| spatial-reasoning-on-embspatial-bench | Qwen-VL-Max | #2 | Generation: 49.11 |
| visual-question-answering-vqa-on-core-mm | Qwen-VL-Chat | #3 | Overall score: 37.39Deductive: 37.55Abductive: 44.39… |
| fs-mevqa-on-sme | Qwen-VL-Max | #4 | BLEU-4: 24.30METEOR: 23.40ROUGE-L: 34.52CIDEr: 201.47… |
| mmr-total-on-mrr-benchmark | Qwen-vl-max | #4 | Total Column Score: 366 |
| mmr-total-on-mrr-benchmark | Qwen-vl-plus | #6 | Total Column Score: 310 |
| visual-grounding-on-refcoco-val | Qwen-VL | #5 | Accuracy: 89.36 |
| visual-question-answering-on-vip-bench | Qwen-VL-Chat (Coordinates) | #6 | GPT-4 score (bbox): 45.3 |
| visual-question-answering-on-vip-bench | Qwen-VL-Chat (Visual Prompt) | #9 | GPT-4 score (bbox): 39.2GPT-4 score (human): 41.7 |
| visual-question-answering-on-mm-vet-v2 | Qwen-VL-Max | #8 | GPT-4 score: 55.8±0.2 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | Qwen-VL | #17 | Accuracy: 86.02 |
| visual-question-answering-on-mm-vet | Qwen-VL-Max | #19 | GPT-4 score: 66.6±0.5 |
| visual-question-answering-on-mm-vet | Qwen-VL-Plus | #41 | GPT-4 score: 61.1±0.2 |
| visual-question-answering-vqa-on-mme | Qwen-VL-Chat | #21 | Score: 1848.29 |
| natural-language-visual-grounding-on-screenspot | Qwen-VL | #34 | Accuracy (%): 5.2 |
| visual-question-answering-on-docvqa-test | Qwen-VL-Plus | #41 | ANLS: 0.9024 |
| visual-question-answering-on-docvqa-test | Qwen-VL | #85 | ANLS: 0.651 |
| visual-question-answering-on-docvqa-test | Qwen-VL-Chat | #87 | ANLS: 0.626 |
| chart-question-answering-on-chartqa | Qwen-VL-Chat | #102 | 1:1 Accuracy: 66.3 |
| chart-question-answering-on-chartqa | Qwen-VL | #104 | 1:1 Accuracy: 65.7 |