| object-localization-on-illusionvqa | GPT4-Vision 4-shot+CoT | #1 | Accuracy: 49.7 |
| object-localization-on-illusionvqa | GPT4-Vision 4-shot | #2 | Accuracy: 46 |
| object-localization-on-illusionvqa | Gemini-Pro | #3 | Accuracy: 43.5 |
| object-localization-on-illusionvqa | Gemini-Pro 4-shot | #4 | Accuracy: 41.8 |
| object-localization-on-illusionvqa | GPT4-Vision | #5 | Accuracy: 40 |
| object-localization-on-illusionvqa | Gemini-Pro 4-shot+CoT | #6 | Accuracy: 33.9 |
| object-localization-on-illusionvqa | CogVLM | #7 | Accuracy: 28 |
| object-localization-on-illusionvqa | LLaVA-1.5-13B | #8 | Accuracy: 24.8 |
| object-localization-on-illusionvqa | InstructBLIP-13B | #9 | Accuracy: 24.3 |
| visual-question-answering-vqa-on-illusionvqa | GPT4-Vision 4-shot | #1 | Accuracy: 62.99 |
| visual-question-answering-vqa-on-illusionvqa | GPT4-Vision | #2 | Accuracy: 58.85 |
| visual-question-answering-vqa-on-illusionvqa | Gemini-Pro 4-shot | #3 | Accuracy: 52.87 |
| visual-question-answering-vqa-on-illusionvqa | Gemini-Pro | #4 | Accuracy: 51.26 |
| visual-question-answering-vqa-on-illusionvqa | LLaVA-1.5-13B | #5 | Accuracy: 40 |
| visual-question-answering-vqa-on-illusionvqa | CogVLM | #6 | Accuracy: 38.16 |
| visual-question-answering-vqa-on-illusionvqa | InstructBLIP-13B | #7 | Accuracy: 34.25 |