Multimodal Evaluation on MME-P
1,687MME-P ScoreBAGEL
Evaluation Results
| Method | Links | |
|---|---|---|
| BAGELParams=7B+7B, Types=AR+Diff, Architecture Category=Uni. MoE/MoT Arch2025.11 | 1,687 | |
| Qwen2.5-VLParams=7B, Types=AR, Architecture Category=Und. Only2025.11 | 1,685 | |
| MetaQuery-XLParams=7B+1.6B, Types=AR+Diff, Architecture Category=Uni. Frozen MLLM2025.11 | 1,685 | |
| Blip3-oParams=7B+1.4B, Types=AR+Diff, Architecture Category=Uni. Frozen MLLM2025.11 | 1,685 | |
| UniWorld-V1Params=7B+12B, Types=AR+Diff, Architecture Category=Uni. Frozen MLLM2025.11 | 1,685 | |
| Janus-Pro + AIA (Ours)Params=7B, Types=AR, Architecture Category=Uni. Double Image Encoders / Training Objectives2025.11 | 1,656 | |
| OneCatParams=3B+3B+3B, Types=AR+VAR, Architecture Category=Uni. MoE/MoT Arch2025.11 | 1,630 | |
| Show-o2Params=7B, Types=AR+Diff, Architecture Category=Uni. Double Image Encoders / Training Objectives2025.11 | 1,621 | |
| Janus-ProParams=7B, Types=AR, Architecture Category=Uni. Double Image Encoders / Training Objectives2025.11 | 1,567 | |
| VILA-UParams=7B, Types=AR, Architecture Category=Uni. Purely2025.11 | 1,336 | |
| Emu3-ChatParams=8B, Types=AR, Architecture Category=Und. Only2025.11 | 1,244 | |
| Show-oParams=1.3B, Types=AR+Mask, Architecture Category=Uni. Double Image Encoders / Training Objectives2025.11 | 1,097 | |
| Emu3 + AIA (Ours)Params=8B, Types=AR, Architecture Category=Uni. Purely2025.11 | 1,084 | |
| Emu3Params=8B, Types=AR, Architecture Category=Uni. Purely, re-implemented=true2025.11 | 910 |