{ "leaderboard": [ { "model": "wan2.5-t2i-preview", "link": "https://help.aliyun.com/zh/model-studio/text-to-image-v2-api-reference", "hf": "-", "open_source": false, "release_date": "2025-09", "Overall": 84.24, "Style": 98.00, "World Knowledge": 94.30, "Attribute-Overall": 90.49, "Quantity": 83.51, "Expression": 80.90, "Material": 91.77, "Size": 91.41, "Shape": 87.24, "Color": 94.59, "Action-Overall": 78.39, "Hand": 72.12, "Full body": 78.16, "Animal": 83.82, "Non Contact": 74.55, "Contact": 75.29, "State": 80.85, "Relationship-Overall": 86.64, "Composition": 85.59, "Similarity": 77.56, "Inclusion": 91.95, "Comparison": 91.02, "Compound-Overall": 85.13, "Imagination": 86.18, "Feature matching": 82.78, "Grammar-Overall": 80.08, "Pronoun Reference": 91.67, "Consistency": 79.37, "Negation": 70.42, "Layout-Overall": 88.54, "2D": 89.91, "3D": 86.78, "Logical Reasoning": 74.51, "Text": 66.30 }, { "model": "Emu3", "link": "https://arxiv.org/pdf/2409.18869", "hf": "https://huggingface.co/BAAI/Emu3-Gen", "open_source": true, "release_date": "2024-09", "Overall": 35.95, "Style": 75.08, "World Knowledge": 53.03, "Attribute-Overall": 48.82, "Quantity": 23.40, "Expression": 38.33, "Material": 49.17, "Size": 57.77, "Shape": 36.19, "Color": 56.34, "Action-Overall": 27.81, "Hand": 10.58, "Full body": 22.81, "Animal": 25.36, "Non Contact": 12.05, "Contact": 17.53, "State": 42.39, "Relationship-Overall": 32.06, "Composition": 33.29, "Similarity": 29.17, "Inclusion": 35.06, "Comparison": 29.37, "Compound-Overall": 28.49, "Imagination": 33.02, "Feature matching": 18.46, "Grammar-Overall": 38.32, "Pronoun Reference": 42.86, "Consistency": 26.59, "Negation": 44.72, "Layout-Overall": 35.40, "2D": 30.37, "3D": 41.85, "Logical Reasoning": 19.66, "Text": 0.82 }, { "model": "UniWorld-V1", "link": "https://arxiv.org/pdf/2506.03147", "hf": "https://huggingface.co/LanguageBind/UniWorld-V1", "open_source": true, "release_date": "2025-06", "Overall": 21.50, "Style": 55.48, "World Knowledge": 17.34, "Attribute-Overall": 27.50, "Quantity": 12.23, "Expression": 30.28, "Material": 19.80, "Size": 27.27, "Shape": 19.76, "Color": 35.69, "Action-Overall": 19.34, "Hand": 12.18, "Full body": 20.31, "Animal": 23.19, "Non Contact": 9.38, "Contact": 8.05, "State": 26.28, "Relationship-Overall": 19.34, "Composition": 16.20, "Similarity": 21.47, "Inclusion": 23.56, "Comparison": 20.15, "Compound-Overall": 12.50, "Imagination": 15.30, "Feature matching": 6.31, "Grammar-Overall": 28.68, "Pronoun Reference": 23.81, "Consistency": 21.03, "Negation": 39.79, "Layout-Overall": 24.44, "2D": 24.15, "3D": 24.82, "Logical Reasoning": 8.98, "Text": 1.36 }, { "model": "Echo-4o", "link": "https://arxiv.org/pdf/2508.09987", "hf": "https://huggingface.co/Yejy53/Echo-4o", "open_source": true, "release_date": "2025-8", "Overall": 78.31, "Style": 96.26, "World Knowledge": 91.18, "Attribute-Overall": 91.82, "Quantity": 71.81, "Expression": 82.22, "Material": 94.50, "Size": 90.72, "Shape": 88.64, "Color": 96.80, "Action-Overall": 75.56, "Hand": 73.72, "Full body": 81.56, "Animal": 74.28, "Non Contact": 67.41, "Contact": 66.38, "State": 79.55, "Relationship-Overall": 85.83, "Composition": 86.99, "Similarity": 81.09, "Inclusion": 89.08, "Comparison": 84.47, "Compound-Overall": 85.25, "Imagination": 86.08, "Feature matching": 83.41, "Grammar-Overall": 83.50, "Pronoun Reference": 87.70, "Consistency": 83.73, "Negation": 79.58, "Layout-Overall": 88.10, "2D": 90.54, "3D": 84.96, "Logical Reasoning": 72.57, "Text": 13.04 }, { "model": "Lumina-DiMOO", "link": "https://synbol.github.io/Lumina-DiMOO/", "hf": "https://huggingface.co/Alpha-VLLM/Lumina-DiMOO", "open_source": true, "release_date": "2025-09", "Overall": 