Multimodal Understanding on MMStar 80% (test)
60.08AccuracyQwen2-VL-VCD
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2-VL-VCDBase Model=Qwen2-VL, Inference Strategy=VCD2026.03 | 60.08 | |
| Qwen2-VL-SCI5Base Model=Qwen2-VL, Inference Strategy=SCI52026.03 | 59.92 | |
| Qwen2-VL-M3IDBase Model=Qwen2-VL, Inference Strategy=M3ID2026.03 | 59.75 | |
| Qwen2-VLBase Model=Qwen2-VL2026.03 | 59.5 | |
| Qwen2-VL-TIEBase Model=Qwen2-VL, Inference Strategy=TIE2026.03 | 59 | |
| LLaVA-NeXT-TIEBase Model=LLaVA-NeXT, Inference Strategy=TIE2026.03 | 46 | |
| LLaVA-NeXT-M3IDBase Model=LLaVA-NeXT, Inference Strategy=M3ID2026.03 | 45.92 | |
| LLaVA-NeXT-SCI5Base Model=LLaVA-NeXT, Inference Strategy=SCI52026.03 | 45.75 | |
| LLaVA-NeXT-VCDBase Model=LLaVA-NeXT, Inference Strategy=VCD2026.03 | 45 | |
| LLaVA-NeXTBase Model=LLaVA-NeXT2026.03 | 44.75 |