Visual Reasoning On Bongard Openworld
Metrics
2-Class Accuracy
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | 2-Class Accuracy |
|---|---|
| bongard-openworld-few-shot-reasoning-for-free | 91.0 |
| bongard-openworld-few-shot-reasoning-for-free | 49.3 |
| cognitive-paradigms-for-evaluating-vlms-on | 92.8 |
| cognitive-paradigms-for-evaluating-vlms-on | 93.6 |
| bongard-openworld-few-shot-reasoning-for-free | 63.3 |
| bongard-openworld-few-shot-reasoning-for-free | 55.5 |
| bongard-openworld-few-shot-reasoning-for-free | 64.0 |
| bongard-openworld-few-shot-reasoning-for-free | 49.3 |
| bongard-openworld-few-shot-reasoning-for-free | 63.8 |