Chart Question Answering On Chartqa
المقاييس
1:1 Accuracy
النتائج
نتائج أداء النماذج المختلفة على هذا المعيار القياسي
جدول المقارنة
| اسم النموذج | 1:1 Accuracy |
|---|---|
| pali-3-vision-language-models-smaller-faster | 69.5 |
| deplot-one-shot-visual-language-reasoning-by | 42.3 |
| matcha-enhancing-visual-language-pretraining | 64.2 |
| unichart-a-universal-vision-language | 66.24 |
| pali-x-on-scaling-up-a-multilingual-vision | 70.9 |
| deplot-one-shot-visual-language-reasoning-by | 36.9 |
| chartqa-a-benchmark-for-question-answering | 45.5 |
| pix2struct-screenshot-parsing-as-pretraining | 58.6 |
| gemini-a-family-of-highly-capable-multimodal-1 | 80.8 |
| structchart-perception-structuring-reasoning | 60.7 |
| omni-smola-boosting-generalist-multimodal | 73.8 |
| qwen-vl-a-frontier-large-vision-language | 65.7 |
| omni-smola-boosting-generalist-multimodal | 74.6 |
| screenai-a-vision-language-model-for-ui-and | 76.7 |
| chart-based-reasoning-transferring | 81.3 |
| deplot-one-shot-visual-language-reasoning-by | 76.7 |
| pali-x-on-scaling-up-a-multilingual-vision | 70.6 |
| deplot-one-shot-visual-language-reasoning-by | 67.3 |
| pali-3-vision-language-models-smaller-faster | 70 |
| pix2struct-screenshot-parsing-as-pretraining | 56.0 |
| pali-x-on-scaling-up-a-multilingual-vision | 72.3 |
| deplot-one-shot-visual-language-reasoning-by | 79.3 |
| qwen-vl-a-frontier-large-vision-language | 66.3 |
| deplot-one-shot-visual-language-reasoning-by | 70.5 |
| structchart-perception-structuring-reasoning | 65.3 |
| chart-based-reasoning-transferring | 77.3 |
| synthesize-step-by-step-tools-templates-and-1 | 72.64 |