Multimodal Understanding on MME 80% (test)
87.89AccuracyQwen2-VL
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2-VLBase Model=Qwen2-VL2026.03 | 87.89 | |
| Qwen2-VL-SCI5Base Model=Qwen2-VL, Inference Strategy=SCI52026.03 | 87.36 | |
| Qwen2-VL-TIEBase Model=Qwen2-VL, Inference Strategy=TIE2026.03 | 86.52 | |
| Qwen2-VL-VCDBase Model=Qwen2-VL, Inference Strategy=VCD2026.03 | 86.41 | |
| Qwen2-VL-M3IDBase Model=Qwen2-VL, Inference Strategy=M3ID2026.03 | 86.1 | |
| LLaVA-NeXT-SCI5Base Model=LLaVA-NeXT, Inference Strategy=SCI52026.03 | 80.15 | |
| LLaVA-NeXTBase Model=LLaVA-NeXT2026.03 | 79.57 | |
| LLaVA-NeXT-M3IDBase Model=LLaVA-NeXT, Inference Strategy=M3ID2026.03 | 78.62 | |
| LLaVA-NeXT-VCDBase Model=LLaVA-NeXT, Inference Strategy=VCD2026.03 | 78.09 | |
| LLaVA-NeXT-TIEBase Model=LLaVA-NeXT, Inference Strategy=TIE2026.03 | 77.3 |