63.80, "Style": 84.30, "World Knowledge": 76.45, "Attribute-Overall": 79.41, "Quantity": 64.36, "Expression": 68.06, "Material": 77.18, "Size": 82.01, "Shape": 72.73, "Color": 88.00, "Action-Overall": 61.32, "Hand": 54.81, "Full body": 57.50, "Animal": 61.96, "Non Contact": 60.27, "Contact": 49.43, "State": 68.68, "Relationship-Overall": 66.70, "Composition": 62.24, "Similarity": 61.22, "Inclusion": 78.74, "Comparison": 69.17, "Compound-Overall": 68.90, "Imagination": 72.57, "Feature matching": 60.75, "Grammar-Overall": 71.95, "Pronoun Reference": 76.98, "Consistency": 67.06, "Negation": 71.83, "Layout-Overall": 78.33, "2D": 84.18, "3D": 70.83, "Logical Reasoning": 49.27, "Text": 1.36 }, { "model": "MMaDA", "link": "https://arxiv.org/pdf/2505.15809", "hf": "https://huggingface.co/Gen-Verse/MMaDA-8B-MixCoT", "open_source": true, "release_date": "2025-05", "Overall": 50.61, "Style": 84.05, "World Knowledge": 63.58, "Attribute-Overall": 61.31, "Quantity": 46.81, "Expression": 40.00, "Material": 58.96, "Size": 67.80, "Shape": 52.62, "Color": 73.22, "Action-Overall": 42.98, "Hand": 23.40, "Full body": 39.06, "Animal": 40.58, "Non Contact": 29.02, "Contact": 30.75, "State": 58.20, "Relationship-Overall": 52.69, "Composition": 48.09, "Similarity": 49.04, "Inclusion": 60.63, "Comparison": 57.52, "Compound-Overall": 50.07, "Imagination": 56.65, "Feature matching": 35.51, "Grammar-Overall": 58.76, "Pronoun Reference": 61.11, "Consistency": 50.79, "Negation": 63.73, "Layout-Overall": 60.63, "2D": 65.54, "3D": 54.35, "Logical Reasoning": 31.80, "Text": 0.27 }, { "model": "OmniGen2", "link": "https://arxiv.org/pdf/2506.18871", "hf": "https://huggingface.co/OmniGen2/OmniGen2", "open_source": true, "release_date": "2025-06", "Overall": 70.75, "Style": 95.35, "World Knowledge": 87.57, "Attribute-Overall": 85.05, "Quantity": 74.47, "Expression": 73.33, "Material": 84.94, "Size": 85.23, "Shape": 79.90, "Color": 92.09, "Action-Overall": 67.17, "Hand": 63.46, "Full body": 67.81, "Animal": 63.41, "Non Contact": 63.39, "Contact": 60.34, "State": 72.33, "Relationship-Overall": 75.38, "Composition": 70.79, "Similarity": 70.51, "Inclusion": 87.64, "Comparison": 77.43, "Compound-Overall": 74.06, "Imagination": 76.05, "Feature matching": 69.63, "Grammar-Overall": 77.03, "Pronoun Reference": 85.71, "Consistency": 76.59, "Negation": 69.72, "Layout-Overall": 81.35, "2D": 84.89, "3D": 76.81, "Logical Reasoning": 62.62, "Text": 1.90 }, { "model": "OneCAT", "link": "https://arxiv.org/pdf/2509.03498", "hf": "https://huggingface.co/onecat-ai/OneCAT-3B", "open_source": true, "release_date": "2025-09", "Overall": 63.88, "Style": 95.85, "World Knowledge": 85.26, "Attribute-Overall": 74.79, "Quantity": 57.98, "Expression": 65.56, "Material": 78.92, "Size": 81.25, "Shape": 59.79, "Color": 79.77, "Action-Overall": 60.11, "Hand": 35.26, "Full body": 69.69, "Animal": 64.13, "Non Contact": 55.36, "Contact": 42.24, "State": 70.85, "Relationship-Overall": 65.03, "Composition": 63.65, "Similarity": 63.14, "Inclusion": 65.52, "Comparison": 68.69, "Compound-Overall": 62.35, "Imagination": 70.78, "Feature matching": 43.69, "Grammar-Overall": 63.07, "Pronoun Reference": 69.05, "Consistency": 63.49, "Negation": 57.39, "Layout-Overall": 75.79, "2D": 76.13, "3D": 75.36, "Logical Reasoning": 54.37, "Text": 2.17 }, { "model": "X-Omni", "link": "https://arxiv.org/pdf/2507.22058", "hf": "https://huggingface.co/X-Omni/X-Omni-Zh", "open_source": true, "release_date": "2025-08", "Overall": 62.18, "Style": 76.91, "World Knowledge": 74.13, "Attribute-Overall": 76.51, "Quantity": 72.34, "Expression": 59.72, "Material": 77.79, "Size": 82.20, "Shape": 67.83, "Color": 83.39, "Action-Overall": 