| audio-understanding-reasoning-on-mmau-pro | dots3-note Preview | #1 | MMAU-Pro Overall Weighted Performance: 69.79 |
| deep-research-agents-on-browsecomp-zh | dots3-note Preview | #1 | Accuracy: 75.78 |
| chart-question-answering-on-charxiv-rq | dots3-note Preview | #2 | Accuracy: 83.1 |
| multimodal-reasoning-on-mathvision | dots3-note Preview | #2 | Accuracy: 87.66 |
| video-question-answering-on-video-mmmu | dots3-note Preview | #2 | Accuracy: 86.78 |
| multimodal-reasoning-on-babyvision | dots3-note Preview | #3 | Accuracy: 50 |
| multimodal-reasoning-on-mmmu-pro | dots3-note Preview | #3 | Accuracy: 79.08 |
| video-question-answering-on-mmvu | dots3-note Preview | #5 | Accuracy: 79.9 |
| code-generation-on-nl2repo | dots3-note Preview | #9 | Accuracy: 49.82 |
| deep-research-agents-on-browsecomp | dots3-note Preview (w/ context management) | #10 | Accuracy: 83.3 |
| code-generation-on-swe-bench-verified | dots3-note Preview (live-swe-agent) | #13 | Accuracy: 78.4 |
| code-generation-on-swe-bench-multilingual | dots3-note Preview (live-swe-agent) | #15 | Accuracy: 75.67 |