{"Model": "Nano-Banana-Pro", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 76.7, "easy": 93.7}, "AverageByDimension": {"hard": 76.7, "easy": 93.7}, "by_domain": {"Slides": {"hard": 82.2, "easy": 94.8}, "Webpage": {"hard": 77.5, "easy": 96.5}, "Poster": {"hard": 76.5, "easy": 94.8}, "Chart": {"hard": 73.0, "easy": 92.2}, "Scientific Figure": {"hard": 74.2, "easy": 90.0}}, "by_dimension": {"Layout": {"hard": 72.2, "easy": 91.2}, "Attribute": {"hard": 65.6, "easy": 92.2}, "Text": {"hard": 86.4, "easy": 95.0}, "Knowledge": {"hard": 82.6, "easy": 96.2}}} {"Model": "Nano-Banana-2.0", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 68.5, "easy": 92.5}, "AverageByDimension": {"hard": 68.5, "easy": 92.5}, "by_domain": {"Slides": {"hard": 73.8, "easy": 95.8}, "Webpage": {"hard": 71.2, "easy": 94.5}, "Poster": {"hard": 67.5, "easy": 91.2}, "Chart": {"hard": 60.2, "easy": 89.2}, "Scientific Figure": {"hard": 69.5, "easy": 92.0}}, "by_dimension": {"Layout": {"hard": 68.4, "easy": 91.0}, "Attribute": {"hard": 57.4, "easy": 91.6}, "Text": {"hard": 83.4, "easy": 94.6}, "Knowledge": {"hard": 64.6, "easy": 93.0}}} {"Model": "Seedream-5.0", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 48.8, "easy": 79.2}, "AverageByDimension": {"hard": 48.8, "easy": 79.2}, "by_domain": {"Slides": {"hard": 54.5, "easy": 80.8}, "Webpage": {"hard": 47.0, "easy": 80.8}, "Poster": {"hard": 50.7, "easy": 77.0}, "Chart": {"hard": 46.0, "easy": 76.2}, "Scientific Figure": {"hard": 45.8, "easy": 81.5}}, "by_dimension": {"Layout": {"hard": 67.6, "easy": 89.0}, "Attribute": {"hard": 42.4, "easy": 77.2}, "Text": {"hard": 43.4, "easy": 75.6}, "Knowledge": {"hard": 41.8, "easy": 75.2}}} {"Model": "GPT-Image-1.5", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 35.9, "easy": 81.6}, "AverageByDimension": {"hard": 35.9, "easy": 81.6}, "by_domain": {"Slides": {"hard": 40.8, "easy": 89.2}, "Webpage": {"hard": 41.0, "easy": 86.0}, "Poster": {"hard": 42.0, "easy": 83.5}, "Chart": {"hard": 28.2, "easy": 76.5}, "Scientific Figure": {"hard": 27.8, "easy": 72.8}}, "by_dimension": {"Layout": {"hard": 51.6, "easy": 84.8}, "Attribute": {"hard": 25.8, "easy": 75.2}, "Text": {"hard": 40.4, "easy": 82.8}, "Knowledge": {"hard": 26.0, "easy": 83.6}}} {"Model": "Seedream-4.5", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 30.1, "easy": 66.2}, "AverageByDimension": {"hard": 30.1, "easy": 66.2}, "by_domain": {"Slides": {"hard": 33.8, "easy": 71.0}, "Webpage": {"hard": 36.2, "easy": 75.5}, "Poster": {"hard": 35.5, "easy": 72.2}, "Chart": {"hard": 18.0, "easy": 47.8}, "Scientific Figure": {"hard": 27.3, "easy": 64.8}}, "by_dimension": {"Layout": {"hard": 35.4, "easy": 71.6}, "Attribute": {"hard": 22.4, "easy": 62.8}, "Text": {"hard": 41.4, "easy": 72.4}, "Knowledge": {"hard": 21.4, "easy": 58.2}}} {"Model": "Wan2.6-T2I", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 