List your company

Multimodal Understanding on MME (test)

2,473.6ScoreMiMo-VL-7B-SFT-2508
1,042.1441,413.7721,785.42,157.028May 29, 2025Jul 2, 2025Aug 5, 2025Sep 8, 2025Oct 12, 2025Nov 15, 2025Dec 19, 2025

Evaluation results

MethodLinks
MiMo-VL-7B-SFT-2508Evaluation pipeline=reproduced2025.122,473.6
MiMo-VL-Miloco-7BEvaluation pipeline=reproduced2025.122,396.4
Lumina-DiMOOParams=8B, Base model=LLaDA, Architecture=Discrete Diff., Data scale=80M2025.051,534.2
MMaDAParams=8B, Base model=LLaDA, Architecture=Discrete Diff., Data scale=Unknown, Resolution=512 × 5122025.051,410.7
MudditParams=1B, Base model=Meissonic, Architecture=Discrete Diff, Data scale=16M, Resolution=1024 × 10242025.051,139.2
D-DiTParams=2B, Base model=SD3-medium, Architecture=Discrete Diff. + Diff., Data scale=40M, Resolution=512 × 5122025.051,124.7
MudditParams=1B, Base model=Meissonic, Architecture=Discrete Diff., Data scale=10M, Resolution=512 × 5122025.051,107.4
Show-OParams=1.3B, Base model=Phi-1.5, Architecture=AR + Discrete Diff, Data scale=35M, Resolution=512 × 5122025.051,097.2