| monocular-depth-estimation-on-diode-relative-depth-aligned | Modus | #2 | AbsRel: 0.285delta1: 0.718 |
| monocular-depth-estimation-on-scannet-relative-depth-aligned | Modus | #11 | AbsRel: 0.067delta1: 0.957 |
| object-hallucination-evaluation-on-pope | Modus | #17 | F1: 87.27 |
| monocular-depth-estimation-on-nyu-depth-v2 | Modus | #20 | absolute relative error: 0.065Delta < 1.25: 0.958 |
| visual-question-answering-on-docvqa-test | Modus | #42 | ANLS: 0.9011 |
| chart-question-answering-on-chartqa | Modus | #57 | 1:1 Accuracy: 82.45 |
| multimodal-reasoning-on-mmmu | MODUS | #96 | Accuracy: 51.1 |
| text-to-image-generation-on-geneval | MODUS (original prompts, no self-verification) | #96 | Overall: 0.81 |