| Benchmark | Model | Rank | Results |
|---|---|---|---|
| few-shot-image-classification-on-bongard-hoi | GPT-4o + CA | – | Avg. Accuracy: 77.3 |
| few-shot-image-classification-on-bongard-hoi | Gemini 2.0 + CA | – | Avg. Accuracy: 74.5 |
| visual-reasoning-on-bongard-openworld | GPT-4o + CA | – | 2-Class Accuracy: 92.8 |
| visual-reasoning-on-bongard-openworld | Gemini-2.0 + CA | – | 2-Class Accuracy: 93.6 |
| visual-reasoning-on-winoground | GPT-4o + CA | – | Text Score: 75.5Image Score: 58.5Group Score: 52 |