Multimodal Reasoning on RealWorldQA
70.46Mean@8 AccuracyQwen2.5-VL-VIF
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-VIFParams=7B, Base model=Qwen-2.5-VL2026.05 | 70.46 | |
| CAVE-7BParameters=7B2026.05 | 69.7 | |
| RAPOBase Model=Qwen3-VL-8B-Instruct2026.05 | 69.54 | |
| PAPOBase Model=Qwen3-VL-8B-Instruct2026.05 | 69.41 | |
| Qwen3-VL-8B-InstructParameters=8B, Instruct=true2026.05 | 69.3 | |
| Qwen2.5-VLParams=7B, Base model=Qwen-2.5-VL2026.05 | 68.63 | |
| DeepEyes-7BParameters=7B2026.05 | 68.4 | |
| Qwen2.5-VL-SFTParams=7B, Base model=Qwen-2.5-VL2026.05 | 68.37 | |
| GRPOBase Model=Qwen3-VL-8B-Instruct2026.05 | 67.66 | |
| VPPOBase Model=Qwen3-VL-8B-Instruct2026.05 | 67.48 | |
| BaseBase Model=Qwen3-VL-8B-Instruct2026.05 | 67.2 | |
| RAPOBase Model=Qwen3-VL-2B-Instruct2026.05 | 65.36 | |
| RAPO_DBase Model=Qwen2-VL-7B-Instruct2026.05 | 65.01 | |
| RAPO_GBase Model=Qwen2-VL-7B-Instruct2026.05 | 64.67 | |
| GRPOBase Model=Qwen3-VL-2B-Instruct2026.05 | 64.28 | |
| Cambrian-1Params=8B2026.05 | 64.2 | |
| PAPOBase Model=Qwen3-VL-2B-Instruct2026.05 | 64.05 | |
| VPPOBase Model=Qwen3-VL-2B-Instruct2026.05 | 63.14 | |
| GPT-4V-1106Params=-2026.05 | 63 | |
| MM-EurekaBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 61.96 | |
| InternVL3.5-8BParameters=8B2026.05 | 61.6 | |
| BaseBase Model=Qwen3-VL-2B-Instruct2026.05 | 60.47 | |
| Gemini ProParams=-2026.05 | 60.4 | |
| mPLUG-Owl3Params=8B2026.05 | 60.4 | |
| RAPO_GBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 60.26 | |
| Qwen2.5-VLParameters=7B2026.05 | 59.4 | |
| VL-RethinkerBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 59.22 | |
| RAPO_DBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 58.4 | |
| LLaVA-1.5-VIFParams=7B, Base model=LLaVA-1.52026.05 | 57.78 | |
| LLaVA-1.5-VIFParams=13B, Base model=LLaVA-1.52026.05 | 56.99 | |
| R1-ShareVLBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 56.47 | |
| VISTAParams=7B, Base model=LLaVA-1.52026.05 | 56.34 | |
| LLaVA-1.5Params=7B, Base model=LLaVA-1.52026.05 | 55.95 | |
| LLaVA-1.5-SFTParams=7B, Base model=LLaVA-1.52026.05 | 55.56 | |
| LLaVA-1.5-SFTParams=13B, Base model=LLaVA-1.52026.05 | 55.29 | |
| LLaVA-1.5Params=13B, Base model=LLaVA-1.52026.05 | 54.9 | |
| BaseBase Model=Qwen2.5-VL-7B-Instruct2026.05 | 54.51 | |
| TVCBase Model=Qwen2-VL-7B-Instruct2026.05 | 52.88 | |
| MINT-CoTBase Model=Qwen2-VL-7B-Instruct2026.05 | 49.15 | |
| BaseBase Model=Qwen2-VL-7B-Instruct2026.05 | 31.83 |