Visual Understanding on MME perception and cognition v1.0
1,687MME Perception ScoreBAGEL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BAGELType=Unified, LLM Parameters=7B MOT2025.05 | 1,687 | 2,388 | |
| MetaQuery-XLType=Unified, LLM Parameters=7B2025.05 | 1,685 | — | |
| InternVL2Type=Und. Only, LLM Parameters=7B2025.05 | 1,648 | 2,210 | |
| BAGELType=Unified, LLM Parameters=1.5B MOT2025.05 | 1,610 | 2,183 | |
| LlamaFusionType=Unified, LLM Parameters=8B2025.05 | 1,604 | — | |
| LLava-OVType=Und. Only, LLM Parameters=7B2025.05 | 1,580 | — | |
| Janus-ProType=Unified, LLM Parameters=7B2025.05 | 1,567 | — | |
| TokenFlow-XLType=Unified, LLM Parameters=13B2025.05 | 1,546 | — | |
| LLaVA-1.5Type=Und. Only, LLM=Vicuna-1.5-7B, V-Token=CLIP, Resolution=3362024.10 | 1,510.7 | — | |
| MMAR-7BType=Joint Prob. Models, LLM=Qwen-2-7B, V-Token=vae, Resolution=2562024.10 | 1,486.9 | — | |
| SEED-XType=Unified, LLM Parameters=13B2025.05 | 1,457 | — | |
| ILLUMEType=Unified, LLM Parameters=7B2025.05 | 1,445 | — | |
| Janus-ProType=Unified, LLM Parameters=1.5B2025.05 | 1,444 | — | |
| InternVL2Type=Und. Only, LLM Parameters=1.8B2025.05 | 1,440 | 1,877 | |
| SEED-XType=Und. & Gen. Non-prob., LLM=LLaMA-13B, V-Token=CLIP, Resolution=dynamic2024.10 | 1,435.7 | — | |
| JanusType=Unified, LLM Parameters=1.5B2025.05 | 1,338 | — | |
| VILA-UType=Joint Prob. Models, LLM=LLaMA-2-7B, V-Token=vq-vae, Resolution=2562024.10 | 1,336.2 | — | |
| VILA-UType=Unified, LLM Parameters=7B, Resolution=2562025.05 | 1,336 | — | |
| Emu3-ChatType=Und. Only, LLM Parameters=8B2025.05 | 1,244 | — | |
| Show-oType=Joint Prob. Models, LLM=Phi-1.5B, V-Token=CLIP, Resolution=3362024.10 | 1,182.7 | — | |
| Show-oType=Unified, LLM Parameters=1.3B, Resolution=5122025.05 | 1,097 | — | |
| MMAR-0.5BType=Joint Prob. Models, LLM=Qwen-2-0.5B, V-Token=vae, Resolution=2562024.10 | 882.1 | — | |
| Transfusion*Type=Joint Prob. Models, LLM=Qwen-2-0.5B, V-Token=vae, Resolution=2562024.10 | 594.3 | — | |
| Chameleon-7BType=Joint Prob. Models, LLM=7B from scratch, V-Token=vq-vae, Resolution=5122024.10 | 125.8 | — | |
| InternVL2.5Type=Und. Only, LLM Parameters=1.8B2025.05 | — | 2,138 | |
| InternVL2.5Type=Und. Only, LLM Parameters=7B2025.05 | — | 2,344 | |
| Qwen2-VLType=Und. Only, LLM Parameters=1.5B2025.05 | — | 1,872 | |
| Qwen2-VLType=Und. Only, LLM Parameters=7B2025.05 | — | 2,327 | |
| Qwen2.5-VLType=Und. Only, LLM Parameters=3B2025.05 | — | 2,157 | |
| Qwen2.5-VLType=Und. Only, LLM Parameters=7B2025.05 | — | 2,347 |