| image-editing-on-kris-bench | BAGEL (7B active / 14B total MoT) with Self-CoT | #4 | KRIS-Bench Overall: 60.18 |
| visual-question-answering-vqa-on-mme | BAGEL (7B MoT) | #6 | Score: 2388 |
| image-editing-on-risebench | BAGEL (w/ Self-CoT) | #8 | RISEBench Overall Accuracy: 11.9 |
| text-to-image-generation-on-wise | BAGEL | #16 | Overall: 0.52Cultural: 0.44Time: 0.55Space: 0.68Biology: 0.44… |
| visual-question-answering-vqa-on-mmbench-en | BAGEL (7B MoT) | #16 | Accuracy: 85.0 |
| image-generation-on-wise | Bagel (w/ cot) | #17 | Overall: 0.70Cultural: 0.76Time: 0.69Space: 0.75Biology: 0.65… |
| image-generation-on-wise | Bagel | #41 | Overall: 0.52Cultural: 0.44Time: 0.55Space: 0.68Biology: 0.44… |
| image-editing-on-imgedit-data | BAGEL | #26 | Overall: 3.20Add: 3.56Adjust: 3.31Extract: 1.70Replace: 3.30… |
| image-editing-on-gedit-bench-en | BAGEL | #30 | Overall: 6.52Perceptual Quality: 6.83Semantic Consistency: 7.36 |
| multimodal-reasoning-on-mathvista | BAGEL (7B MoT) | #57 | Accuracy: 73.1 |
| multimodal-reasoning-on-mmmu | BAGEL (7B MoT) | #74 | Accuracy: 55.3 |
| text-to-image-generation-on-geneval | BAGEL (7B MoT) | #90 | Overall: 0.82 |