21.9, "easy": 58.7}, "AverageByDimension": {"hard": 21.9, "easy": 58.7}, "by_domain": {"Slides": {"hard": 27.1, "easy": 56.5}, "Webpage": {"hard": 25.5, "easy": 67.0}, "Poster": {"hard": 27.5, "easy": 62.5}, "Chart": {"hard": 17.2, "easy": 48.8}, "Scientific Figure": {"hard": 12.5, "easy": 58.8}}, "by_dimension": {"Layout": {"hard": 46.4, "easy": 80.6}, "Attribute": {"hard": 16.6, "easy": 60.6}, "Text": {"hard": 12.6, "easy": 52.6}, "Knowledge": {"hard": 12.2, "easy": 41.0}}} {"Model": "Seedream-4.0", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 14.3, "easy": 60.1}, "AverageByDimension": {"hard": 14.3, "easy": 60.1}, "by_domain": {"Slides": {"hard": 18.5, "easy": 67.8}, "Webpage": {"hard": 19.2, "easy": 71.8}, "Poster": {"hard": 18.8, "easy": 65.5}, "Chart": {"hard": 7.8, "easy": 46.0}, "Scientific Figure": {"hard": 7.2, "easy": 49.2}}, "by_dimension": {"Layout": {"hard": 27.6, "easy": 73.4}, "Attribute": {"hard": 11.4, "easy": 59.2}, "Text": {"hard": 11.4, "easy": 52.8}, "Knowledge": {"hard": 6.8, "easy": 54.8}}} {"Model": "Emu3.5", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 13.2, "easy": 40.2}, "AverageByDimension": {"hard": 13.2, "easy": 40.2}, "by_domain": {"Slides": {"hard": 14.5, "easy": 44.8}, "Webpage": {"hard": 20.0, "easy": 48.8}, "Poster": {"hard": 20.3, "easy": 53.0}, "Chart": {"hard": 4.8, "easy": 20.3}, "Scientific Figure": {"hard": 6.5, "easy": 34.0}}, "by_dimension": {"Layout": {"hard": 30.4, "easy": 63.4}, "Attribute": {"hard": 14.2, "easy": 52.6}, "Text": {"hard": 7.0, "easy": 33.6}, "Knowledge": {"hard": 1.2, "easy": 11.0}}} {"Model": "HunyuanImage-3.0", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 13.0, "easy": 40.1}, "AverageByDimension": {"hard": 13.0, "easy": 40.1}, "by_domain": {"Slides": {"hard": 19.3, "easy": 47.0}, "Webpage": {"hard": 21.0, "easy": 52.0}, "Poster": {"hard": 19.8, "easy": 53.5}, "Chart": {"hard": 2.0, "easy": 18.8}, "Scientific Figure": {"hard": 2.8, "easy": 29.0}}, "by_dimension": {"Layout": {"hard": 27.8, "easy": 65.0}, "Attribute": {"hard": 13.8, "easy": 53.6}, "Text": {"hard": 10.2, "easy": 39.6}, "Knowledge": {"hard": 0.0, "easy": 2.0}}} {"Model": "GPT-Image-1.0", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 11.2, "easy": 52.4}, "AverageByDimension": {"hard": 11.2, "easy": 52.4}, "by_domain": {"Slides": {"hard": 18.2, "easy": 64.8}, "Webpage": {"hard": 12.0, "easy": 63.0}, "Poster": {"hard": 17.2, "easy": 64.8}, "Chart": {"hard": 3.2, "easy": 31.2}, "Scientific Figure": {"hard": 5.0, "easy": 38.5}}, "by_dimension": {"Layout": {"hard": 21.4, "easy": 60.2}, "Attribute": {"hard": 6.8, "easy": 48.6}, "Text": {"hard": 8.6, "easy": 41.0}, "Knowledge": {"hard": 7.8, "easy": 60.0}}} {"Model": "HunyuanImage-2.1", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 8.6, "easy": 27.7}, "AverageByDimension": {"hard": 8.6, "easy": 