58.43, "Hand": 50.00, "Full body": 61.56, "Animal": 61.96, "Non Contact": 49.55, "Contact": 42.82, "State": 66.40, "Relationship-Overall": 60.83, "Composition": 57.02, "Similarity": 55.45, "Inclusion": 65.52, "Comparison": 68.20, "Compound-Overall": 61.12, "Imagination": 65.51, "Feature matching": 51.40, "Grammar-Overall": 64.85, "Pronoun Reference": 76.19, "Consistency": 58.33, "Negation": 60.56, "Layout-Overall": 73.02, "2D": 76.84, "3D": 68.12, "Logical Reasoning": 46.60, "Text": 29.35 }, { "model": "Bagel", "link": "https://arxiv.org/pdf/2505.14683", "hf": "https://huggingface.co/ByteDance-Seed/BAGEL-7B-MoT", "open_source": true, "release_date": "2025-05", "Overall": 75.75, "Style": 96.10, "World Knowledge": 89.02, "Attribute-Overall": 88.25, "Quantity": 71.81, "Expression": 73.47, "Material": 88.93, "Size": 90.53, "Shape": 83.39, "Color": 95.81, "Action-Overall": 72.43, "Hand": 71.47, "Full body": 75.62, "Animal": 76.09, "Non Contact": 66.96, "Contact": 63.22, "State": 75.10, "Relationship-Overall": 81.52, "Composition": 80.87, "Similarity": 76.60, "Inclusion": 86.78, "Comparison": 82.04, "Compound-Overall": 82.05, "Imagination": 83.97, "Feature matching": 77.80, "Grammar-Overall": 81.09, "Pronoun Reference":84.92, "Consistency": 83.33, "Negation": 75.70, "Layout-Overall": 83.97, "2D": 87.29, "3D": 79.71, "Logical Reasoning": 68.69, "Text": 14.40 }, { "model": "HiDream-I1-Full", "link": "https://arxiv.org/pdf/2505.22705", "hf": "https://huggingface.co/HiDream-ai/HiDream-I1-Full", "open_source": true, "release_date": "2025-05", "Overall": 50.70, "Style": 83.06, "World Knowledge": 78.61, "Attribute-Overall": 65.05, "Quantity": 63.30, "Expression": 55.97, "Material": 62.50, "Size": 69.70, "Shape": 56.12, "Color": 71.80, "Action-Overall": 47.47, "Hand": 38.14, "Full body": 45.00, "Animal": 44.93, "Non Contact": 38.39, "Contact": 36.21, "State": 57.71, "Relationship-Overall": 49.25, "Composition": 46.30, "Similarity": 45.83, "Inclusion": 59.20, "Comparison": 49.03, "Compound-Overall": 42.08, "Imagination": 45.99, "Feature matching": 33.41, "Grammar-Overall": 53.81, "Pronoun Reference": 59.52, "Consistency": 49.60, "Negation": 52.46, "Layout-Overall": 60.40, "2D": 62.99, "3D": 57.07, "Logical Reasoning": 24.27, "Text": 2.99 }, { "model": "Hunyuan-Image-2.1", "link": "https://github.com/Tencent-Hunyuan/HunyuanImage-2.1", "hf": "https://huggingface.co/spaces/tencent/HunyuanImage-2.1", "open_source": true, "release_date": "2025-09", "Overall": 87.01, "Style": 95.18, "World Knowledge": 94.08, "Attribute-Overall": 93.82, "Quantity": 87.77, "Expression": 87.08, "Material": 95.41, "Size": 91.67, "Shape": 89.69, "Color": 97.69, "Action-Overall": 83.99, "Hand": 85.58, "Full body": 84.69, "Animal": 85.51, "Non Contact": 83.48, "Contact": 79.02, "State": 84.68, "Relationship-Overall": 88.09, "Composition": 87.88, "Similarity": 81.41, "Inclusion": 92.24, "Comparison": 90.05, "Compound-Overall": 85.61, "Imagination": 85.97, "Feature matching": 84.81, "Grammar-Overall": 80.08, "Pronoun Reference": 92.86, "Consistency": 83.33, "Negation": 65.85, "Layout-Overall": 91.43, "2D": 93.50, "3D": 88.77, "Logical Reasoning": 71.36, "Text": 86.41 }, { "model": "BLIP3-o", "link": "https://arxiv.org/pdf/2505.09568", "hf": "https://huggingface.co/BLIP3o/BLIP3o-NEXT-SFT-3B", "open_source": true, "release_date": "2025-08", "Overall": 59.25, "Style": 89.70, "World Knowledge": 77.17, "Attribute-Overall": 69.24, "Quantity": 53.19, "Expression": 59.03, "Material": 71.31, "Size": 79.36, "Shape": 54.02, "Color": 75.00, "Action-Overall": 55.98, "Hand": 42.63, "Full body": 59.38, "Animal": 60.87, "Non Contact": 45.98, "Contact": 43.97, "State": 