17
GPTAQModel=Qwen2-VL-7B-Instruct, Bit-width=3-bit2025.0849.76
VLMQModel=LLaVA-OneVision-7B, Bit-width=3-bit, Importance Factor Configuration=token-level ℓ2-norm2025.0849.12
VLMQModel=LLaVA-OneVision-7B, Bit-width=3-bit, Importance Factor Configuration=Default (ℓ1-norm)2025.0848.93
GPTQModel=Qwen2-VL-7B-Instruct, Bit-width=3-bit2025.0847.76
GPTAQModel=Qwen2.5-VL-7B-Instruct, Bit-width=3-bit2025.0847.18
GPTAQModel=LLaVA-OneVision-7B, Bit-width=3-bit2025.0846.48
GPTQModel=LLaVA-OneVision-7B, Bit-width=3-bit2025.0846.47
VLMQModel=Qwen2.5-VL-7B-Instruct, Bit-width=3-bit, Importance Factor Configuration=Default (ℓ1-norm)2025.0845.5
GPTQBase Model=Qwen2.5-VL-7B-Instruct, Bit-width=2-bit, Group Size=1282025.0844.94
GPTAQBase Model=LLaVA-OneVision-7B, Bit-width=2-bit, Group Size=1282025.0842.59
GPTQModel=Qwen2.5-VL-7B-Instruct, Bit-width=3-bit2025.0842.31
VLMQBase Model=Qwen2-VL-7B-Instruct, Bit-width=2-bit, Group Size=128, Precursor Algorithm=GPTQ2025.0841.97
GPTQBase Model=Qwen2-VL-7B-Instruct, Bit-width=2-bit, Group Size=1282025.0841.33
VLMQBase Model=Qwen2.5-VL-7B-Instruct, Bit-width=2-bit, Group Size=128, Precursor Algorithm=GPTQ2025.0841.27
GPTQBase Model=LLaVA-OneVision-7B, Bit-width=2-bit, Group Size=1282025.0840.29
Full PrecModel=Qwen2-VL-2B-Instruct, Bit-width=Full Precision2025.0840.27
GPTAQBase Model=Qwen2.5-VL-7B-Instruct, Bit-width=2-bit, Group Size=1282025.0839.38
Full PrecModel=LLaVA-OneVision-0.5B, Bit-width=Full Precision2025.0838.94
GPTAQModel=Qwen2-VL-2B-Instruct, Bit-width=3-bit2025.0838.71
VLMQBase Model=LLaVA-OneVision-7B, Bit-width=2-bit, Group Size=1282025.0838.66
VLMQModel=Qwen2-VL-2B-Instruct, Bit-width=3-bit, Importance Factor Configuration=Default (ℓ1-norm)2025.0837.94
GPTAQBase Model=Qwen2-VL-7B-Instruct, Bit-width=2-bit, Group Size=1282025.0837.91
GPTQModel=Qwen2-VL-2B-Instruct, Bit-width=3-bit2025.0833.25
AWQModel=Qwen2-VL-7B-Instruct, Bit-width=3-bit2025.0830.2
MBQModel=Qwen2-VL-7B-Instruct, Bit-width=3-bit2025.0827.23
VLMQModel=LLaVA-OneVision-0.5B, Bit-width=3-bit, Importance Factor Configuration=‡ (unspecified variant)2025.0820.42
GPTQModel=LLaVA-OneVision-0.5B, Bit-width=3-bit2025.0813.4
MBQBase Model=Qwen2-VL-7B-Instruct, Bit-width=2-bit, Group Size=1282025.0812.46
AWQBase Model=Qwen2-VL-7B-Instruct, Bit-width=2-bit, Group Size=1282025.0811.58
MBQModel=Qwen2-VL-2B-Instruct, Bit-width=3-bit2025.0810.22
AWQModel=Qwen2-VL-2B-Instruct, Bit-width=3-bit2025.089.65
GPTAQModel=LLaVA-OneVision-0.5B, Bit-width=3-bit2025.089.2