Multimodal Understanding on ViLP 80% (test)
58.06AccuracyQwen2-VL-SCI5
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2-VL-SCI5Base Model=Qwen2-VL, Inference Strategy=SCI52026.03 | 58.06 | |
| Qwen2-VL-VCDBase Model=Qwen2-VL, Inference Strategy=VCD2026.03 | 57.92 | |
| Qwen2-VL-M3IDBase Model=Qwen2-VL, Inference Strategy=M3ID2026.03 | 57.78 | |
| Qwen2-VL-TIEBase Model=Qwen2-VL, Inference Strategy=TIE2026.03 | 57.08 | |
| Qwen2-VLBase Model=Qwen2-VL2026.03 | 56.53 | |
| LLaVA-NeXT-VCDBase Model=LLaVA-NeXT, Inference Strategy=VCD2026.03 | 54.31 | |
| LLaVA-NeXT-M3IDBase Model=LLaVA-NeXT, Inference Strategy=M3ID2026.03 | 54.03 | |
| LLaVA-NeXT-TIEBase Model=LLaVA-NeXT, Inference Strategy=TIE2026.03 | 53.19 | |
| LLaVA-NeXT-SCI5Base Model=LLaVA-NeXT, Inference Strategy=SCI52026.03 | 53.06 | |
| LLaVA-NeXTBase Model=LLaVA-NeXT2026.03 | 51.53 |