64.03, "Relationship-Overall": 60.56, "Composition": 58.29, "Similarity": 54.81, "Inclusion": 60.63, "Comparison": 69.17, "Compound-Overall": 60.68, "Imagination": 67.72, "Feature matching": 45.09, "Grammar-Overall": 60.91, "Pronoun Reference": 72.22, "Consistency": 53.17, "Negation": 57.75, "Layout-Overall": 69.29, "2D": 72.60, "3D": 65.04, "Logical Reasoning": 47.09, "Text": 1.90 }, { "model": "BLIP3-o-Next", "link": "https://arxiv.org/pdf/2505.09568", "hf": "https://huggingface.co/BLIP3o/BLIP3o-NEXT-SFT-3B", "open_source": true, "release_date": "2025-08", "Overall": 54.55, "Style": 87.71, "World Knowledge": 61.85, "Attribute-Overall": 63.75, "Quantity": 50.00, "Expression": 64.58, "Material": 67.85, "Size": 67.61, "Shape": 55.94, "Color": 63.21, "Action-Overall": 51.81, "Hand": 37.50, "Full body": 56.25, "Animal": 50.72, "Non Contact": 45.98, "Contact": 37.36, "State": 61.36, "Relationship-Overall": 57.76, "Composition": 55.36, "Similarity": 53.53, "Inclusion": 60.34, "Comparison": 63.35, "Compound-Overall": 54.00, "Imagination": 59.49, "Feature matching": 41.82, "Grammar-Overall": 60.66, "Pronoun Reference": 65.48, "Consistency": 58.73, "Negation": 58.10, "Layout-Overall": 64.60, "2D": 67.80, "3D": 60.51, "Logical Reasoning": 41.50, "Text": 1.90 }, { "model": "Janus-flow", "link": "https://arxiv.org/pdf/2411.07975", "hf": "https://huggingface.co/deepseek-ai/JanusFlow-1.3B", "open_source": true, "release_date": "2024-11", "Overall": 23.01, "Style": 57.39, "World Knowledge": 17.49, "Attribute-Overall": 23.42, "Quantity": 11.70, "Expression": 11.39, "Material": 23.72, "Size": 32.20, "Shape": 15.91, "Color": 28.72, "Action-Overall": 19.46, "Hand": 3.85, "Full body": 18.75, "Animal": 19.20, "Non Contact": 9.38, "Contact": 9.48, "State": 30.24, "Relationship-Overall": 20.04, "Composition": 18.62, "Similarity": 18.91, "Inclusion": 24.43, "Comparison": 19.90, "Compound-Overall": 21.58, "Imagination": 28.80, "Feature matching": 5.61, "Grammar-Overall": 32.23, "Pronoun Reference": 29.76, "Consistency": 13.89, "Negation": 50.70, "Layout-Overall": 21.59, "2D": 18.64, "3D": 25.36, "Logical Reasoning": 17.48, "Text": 0.27 }, { "model": "Janus", "link": "https://arxiv.org/pdf/2410.13848", "hf": "https://huggingface.co/deepseek-ai/Janus-1.3B", "open_source": true, "release_date": "2024-10", "Overall": 33.63, "Style": 75.00, "World Knowledge": 30.06, "Attribute-Overall": 35.98, "Quantity": 25.53, "Expression": 25.97, "Material": 39.16, "Size": 45.83, "Shape": 22.20, "Color": 39.99, "Action-Overall": 29.74, "Hand": 11.54, "Full body": 35.31, "Animal": 32.25, "Non Contact": 16.96, "Contact": 14.08, "State": 41.11, "Relationship-Overall": 28.23, "Composition": 26.02, "Similarity": 26.60, "Inclusion": 30.46, "Comparison": 31.80, "Compound-Overall": 31.47, "Imagination": 38.92, "Feature matching": 14.95, "Grammar-Overall": 44.04, "Pronoun Reference": 46.43, "Consistency": 24.60, "Negation": 59.15, "Layout-Overall": 40.56, "2D": 38.98, "3D": 42.57, "Logical Reasoning": 20.15, "Text": 1.09 }, { "model": "CogView4", "link": "https://arxiv.org/pdf/2403.05121", "hf": "https://huggingface.co/zai-org/CogView4-6B", "open_source": true, "release_date": "2024-03", "Overall": 68.09, "Style": 89.62, "World Knowledge": 89.31, "Attribute-Overall": 80.99, "Quantity": 73.40, "Expression": 65.69, "Material": 80.35, "Size": 85.98, "Shape": 73.43, "Color": 88.84, "Action-Overall": 67.94, "Hand": 67.31, "Full body": 68.75, "Animal": 71.01, "Non Contact": 58.04, "Contact": 63.79, "State": 70.65, "Relationship-Overall": 70.58, "Composition": 66.07, "Similarity": 64.10, "Inclusion": 80.17, "Comparison": 75.97, "Compound-Overall": 69.91, "Imagination": 71.94, "Feature matching": 