List your company

Multimodal Perception on MME P

1,682.6MME-P ScoreBLIP3-o
143.504543.077942.651,342.223Jun 8, 2025Aug 4, 2025Sep 30, 2025Nov 27, 2025Jan 23, 2026Mar 21, 2026May 18, 2026

Evaluation results

MethodLinks
BLIP3-oLLM=Qwen2.5VL-7B-Instruct, Token Type=2D-Continuous dynamic2026.051,682.6
LLaVA-OneVisionLLM=Qwen2-7B, Token Type=2D-Continuous, Res.=3842026.051,580
ShareGPT4VLLM=Vicuna-7B, Token Type=2D-Continuous, Res.=3362026.051,567.4
Janus-ProLLM=DeepSeek-LLM-7B, Token Type=2D-Continuous, Res.=3842026.051,567.1
Lumina-DiMOO + OursBase Model=Lumina-DiMOO, Reproduction Status=Reproduced, Method Variation=With Mask Prior Suppression and Monotonic RoPE Scaling2026.051,553.1
WinTokLLM=Qwen3-8B, Token Type=1D-Continuous, Res.=2562026.051,552
Lumina-DiMOOBase Model=Lumina-DiMOO, Reproduction Status=Reproduced, Method Variation=Baseline2026.051,543.6
Lumina-DiMOOBase Model=Lumina-DiMOO, Reproduction Status=Reported, Method Variation=Original2026.051,534.2
LLaVA-v1.5LLM=Vicuna-7B, Token Type=2D-Continuous, Res.=3362026.051,510.7
Qwen2-VL-2B#Params=2B, TFLOPs=0.42025.061,501.4
LaTtE-Flow#Params=2B, TFLOPs=0.42025.061,501.4
TokLIPLLM=Qwen2.5-7B-Instruct, Token Type=1D-Continuous, Res.=3842026.051,496.6
VQRAELLM=Vicuna-13B, Token Type=2D-Continuous, Res.=2562026.051,491.1
VARGPTLLM=Vicuna-7B, Token Type=2D-Continuous, Res.=2562026.051,488.8
SEED-XLLM=LLaMA2-13B, Token Type=2D-Continuous, Res.=4482026.051,457
Seed-X#Params=17B, TFLOPs=11.12025.061,457
SemHiTokLLM=Qwen2.5-7B-Instruct, Token Type=2D-Discrete, Res.=2562026.051,449
UniTokLLM=LLaMA2-7B, Token Type=2D-Discrete, Res.=2562026.051,448
ILLUMELLM=Vicuna-7B, Token Type=2D-Continuous, Res.=2242026.051,445.3
Janus Pro#Params=1.5B, TFLOPs=0.82025.061,444
MMaDABase Model=MMaDA, Reproduction Status=Reported, Method Variation=Original2026.051,410.7
VILA-U#Params=7B, TFLOPs=3.62025.061,401.8
WinTokLLM=Qwen3-8B, Token Type=1D-Continuous, Res.=256, semantic tokens=642026.051,370.4
TokenFlow-LLLM=Vicuna-13B, Token Type=2D-Discrete, Res.=2562026.051,365.4
Janus#Params=1.5B, TFLOPs=0.82025.061,338
VILA-ULLM=LLaMA2-7B, Token Type=2D-Discrete, Res.=2562026.051,336.2
Emu3LLM=8B (from scratch), Token Type=2D-Discrete, Res.=5122026.051,243.8
EMU3#Params=8B, TFLOPs=4.12025.061,243.8
LiquidLLM=Gemma-7B, Token Type=2D-Discrete, Res.=5122026.051,119
MMaDA + OursBase Model=MMaDA, Reproduction Status=Reproduced, Method Variation=With Mask Prior Suppression and Monotonic RoPE Scaling2026.051,117.2
Show-oLLM=Phi-1.5-1.3B, Token Type=2D-Discrete, Res.=2562026.051,097.2
Show-o#Params=1.3B, TFLOPs=0.72025.061,097.2
MMaDABase Model=MMaDA, Reproduction Status=Reproduced, Method Variation=Baseline2026.051,070.6
Chameleon#Params=34B, TFLOPs=17.42025.06604.5
Chameleon#Params=7B, TFLOPs=3.62025.06202.7