| Benchmark | Model | Rank | Results |
|---|---|---|---|
| object-hallucination-evaluation-on-pope | LLaVA-1.5-Qwen2.5-7B + V-GIFT | #11 | F1: 87.7 |
| visual-question-answering-vqa-on-blink | LLaVA-1.5-Qwen2.5-7B + V-GIFT | #48 | Accuracy: 41.8 |
| vision-language-understanding-on-mmstar | LLaVA-1.5-Qwen2.5-7B + V-GIFT | #96 | Accuracy: 43.2 |