| text-to-image-generation-on-tiif-bench-mini | SenseNova-U1-8B-MoT | #1 | Accuracy: 89.74 |
| image-editing-on-risebench | SenseNova-U1-SFT (8BA3B, w/ CoT) | #2 | RISEBench Overall Accuracy: 30.0 |
| text-to-image-generation-on-cvtg-2k | SenseNova-U1-8B-MoT | #2 | Word Accuracy: 0.940NED: 0.972 |
| image-generation-on-wise | SenseNova-U1-A3B-MoT (w/ CoT) | #3 | Overall: 0.81 |
| text-to-image-generation-on-oneig-zh | SenseNova-U1-A3B-MoT | #3 | OneIG Overall Score: 0.540 |
| visual-question-answering-vqa-on-mmbench-en | SenseNova-U1-A3B-MoT | #3 | Accuracy: 91.59 |
| optical-character-recognition-ocr-on-ocrbench | SenseNova-U1-A3B-MoT | #4 | Score: 919 |
| instruction-following-on-ifbench | SenseNova-U1-A3B-MoT | #5 | Accuracy: 79.79 |
| text-to-image-generation-on-longtext-bench | SenseNova-U1-8B-MoT | #5 | Accuracy: 97.9 |
| text-to-image-generation-on-longtext-bench-zh | SenseNova-U1-8B-MoT | #7 | Accuracy: 96.2 |
| text-to-image-generation-on-longtext-bench-zh | SenseNova-U1 (8BA3B) | #8 | Accuracy: 95.5 |
| text-to-image-generation-on-oneig-en | SenseNova-U1-8B-MoT | #7 | OneIG Overall Score: 0.549 |
| agents-on-claw-eval | SenseNova-U1-A3B-MoT | #8 | Accuracy: 58.50 |
| vision-language-understanding-on-mmstar | SenseNova-U1-A3B-MoT | #8 | Accuracy: 80.92 |
| multimodal-reasoning-on-babyvision | SenseNova-U1-A3B-MoT | #9 | Accuracy: 31.70 |
| multimodal-reasoning-on-mmmu | SenseNova-U1-A3B-MoT | #10 | Accuracy: 80.55 |
| multiple-choice-question-answering-mcqa-on-supergpqa | SenseNova-U1-A3B-MoT | #10 | Accuracy: 59.71 |
| multimodal-reasoning-on-mathvision | SenseNova-U1-A3B-MoT | #11 | Accuracy: 79.63 |
| text-to-image-generation-on-dpg-bench | SenseNova-U1 (8BA3B) | #12 | DPG-Bench Score: 88.14 |
| image-editing-on-imgedit-data | SenseNova-U1-A3B-MoT | #13 | Overall: 3.91 |
| multimodal-reasoning-on-mathvista | SenseNova-U1-A3B-MoT | #15 | Accuracy: 85.30 |
| image-editing-on-gedit-bench-en | SenseNova-U1-8B-MoT | #17 | Overall: 7.47 |
| multi-task-language-understanding-on-mmlu-redux | SenseNova-U1-A3B-MoT | #17 | Accuracy: 89.44 |
| multimodal-reasoning-on-mmmu-pro | SenseNova-U1-A3B-MoT | #17 | Accuracy: 72.83 |
| agents-on-bench | SenseNova-U1-A3B-MoT | #18 | Accuracy: 75.39 |
| text-to-image-generation-on-geneval | SenseNova-U1-A3B-MoT | #18 | Overall: 0.91 |
| multi-task-language-understanding-on-c-eval | SenseNova-U1-A3B-MoT | #20 | Accuracy: 85.89 |
| multi-task-language-understanding-on-mmlu-pro | SenseNova-U1-A3B-MoT | #23 | Accuracy: 84.04 |