65.42, "Grammar-Overall": 70.94, "Pronoun Reference": 83.33, "Consistency": 69.05, "Negation": 61.62, "Layout-Overall": 81.51, "2D": 77.72, "3D": 84.46, "Logical Reasoning": 51.94, "Text": 8.15 }, { "model": "Kolors", "link": "https://github.com/Kwai-Kolors/Kolors/blob/master/imgs/Kolors_paper.pdf", "hf": "https://huggingface.co/Kwai-Kolors/Kolors", "open_source": true, "release_date": "2024-7", "Overall": 65.12, "Style": 90.61, "World Knowledge": 87.14, "Attribute-Overall": 81.18, "Quantity": 63.83, "Expression": 64.86, "Material": 82.98, "Size": 83.52, "Shape": 70.80, "Color": 90.25, "Action-Overall": 64.49, "Hand": 58.97, "Full body": 57.19, "Animal": 63.41, "Non Contact": 65.18, "Contact": 50.57, "State": 73.42, "Relationship-Overall": 71.23, "Composition": 69.90, "Similarity": 74.68, "Inclusion": 74.43, "Comparison": 68.45, "Compound-Overall": 64.17, "Imagination": 67.83, "Feature matching": 56.07, "Grammar-Overall": 63.96, "Pronoun Reference": 81.35, "Consistency": 62.30, "Negation": 50.00, "Layout-Overall": 74.60, "2D": 72.46, "3D": 77.36, "Logical Reasoning": 47.82, "Text": 5.98 }, { "model": "Janus-Pro", "link": "https://arxiv.org/pdf/2501.17811", "hf": "https://huggingface.co/deepseek-ai/Janus-Pro-7B", "open_source": true, "release_date": "2025-01", "Overall": 60.21, "Style": 91.28, "World Knowledge": 75.87, "Attribute-Overall": 65.79, "Quantity": 44.15, "Expression": 52.92, "Material": 69.80, "Size": 78.22, "Shape": 56.99, "Color": 69.18, "Action-Overall": 54.33, "Hand": 37.82, "Full body": 51.25, "Animal": 63.04, "Non Contact": 48.21, "Contact": 51.72, "State": 60.28, "Relationship-Overall": 62.61, "Composition": 62.50, "Similarity": 57.05, "Inclusion": 66.38, "Comparison": 63.83, "Compound-Overall": 65.62, "Imagination": 72.47, "Feature matching": 50.47, "Grammar-Overall": 68.53, "Pronoun Reference": 72.22, "Consistency": 61.11, "Negation": 71.83, "Layout-Overall": 66.59, "2D": 66.38, "3D": 66.85, "Logical Reasoning": 49.27, "Text": 2.17 }, { "model": "Seedream-4.0", "link": "https://www.volcengine.com/docs/82379/1541523", "hf": "-", "open_source": false, "release_date": "2025-09", "Overall": 90.35, "Style": 98.42, "World Knowledge": 96.39, "Attribute-Overall": 95.54, "Quantity": 86.70, "Expression": 90.69, "Material": 96.08, "Size": 95.45, "Shape": 93.71, "Color": 98.43, "Action-Overall": 89.29, "Hand": 84.94, "Full body": 91.56, "Animal": 92.03, "Non Contact": 92.41, "Contact": 86.21, "State": 89.53, "Relationship-Overall": 88.69, "Composition": 86.35, "Similarity": 83.01, "Inclusion": 93.39, "Comparison": 93.45, "Compound-Overall": 87.72, "Imagination": 87.66, "Feature matching": 87.85, "Grammar-Overall": 83.63, "Pronoun Reference": 94.44, "Consistency": 82.14, "Negation": 75.35, "Layout-Overall": 91.90, "2D": 92.66, "3D": 90.94, "Logical Reasoning": 80.58, "Text": 91.30 }, { "model": "DALL-E-3", "link": "https://openai.com/zh-Hans-CN/index/dall-e-3/", "hf": "-", "open_source": false, "release_date": "2023-09", "Overall": 71.16, "Style": 95.85, "World Knowledge": 94.36, "Attribute-Overall": 85.41, "Quantity": 64.36, "Expression": 71.11, "Material": 88.93, "Size": 90.72, "Shape": 77.62, "Color": 91.30, "Action-Overall": 70.59, "Hand": 61.22, "Full body": 65.94, "Animal": 74.28, "Non Contact": 67.41, "Contact": 62.64, "State": 77.37, "Relationship-Overall": 80.12, "Composition": 81.63, "Similarity": 73.72, "Inclusion": 85.63, "Comparison": 77.43, "Compound-Overall": 75.87, "Imagination": 80.38, "Feature matching": 65.89, "Grammar-Overall": 70.81, "Pronoun Reference": 80.16, "Consistency": 74.21, "Negation": 59.51, "Layout-Overall": 73.33, "2D": 70.48, "3D": 76.99, "Logical Reasoning": 61.41, "Text": 3.80 }, { "model": "Qwen-Image", "link": "https://arxiv.org/pdf/2508.02324", "hf": "https://huggingface.co/Qwen/Qwen-Image", "open_source": true, "release_date": "2025-08", "Overall": 86.91, "Style": 97.84, "World Knowledge": 95.66, "Attribute-Overall": 95.04, "Quantity": 89.36, "Expression": 91.11, "Material": 96.23, "Size": 93.56, "Shape": 90.91, "Color": 97.90, "Action-Overall": 86.56, "Hand": 83.33, "Full body": 90.62, "Animal": 89.86, "Non Contact": 86.61, "Contact": 79.60, "State": 87.75, "Relationship-Overall": 87.61, "Composition": 85.59, "Similarity": 84.29, "Inclusion": 91.67, "Comparison": 90.53, "Compound-Overall": 82.99, "Imagination": 83.44, "Feature matching": 82.01, "Grammar-Overall": 76.90, "Pronoun Reference": 94.05, "Consistency": 83.73, "Negation": 55.63, "Layout-Overall": 90.48, "2D": 92.09, "3D": 88.41, "Logical Reasoning": 69.90, "Text": 86.14 }, { "model": "Imagen-4.0-generate-preview-06-06", "link": "https://deepmind.google/models/imagen/", "hf": "-", "open_source": false, "release_date": "2025-01", "Overall": 79.90, "Style": 95.60, "World Knowledge": 97.98, "Attribute-Overall": 90.94, "Quantity": 82.45, "Expression": 80.42, "Material": 92.24, "Size": 91.29, "Shape": 85.84, "Color": 96.28, "Action-Overall": 84.55, "Hand": 81.09, "Full body": 84.69, "Animal": 82.25, "Non Contact": 83.48, "Contact": 85.63, "State": 86.07, "Relationship-Overall": 88.04, "Composition": 87.24, "Similarity": 82.05, "Inclusion": 93.97, "Comparison": 89.08, "Compound-Overall": 86.63, "Imagination": 88.71, "Feature matching": 82.01, "Grammar-Overall": 82.74, "Pronoun Reference": 92.06, "Consistency": 81.75, "Negation": 75.35, "Layout-Overall": 90.48, "2D": 90.25, "3D": 90.76, "Logical Reasoning": 77.18, "Text": 4.89 }, { "model": "Recraft", "link": "https://www.recraft.ai/docs#generate-image", "hf": "-", "open_source": false, "release_date": "2024-12", "Overall": 56.90, "Style": 86.38, "World Knowledge": 85.55, "Attribute-Overall": 74.31, "Quantity": 61.70, "Expression": 60.56, "Material": 73.72, "Size": 79.92, "Shape": 65.03, "Color": 82.39, "Action-Overall": 54.65, "Hand": 44.23, "Full body": 57.81, "Animal": 60.87, "Non Contact": 42.86, "Contact": 43.39, "State": 61.66, "Relationship-Overall": 57.44, "Composition": 54.72, "Similarity": 49.68, "Inclusion": 63.22, "Comparison": 63.59, "Compound-Overall": 50.00, "Imagination": 50.95, "Feature matching": 47.90, "Grammar-Overall": 57.49, "Pronoun Reference": 71.83, "Consistency": 55.95, "Negation": 46.13, "Layout-Overall": 64.52, "2D": 64.12, "3D": 65.04, "Logical Reasoning": 36.17, "Text": 2.45 }, { "model": "Nano Banana", "link": "https://ainanobanana.io/", "hf": "-", "open_source": false, "release_date": "2025-08", "Overall": 83.17, "Style": 98.41, "World Knowledge": 97.38, "Attribute-Overall": 93.29, "Quantity": 90.37, "Expression": 85.06, "Material": 93.11, "Size": 94.29, "Shape": 87.99, "Color": 98.10, "Action-Overall": 85.55, "Hand": 84.42, "Full body": 88.09, "Animal": 84.06, "Non Contact": 87.05, "Contact": 82.90, "State": 86.07, "Relationship-Overall": 91.32, "Composition": 90.59, "Similarity": 86.50, "Inclusion": 96.83, "Comparison": 91.71, "Compound-Overall": 91.21, "Imagination": 92.14, "Feature matching": 89.13, "Grammar-Overall": 88.35, "Pronoun Reference": 94.78, "Consistency": 88.10, "Negation": 82.86, "Layout-Overall": 93.15, "2D": 93.19, "3D": 93.10, "Logical Reasoning": 82.40, "Text": 10.68 }, { "model": "GPT-4o", "link": "https://platform.openai.com/docs/guides/image-generation", "hf": "-", "open_source": false, "release_date": "2025-03", "Overall": 90.51, "Style": 99.41, "World Knowledge": 97.96, "Attribute-Overall": 94.72, "Quantity": 85.87, "Expression": 92.56, "Material": 