27.7}, "by_domain": {"Slides": {"hard": 11.0, "easy": 36.2}, "Webpage": {"hard": 16.5, "easy": 40.0}, "Poster": {"hard": 11.8, "easy": 39.0}, "Chart": {"hard": 1.2, "easy": 8.0}, "Scientific Figure": {"hard": 2.2, "easy": 15.0}}, "by_dimension": {"Layout": {"hard": 29.0, "easy": 68.4}, "Attribute": {"hard": 5.2, "easy": 39.8}, "Text": {"hard": 0.0, "easy": 1.4}, "Knowledge": {"hard": 0.0, "easy": 1.0}}} {"Model": "Z-Image", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 8.2, "easy": 43.8}, "AverageByDimension": {"hard": 8.2, "easy": 43.8}, "by_domain": {"Slides": {"hard": 12.2, "easy": 43.8}, "Webpage": {"hard": 6.2, "easy": 48.5}, "Poster": {"hard": 12.0, "easy": 50.0}, "Chart": {"hard": 8.8, "easy": 30.5}, "Scientific Figure": {"hard": 1.8, "easy": 46.0}}, "by_dimension": {"Layout": {"hard": 26.8, "easy": 69.2}, "Attribute": {"hard": 2.6, "easy": 47.6}, "Text": {"hard": 2.8, "easy": 45.0}, "Knowledge": {"hard": 0.6, "easy": 13.2}}} {"Model": "Qwen-Image-2512", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 6.3, "easy": 41.0}, "AverageByDimension": {"hard": 6.3, "easy": 41.0}, "by_domain": {"Slides": {"hard": 10.2, "easy": 45.0}, "Webpage": {"hard": 7.2, "easy": 48.0}, "Poster": {"hard": 11.5, "easy": 47.0}, "Chart": {"hard": 2.2, "easy": 28.0}, "Scientific Figure": {"hard": 0.2, "easy": 37.0}}, "by_dimension": {"Layout": {"hard": 22.2, "easy": 70.6}, "Attribute": {"hard": 1.2, "easy": 47.8}, "Text": {"hard": 1.8, "easy": 39.2}, "Knowledge": {"hard": 0.0, "easy": 6.4}}} {"Model": "FLUX.2-dev", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 4.9, "easy": 42.0}, "AverageByDimension": {"hard": 4.9, "easy": 42.0}, "by_domain": {"Slides": {"hard": 5.5, "easy": 43.2}, "Webpage": {"hard": 5.5, "easy": 48.8}, "Poster": {"hard": 7.2, "easy": 48.2}, "Chart": {"hard": 5.5, "easy": 33.5}, "Scientific Figure": {"hard": 0.5, "easy": 36.5}}, "by_dimension": {"Layout": {"hard": 17.2, "easy": 67.8}, "Attribute": {"hard": 1.2, "easy": 49.2}, "Text": {"hard": 1.0, "easy": 43.0}, "Knowledge": {"hard": 0.0, "easy": 8.2}}} {"Model": "Z-Image-Turbo", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 3.4, "easy": 32.4}, "AverageByDimension": {"hard": 3.4, "easy": 32.4}, "by_domain": {"Slides": {"hard": 7.0, "easy": 36.5}, "Webpage": {"hard": 4.5, "easy": 45.8}, "Poster": {"hard": 4.8, "easy": 40.8}, "Chart": {"hard": 0.8, "easy": 15.5}, "Scientific Figure": {"hard": 0.0, "easy": 23.2}}, "by_dimension": {"Layout": {"hard": 11.0, "easy": 60.6}, "Attribute": {"hard": 1.2, "easy": 35.0}, "Text": {"hard": 1.2, "easy": 29.8}, "Knowledge": {"hard": 0.2, "easy": 4.0}}} {"Model": "Qwen-Image", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 2.8, "easy": 23.8}, "AverageByDimension": {"hard": 2.8, "easy": 23.8}, "by_domain": {"Slides": {"hard": 3.5, "easy": 28.5}, "Webpage": {"hard": 2.5, "easy": 27.5}, "Poster": {"hard": 5.8, "easy": 