Multimodal Understanding on MME (Perc., Cog., Total)
1,527.34Perc. ScoreSeeMe
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SeeMeModel=LLaVA-NEXT2026.07 | 1,527.34 | 346.43 | 1,873.77 | |
| DCLAModel=LLaVA-NEXT2026.07 | 1,525.73 | 330 | 1,855.73 | |
| DCLAModel=LLaVA-1.52026.07 | 1,520.14 | 280 | 1,800.14 | |
| SeeMeModel=LLaVA-1.52026.07 | 1,519.49 | 310 | 1,829.49 | |
| RegularModel=LLaVA-NEXT2026.07 | 1,519.3 | 330 | 1,849.3 | |
| DoLaModel=LLaVA-NEXT2026.07 | 1,515.41 | 262.14 | 1,777.55 | |
| SeeMeModel=INF-MLLM2026.07 | 1,511.17 | 269.29 | 1,780.46 | |
| DCLAModel=INF-MLLM2026.07 | 1,509.05 | 273.21 | 1,782.26 | |
| SPINModel=LLaVA-NEXT2026.07 | 1,506.37 | 326.07 | 1,832.44 | |
| DoLaModel=LLaVA-1.52026.07 | 1,495.02 | 318.21 | 1,813.23 | |
| SPINModel=INF-MLLM2026.07 | 1,493.21 | 268.33 | 1,761.54 | |
| RegularModel=INF-MLLM2026.07 | 1,491.96 | 266.07 | 1,758.03 | |
| SPINModel=LLaVA-1.52026.07 | 1,491.91 | 295.71 | 1,787.62 | |
| RegularModel=LLaVA-1.52026.07 | 1,491.56 | 294.29 | 1,785.85 | |
| DoLaModel=INF-MLLM2026.07 | 1,491.15 | 265 | 1,756.15 | |
| VCDModel=LLaVA-1.52026.07 | 1,484.96 | 287.5 | 1,772.46 | |
| SeeMeModel=mPLUG-Owl22026.07 | 1,472.04 | 345.71 | 1,817.75 | |
| SPINModel=mPLUG-Owl22026.07 | 1,465.38 | 332.56 | 1,797.94 | |
| DCLAModel=mPLUG-Owl22026.07 | 1,463.4 | 334.29 | 1,797.69 | |
| DoLaModel=mPLUG-Owl22026.07 | 1,462.33 | 265 | 1,722.33 | |
| RegularModel=mPLUG-Owl22026.07 | 1,459.54 | 345.71 | 1,805.25 | |
| VCDModel=INF-MLLM2026.07 | 1,444.36 | 270.71 | 1,715.07 | |
| VCDModel=LLaVA-NEXT2026.07 | 1,418.27 | 351.07 | 1,769.34 | |
| VCDModel=mPLUG-Owl22026.07 | 1,311.52 | 329.29 | 1,640.81 |