94.43, "Size": 95.23, "Shape": 94.23, "Color": 96.59, "Action-Overall": 89.33, "Hand": 91.12, "Full body": 92.50, "Animal": 89.49, "Non Contact": 91.52, "Contact": 86.78, "State": 88.14, "Relationship-Overall": 92.59, "Composition": 91.93, "Similarity": 89.10, "Inclusion": 95.64, "Comparison": 93.93, "Compound-Overall": 94.59, "Imagination": 95.36, "Feature matching": 92.87, "Grammar-Overall": 94.11, "Pronoun Reference": 96.37, "Consistency": 92.86, "Negation": 93.24, "Layout-Overall": 95.21, "2D": 95.01, "3D": 95.47, "Logical Reasoning": 90.05, "Text": 57.14 }, { "model": "FLUX-kontext-max", "link": "https://bfl.ai/models/flux-kontext", "hf": "-", "open_source": false, "release_date": "2025-05", "Overall": 75.24, "Style": 97.59, "World Knowledge": 92.31, "Attribute-Overall": 86.17, "Quantity": 72.34, "Expression": 71.41, "Material": 87.48, "Size": 88.83, "Shape": 81.64, "Color": 92.80, "Action-Overall": 75.71, "Hand": 76.28, "Full body": 70.22, "Animal": 79.35, "Non Contact": 69.20, "Contact": 74.43, "State": 78.16, "Relationship-Overall": 81.27, "Composition": 78.95, "Similarity": 73.40, "Inclusion": 87.25, "Comparison": 86.65, "Compound-Overall": 80.16, "Imagination": 84.60, "Feature matching": 70.33, "Grammar-Overall": 78.77, "Pronoun Reference": 88.76, "Consistency": 76.19, "Negation": 72.24, "Layout-Overall": 87.58, "2D": 87.01, "3D": 88.32, "Logical Reasoning": 68.20, "Text": 4.62 }, { "model": "Hunyuan-DiT", "link": "https://arxiv.org/pdf/2405.08748", "hf": "https://huggingface.co/Tencent-Hunyuan/HunyuanDiT", "open_source": true, "release_date": "2024-05", "Overall": 55.57, "Style": 94.10, "World Knowledge": 76.16, "Attribute-Overall": 69.72, "Quantity": 66.49, "Expression": 54.03, "Material": 71.76, "Size": 76.14, "Shape": 58.57, "Color": 76.10, "Action-Overall": 51.04, "Hand": 41.03, "Full body": 51.56, "Animal": 57.25, "Non Contact": 41.52, "Contact": 37.36, "State": 59.09, "Relationship-Overall": 55.60, "Composition": 59.69, "Similarity": 48.08, "Inclusion": 56.90, "Comparison": 52.43, "Compound-Overall": 52.03, "Imagination": 57.49, "Feature matching": 39.95, "Grammar-Overall": 60.06, "Pronoun Reference": 63.49, "Consistency": 60.71, "Negation": 56.34, "Layout-Overall": 61.67, "2D": 60.73, "3D": 62.86, "Logical Reasoning": 33.98, "Text": 1.36 }, { "model": "Imagen-3.0-generate-002", "link": "https://arxiv.org/pdf/2408.07009", "hf": "-", "open_source": false, "release_date": "2025-02", "Overall": 0.98, "Style": 2.66, "World Knowledge": 0.29, "Attribute-Overall": 0.69, "Quantity": 0.00, "Expression": 0.00, "Material": 0.00, "Size": 1.52, "Shape": 0.35, "Color": 1.36, "Action-Overall": 0.60, "Hand": 0.00, "Full body": 0.31, "Animal": 0.00, "Non Contact": 0.00, "Contact": 0.00, "State": 1.38, "Relationship-Overall": 0.32, "Composition": 0.13, "Similarity": 0.64, "Inclusion": 0.00, "Comparison": 0.73, "Compound-Overall": 0.00, "Imagination": 0.00, "Feature matching": 0.00, "Grammar-Overall": 4.06, "Pronoun Reference": 0.79, "Consistency": 1.19, "Negation": 9.51, "Layout-Overall": 0.87, "2D": 1.55, "3D": 0.00, "Logical Reasoning": 0.00, "Text": 0.27 }, { "model": "wan2.2-t2i-plus", "link": "https://help.aliyun.com/zh/model-studio/text-to-image-v2-api-reference", "hf": "-", "open_source": false, "release_date": "2025-07", "Overall": 70.05, "Style": 91.61, "World Knowledge": 88.73, "Attribute-Overall": 82.42, "Quantity": 78.19, "Expression": 66.94, "Material": 82.15, "Size": 84.09, "Shape": 77.10, "Color": 89.99, "Action-Overall": 70.22, "Hand": 67.95, "Full body": 69.06, "Animal": 72.46, "Non Contact": 64.29, "Contact": 63.79, "State": 74.21, "Relationship-Overall": 73.65, "Composition": 70.15, "Similarity": 70.83, "Inclusion": 