Multimodal Model Evaluation on MME (perception score)
1,632.9Perception ScoreSigLIP-SO400M
Evaluation Results
| Method | Links | |
|---|---|---|
| SigLIP-SO400MResolution=384^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,632.9 | |
| RADIOv2.5-gResolution=672^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,606.4 | |
| RADIOv2.5-LResolution=768^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,592.4 | |
| RADIOv2.1-HResolution=512^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,570.6 | |
| RADIOv2.5-HResolution=768^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,562.3 | |
| OpenAI-CLIPResolution=336^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,517.9 | |
| RADIOv2.1-HResolution=768^2, Tokens/im=196, LLM=MN-Minitron-8B, Data mixture=LLaVA1.62024.12 | 1,517.2 |