| audio-visual-question-answering-on-omnibench | Qwen2.5-Omni-7B | #2 | Accuracy: 56.13 |
| visual-question-answering-vqa-on-textvqa-val | Qwen2.5-Omni-7B | #8 | Accuracy: 84.4 |
| visual-question-answering-on-docvqa-test | Qwen2.5-Omni-7B | #9 | ANLS: 0.952 |
| zero-shot-video-question-answer-on-egoschema-fullset | Qwen2.5-Omni | #10 | Accuracy: 68.6 |
| code-generation-on-multipl-e | Qwen2.5-Omni-7B | #12 | Accuracy: 65.8 |
| visual-question-answering-on-mm-vet | Qwen2.5-Omni-7B | #17 | GPT-4 score: 66.8 |
| vision-language-understanding-on-mmbench-v1-1 | Qwen2.5-Omni-7B | #18 | Accuracy: 81.8 |
| video-question-answering-on-video-mme-with-subtitles | Qwen2.5-Omni-7B (w/ subtitles) | #21 | Accuracy: 72.4 |
| math-word-problem-solving-on-math | Qwen2.5-Omni-7B | #29 | Accuracy: 71.5 |
| video-question-answering-on-mvbench | Qwen2.5-Omni-7B | #31 | Avg.: 70.3 |
| multi-task-language-understanding-on-mmlu-redux | Qwen2.5-Omni-7B | #32 | Accuracy: 71.0 |
| chart-question-answering-on-chartqa | Qwen2.5-Omni-7B | #45 | 1:1 Accuracy: 85.3 |
| code-generation-on-mbpp | Qwen2.5-Omni-7B | #48 | Accuracy: 73.2 |
| visual-question-answering-vqa-on-realworldqa | Qwen2.5-Omni-7B | #52 | Accuracy: 70.3 |
| multimodal-reasoning-on-mmmu | Qwen2.5-Omni-7B | #64 | Accuracy: 59.2 |
| code-generation-on-humaneval | Qwen2.5-Omni-7B | #65 | Pass@1: 78.7 |
| vision-language-understanding-on-mmstar | Qwen2.5-Omni-7B | #68 | Accuracy: 64.0 |
| multimodal-reasoning-on-mathvista | Qwen2.5-Omni-7B | #74 | Accuracy: 67.9 |
| arithmetic-reasoning-on-gsm8k | Qwen2.5-Omni-7B | #88 | Accuracy: 88.7 |
| multi-task-language-understanding-on-mmlu-pro | Qwen2.5-Omni-7B | #121 | Accuracy: 47.0 |
| audio-understanding-reasoning-on-mmau | Qwen2.5-Omni (8.2B) | – | Accuracy (Avg, Test-mini): 71.50 |