80.17, "Comparison": 76.94, "Compound-Overall": 71.51, "Imagination": 74.26, "Feature matching": 65.42, "Grammar-Overall": 70.05, "Pronoun Reference": 83.73, "Consistency": 62.70, "Negation": 64.44, "Layout-Overall": 80.08, "2D": 81.50, "3D": 78.26, "Logical Reasoning": 57.04, "Text": 15.22 }, { "model": "Imagen-4.0-Fast-preview-06-06", "link": "https://deepmind.google/models/imagen/", "hf": "-", "open_source": false, "release_date": "2025-01", "Overall": 1.20, "Style": 2.91, "World Knowledge": 0.00, "Attribute-Overall": 0.93, "Quantity": 0.00, "Expression": 2.08, "Material": 0.53, "Size": 0.00, "Shape": 1.22, "Color": 1.05, "Action-Overall": 0.44, "Hand": 0.32, "Full body": 0.00, "Animal": 0.00, "Non Contact": 0.00, "Contact": 0.00, "State": 0.99, "Relationship-Overall": 0.70, "Composition": 0.77, "Similarity": 0.96, "Inclusion": 0.57, "Comparison": 0.49, "Compound-Overall": 0.07, "Imagination": 0.11, "Feature matching": 0.00, "Grammar-Overall": 4.95, "Pronoun Reference": 0.79, "Consistency": 0.40, "Negation": 12.68, "Layout-Overall": 1.51, "2D": 2.54, "3D": 0.18, "Logical Reasoning": 0.24, "Text": 0.27 }, { "model": "Seedream-3.0", "link": "https://www.byteplus.com/en/product/Seedream", "hf": "-", "open_source": false, "release_date": "2025-06", "Overall": 86.14, "Style": 98.42, "World Knowledge": 95.36, "Attribute-Overall": 93.93, "Quantity": 85.64, "Expression": 83.98, "Material": 96.39, "Size": 90.53, "Shape": 93.36, "Color": 97.90, "Action-Overall": 84.53, "Hand": 81.41, "Full body": 89.06, "Animal": 86.13, "Non Contact": 85.71, "Contact": 79.19, "State": 85.18, "Relationship-Overall": 87.55, "Composition": 84.57, "Similarity": 83.01, "Inclusion": 93.10, "Comparison": 91.99, "Compound-Overall": 83.11, "Imagination": 83.83, "Feature matching": 81.54, "Grammar-Overall": 77.54, "Pronoun Reference": 88.89, "Consistency": 82.14, "Negation": 63.38, "Layout-Overall": 90.16, "2D": 90.68, "3D": 89.49, "Logical Reasoning": 68.45, "Text": 82.34 }, { "model": "Imagen-3.0-generate-002", "link": "https://arxiv.org/pdf/2408.07009", "hf": "-", "open_source": false, "release_date": "2025-02", "Overall": 71.85, "Style": 89.25, "World Knowledge": 94.75, "Attribute-Overall": 77.33, "Quantity": 75.78, "Expression": 64.67, "Material": 80.66, "Size": 82.84, "Shape": 70.00, "Color": 93.10, "Action-Overall": 81.46, "Hand": 80.00, "Full body": 83.89, "Animal": 85.29, "Non Contact": 77.37, "Contact": 74.40, "State": 87.38, "Relationship-Overall": 82.86, "Composition": 83.90, "Similarity": 73.33, "Inclusion": 88.64, "Comparison": 83.90, "Compound-Overall": 71.71, "Imagination": 79.23, "Feature matching": 64.06, "Grammar-Overall": 69.84, "Pronoun Reference": 79.04, "Consistency": 70.75, "Negation": 59.13, "Layout-Overall": 81.34, "2D": 82.72, "3D": 79.92, "Logical Reasoning": 48.36, "Text": 21.55 }, { "model": "Imagen-4.0-Ultra-preview-06-06", "link": "https://deepmind.google/models/imagen/", "hf": "-", "open_source": false, "release_date": "2025-06", "Overall": 83.86, "Style": 97.34, "World Knowledge": 97.40, "Attribute-Overall": 93.59, "Quantity": 88.30, "Expression": 83.75, "Material": 94.13, "Size": 95.27, "Shape": 90.91, "Color": 97.80, "Action-Overall": 88.80, "Hand": 83.97, "Full body": 90.94, "Animal": 88.41, "Non Contact": 87.50, "Contact": 88.79, "State": 90.02, "Relationship-Overall": 92.35, "Composition": 92.22, "Similarity": 87.82, "Inclusion": 96.84, "Comparison": 92.23, "Compound-Overall": 92.51, "Imagination": 93.99, "Feature matching": 89.25, "Grammar-Overall": 88.83, "Pronoun Reference": 96.83, "Consistency": 90.08, "Negation": 80.63, "Layout-Overall": 94.13, "2D": 94.77, "3D": 93.30, "Logical Reasoning": 86.89, "Text": 6.79 } ] }