32.2}, "Chart": {"hard": 2.2, "easy": 15.8}, "Scientific Figure": {"hard": 0.0, "easy": 15.2}}, "by_dimension": {"Layout": {"hard": 10.4, "easy": 51.2}, "Attribute": {"hard": 0.2, "easy": 22.2}, "Text": {"hard": 0.6, "easy": 17.6}, "Knowledge": {"hard": 0.0, "easy": 4.4}}} {"Model": "FLUX.2-Pro", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 1.6, "easy": 21.1}, "AverageByDimension": {"hard": 1.6, "easy": 21.1}, "by_domain": {"Slides": {"hard": 1.8, "easy": 23.0}, "Webpage": {"hard": 2.0, "easy": 27.0}, "Poster": {"hard": 2.8, "easy": 26.2}, "Chart": {"hard": 1.3, "easy": 14.7}, "Scientific Figure": {"hard": 0.0, "easy": 14.3}}, "by_dimension": {"Layout": {"hard": 6.1, "easy": 36.2}, "Attribute": {"hard": 0.0, "easy": 22.9}, "Text": {"hard": 0.0, "easy": 13.7}, "Knowledge": {"hard": 0.2, "easy": 11.7}}} {"Model": "GLM-Image", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 1.4, "easy": 15.3}, "AverageByDimension": {"hard": 1.4, "easy": 15.3}, "by_domain": {"Slides": {"hard": 1.5, "easy": 22.8}, "Webpage": {"hard": 1.8, "easy": 27.3}, "Poster": {"hard": 3.8, "easy": 24.8}, "Chart": {"hard": 0.0, "easy": 0.5}, "Scientific Figure": {"hard": 0.0, "easy": 1.5}}, "by_dimension": {"Layout": {"hard": 5.4, "easy": 43.2}, "Attribute": {"hard": 0.0, "easy": 13.4}, "Text": {"hard": 0.2, "easy": 4.4}, "Knowledge": {"hard": 0.0, "easy": 0.4}}} {"Model": "Imagen-4", "SourceType": "closed", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 1.1, "easy": 10.7}, "AverageByDimension": {"hard": 1.1, "easy": 10.7}, "by_domain": {"Slides": {"hard": 1.5, "easy": 15.0}, "Webpage": {"hard": 0.5, "easy": 14.8}, "Poster": {"hard": 1.8, "easy": 12.8}, "Chart": {"hard": 1.5, "easy": 6.8}, "Scientific Figure": {"hard": 0.2, "easy": 4.3}}, "by_dimension": {"Layout": {"hard": 4.2, "easy": 26.8}, "Attribute": {"hard": 0.0, "easy": 8.7}, "Text": {"hard": 0.2, "easy": 4.0}, "Knowledge": {"hard": 0.0, "easy": 3.4}}} {"Model": "LongCat-Image", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.7, "easy": 12.0}, "AverageByDimension": {"hard": 0.7, "easy": 13.0}, "by_domain": {"Slides": {"hard": 0.8, "easy": 15.0}, "Webpage": {"hard": 1.8, "easy": 22.3}, "Poster": {"hard": 0.8, "easy": 21.3}, "Chart": {"hard": 0.0, "easy": 2.5}, "Scientific Figure": {"hard": 0.0, "easy": 3.8}}, "by_dimension": {"Layout": {"hard": 2.4, "easy": 35.8}, "Attribute": {"hard": 0.2, "easy": 11.6}, "Text": {"hard": 0.0, "easy": 4.4}, "Knowledge": {"hard": 0.0, "easy": 0.0}}} {"Model": "X-Omni-EN", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.5, "easy": 9.4}, "AverageByDimension": {"hard": 0.5, "easy": 9.4}, "by_domain": {"Slides": {"hard": 0.8, "easy": 9.0}, "Webpage": {"hard": 0.2, "easy": 14.2}, "Poster": {"hard": 1.5, "easy": 15.8}, "Chart": {"hard": 0.0, "easy": 6.5}, "Scientific Figure": {"hard": 0.0, "easy": 1.8}}, "by_dimension": {"Layout": {"hard": 