Image Classification on Open-MI VL-ICL Bench
85.6Average AccuracyQwen2.5-VL-7B-Instruct
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-VL-7B-InstructVL-Data=-NA-, Params trained=8B, TTA=FT≤302025.06 | 85.6 | |
| LLaVA-OneVision-7BVL-Data=10.4M, Params trained=8B, TTA=FT≤302025.06 | 83.4 | |
| LAQ-7B + MAPDVL-Data=1.3M, Params trained=24M, TTA=FT≤302025.06 | 77.9 | |
| LLaVA-OneVision-72BVL-Data=10.4M, Params trained=73.2B, TTA=ICL2025.06 | 75.1 | |
| Qwen2-VL-7B-InstructVL-Data=-NA-, Params trained=8B, TTA=ICL2025.06 | 73.5 | |
| LAQ-7B + In-ContextPDVL-Data=1.3M, Params trained=24M, TTA=FT≤302025.06 | 64.5 | |
| LLaVA-Next-7BVL-Data=1.3M, Params trained=7.06B, TTA=FT≤302025.06 | 55.1 | |
| LAQ-7B + MAPDVL-Data=1.3M, Params trained=24M, TTA=ICL2025.06 | 53.3 | |
| LAQ-7B + In-ContextPDVL-Data=1.3M, Params trained=24M, TTA=ICL2025.06 | 51.1 | |
| Qwen2.5-VL-7B-InstructVL-Data=-NA-, Params trained=8B, TTA=ICL2025.06 | 44 | |
| LLaVA-OneVision-7BVL-Data=10.4M, Params trained=8B, TTA=ICL2025.06 | 42.1 | |
| LLaVA v1.5-7BVL-Data=1.2M, Params trained=7B, TTA=FT≤302025.06 | 38.4 | |
| LLaVA-Next-7BVL-Data=1.3M, Params trained=7.06B, TTA=ICL2025.06 | 34.4 | |
| LLaVA v1.5-7BVL-Data=1.2M, Params trained=7B, TTA=ICL2025.06 | 12.4 |