General Reasoning on MMStar (Score)
69.2ScoreViLoMem
Evaluation results
| Method | Links | |
|---|---|---|
| ViLoMemBackbone=InternVL-3.5-8B, Augmentation=ViLoMem2026.01 | 69.2 | |
| Vanilla RAGBackbone=QWEN2.5-VL-32B, Augmentation=Vanilla RAG2026.01 | 68.4 | |
| PolarMemBackbone=InternVL-3.5-8B, Augmentation=PolarMem2026.01 | 68.4 | |
| ViLoMemBackbone=QWEN2.5-VL-32B, Augmentation=ViLoMem2026.01 | 68.1 | |
| InternVL-3.5-8BBackbone=InternVL-3.5-8B, Augmentation=None2026.01 | 68.1 | |
| QWEN2.5-VL-32BBackbone=QWEN2.5-VL-32B, Augmentation=None2026.01 | 67.8 | |
| PolarMemBackbone=QWEN2.5-VL-32B, Augmentation=PolarMem2026.01 | 67.2 | |
| Vanilla RAGBackbone=InternVL-3.5-8B, Augmentation=Vanilla RAG2026.01 | 67.2 | |
| PolarMemBackbone=InternVL-3.5-4B, Augmentation=PolarMem2026.01 | 66.2 | |
| ViLoMemBackbone=InternVL-3.5-4B, Augmentation=ViLoMem2026.01 | 65.7 | |
| PolarMemBackbone=QWEN2.5-VL-7B, Augmentation=PolarMem2026.01 | 65.1 | |
| InternVL-3.5-4BBackbone=InternVL-3.5-4B, Augmentation=None2026.01 | 65.1 | |
| Vanilla RAGBackbone=InternVL-3.5-4B, Augmentation=Vanilla RAG2026.01 | 64.9 | |
| ViLoMemBackbone=QWEN2.5-VL-7B, Augmentation=ViLoMem2026.01 | 64.4 | |
| QWEN2.5-VL-7BBackbone=QWEN2.5-VL-7B, Augmentation=None2026.01 | 63.6 | |
| ViLoMemBackbone=LLaVA-Next-Llama-3-8B, Augmentation=ViLoMem2026.01 | 63.6 | |
| Vanilla RAGBackbone=QWEN2.5-VL-7B, Augmentation=Vanilla RAG2026.01 | 63.4 | |
| PolarMemBackbone=LLaVA-Next-Llama-3-8B, Augmentation=PolarMem2026.01 | 62.8 | |
| PolarMemBackbone=DeepSeek-VL2, Augmentation=PolarMem2026.01 | 62.4 | |
| PolarMemBackbone=LLaVA-Next-Mistral-7B, Augmentation=PolarMem2026.01 | 61.8 | |
| ViLoMemBackbone=DeepSeek-VL2, Augmentation=ViLoMem2026.01 | 61.6 | |
| LLaVA-Next-Llama-3-8BBackbone=LLaVA-Next-Llama-3-8B, Augmentation=None2026.01 | 61.5 | |
| ViLoMemBackbone=LLaVA-Next-Mistral-7B, Augmentation=ViLoMem2026.01 | 61.2 | |
| Vanilla RAGBackbone=LLaVA-Next-Llama-3-8B, Augmentation=Vanilla RAG2026.01 | 60.8 | |
| DeepSeek-VL2Backbone=DeepSeek-VL2, Augmentation=None2026.01 | 60.7 | |
| LLaVA-Next-Mistral-7BBackbone=LLaVA-Next-Mistral-7B, Augmentation=None2026.01 | 60.3 | |
| Vanilla RAGBackbone=DeepSeek-VL2, Augmentation=Vanilla RAG2026.01 | 59.7 | |
| ViLoMemBackbone=DeepSeek-VL2-Small, Augmentation=ViLoMem2026.01 | 59 | |
| Vanilla RAGBackbone=LLaVA-Next-Mistral-7B, Augmentation=Vanilla RAG2026.01 | 58.8 | |
| PolarMemBackbone=DeepSeek-VL2-Small, Augmentation=PolarMem2026.01 | 57.8 | |
| DeepSeek-VL2-SmallBackbone=DeepSeek-VL2-Small, Augmentation=None2026.01 | 56.9 | |
| Vanilla RAGBackbone=DeepSeek-VL2-Small, Augmentation=Vanilla RAG2026.01 | 56.2 |