2.0, "easy": 22.8}, "Attribute": {"hard": 0.0, "easy": 5.6}, "Text": {"hard": 0.0, "easy": 8.0}, "Knowledge": {"hard": 0.0, "easy": 1.4}}} {"Model": "SD3.5-Large", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.5, "easy": 2.1}, "AverageByDimension": {"hard": 0.5, "easy": 2.1}, "by_domain": {"Slides": {"hard": 0.0, "easy": 0.5}, "Webpage": {"hard": 0.2, "easy": 2.2}, "Poster": {"hard": 0.0, "easy": 2.8}, "Chart": {"hard": 1.2, "easy": 3.2}, "Scientific Figure": {"hard": 1.2, "easy": 1.5}}, "by_dimension": {"Layout": {"hard": 2.2, "easy": 6.6}, "Attribute": {"hard": 0.0, "easy": 0.4}, "Text": {"hard": 0.0, "easy": 0.0}, "Knowledge": {"hard": 0.0, "easy": 1.2}}} {"Model": "Bagel", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.3, "easy": 3.7}, "AverageByDimension": {"hard": 0.2, "easy": 3.7}, "by_domain": {"Slides": {"hard": 0.3, "easy": 4.8}, "Webpage": {"hard": 0.0, "easy": 5.0}, "Poster": {"hard": 0.5, "easy": 8.5}, "Chart": {"hard": 0.0, "easy": 0.0}, "Scientific Figure": {"hard": 0.0, "easy": 0.0}}, "by_dimension": {"Layout": {"hard": 0.6, "easy": 12.8}, "Attribute": {"hard": 0.0, "easy": 1.6}, "Text": {"hard": 0.0, "easy": 0.0}, "Knowledge": {"hard": 0.0, "easy": 0.2}}} {"Model": "FLUX.1-Krea-dev", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.1, "easy": 5.1}, "AverageByDimension": {"hard": 0.1, "easy": 5.1}, "by_domain": {"Slides": {"hard": 0.0, "easy": 4.8}, "Webpage": {"hard": 0.0, "easy": 8.5}, "Poster": {"hard": 0.2, "easy": 11.8}, "Chart": {"hard": 0.0, "easy": 0.8}, "Scientific Figure": {"hard": 0.0, "easy": 0.0}}, "by_dimension": {"Layout": {"hard": 0.2, "easy": 17.8}, "Attribute": {"hard": 0.0, "easy": 2.8}, "Text": {"hard": 0.0, "easy": 0.0}, "Knowledge": {"hard": 0.0, "easy": 0.0}}} {"Model": "FLUX.1-dev", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.1, "easy": 5.0}, "AverageByDimension": {"hard": 0.1, "easy": 5.0}, "by_domain": {"Slides": {"hard": 0.0, "easy": 6.0}, "Webpage": {"hard": 0.0, "easy": 11.0}, "Poster": {"hard": 0.5, "easy": 7.8}, "Chart": {"hard": 0.0, "easy": 0.2}, "Scientific Figure": {"hard": 0.0, "easy": 0.0}}, "by_dimension": {"Layout": {"hard": 0.4, "easy": 15.8}, "Attribute": {"hard": 0.0, "easy": 2.8}, "Text": {"hard": 0.0, "easy": 0.0}, "Knowledge": {"hard": 0.0, "easy": 1.4}}} {"Model": "FLUX.1-schnell", "SourceType": "open", "PaperLink": "https://arxiv.org/abs/2603.25732", "AverageByDomain": {"hard": 0.0, "easy": 5.1}, "AverageByDimension": {"hard": 0.0, "easy": 5.1}, "by_domain": {"Slides": {"hard": 0.0, "easy": 8.5}, "Webpage": {"hard": 0.0, "easy": 8.2}, "Poster": {"hard": 0.0, "easy": 8.2}, "Chart": {"hard": 0.0, "easy": 0.8}, "Scientific Figure": {"hard": 0.0, "easy": 0.0}}, "by_dimension": {"Layout": {"hard": 0.0, "easy": 16.8}, "Attribute": {"hard": 0.0, "easy": 2.6}, "Text": {"hard": 0.0, "easy": 0.0}, "Knowledge": {"hard": 0.0, "easy": 1.2}}}