| { | |
| "leaderboard": [ | |
| { | |
| "model": "Z-Image-Turbo", | |
| "link": "https://github.com/Tongyi-MAI/Z-Image", | |
| "hf": "https://huggingface.co/Tongyi-MAI/Z-Image-Turbo", | |
| "open_source": true, | |
| "release_date": "2025-11", | |
| "Overall": 71.40, | |
| "Style": 90.00, | |
| "World Knowledge": 92.25, | |
| "Attribute-Overall": 74.57, | |
| "Quantity": 75.00, | |
| "Expression": 58.97, | |
| "Material": 79.25, | |
| "Size": 77.78, | |
| "Shape": 64.38, | |
| "Color": 95.83, | |
| "Action-Overall": 69.30, | |
| "Hand": 62.82, | |
| "Full body": 73.37, | |
| "Animal": 78.68, | |
| "Non Contact": 69.90, | |
| "Contact": 61.31, | |
| "State": 70.28, | |
| "Relationship-Overall": 71.57, | |
| "Composition": 75.68, | |
| "Similarity": 65.00, | |
| "Inclusion": 75.54, | |
| "Comparison": 65.62, | |
| "Compound-Overall": 63.02, | |
| "Imagination": 64.29, | |
| "Feature matching": 61.72, | |
| "Grammar-Overall": 64.57, | |
| "Pronoun Reference": 79.78, | |
| "Consistency": 62.04, | |
| "Negation": 50.77, | |
| "Layout-Overall": 78.36, | |
| "2D": 83.09, | |
| "3D": 73.48, | |
| "Logical Reasoning": 39.68, | |
| "Text": 70.69 | |
| }, | |
| { | |
| "model": "FLUX.2-dev", | |
| "link": "https://github.com/black-forest-labs/flux2", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.2-dev", | |
| "open_source": true, | |
| "release_date": "2025-11", | |
| "Overall": 84.76, | |
| "Style": 96.60, | |
| "World Knowledge": 95.41, | |
| "Attribute-Overall": 87.39, | |
| "Quantity": 73.61, | |
| "Expression": 73.72, | |
| "Material": 96.23, | |
| "Size": 91.67, | |
| "Shape": 88.12, | |
| "Color": 100.0, | |
| "Action-Overall": 82.22, | |
| "Hand": 74.36, | |
| "Full body": 86.41, | |
| "Animal": 83.82, | |
| "Non Contact": 82.14, | |
| "Contact": 80.95, | |
| "State": 84.43, | |
| "Relationship-Overall": 87.31, | |
| "Composition": 93.24, | |
| "Similarity": 77.78, | |
| "Inclusion": 88.59, | |
| "Comparison": 93.24, | |
| "Compound-Overall": 83.51, | |
| "Imagination": 84.95, | |
| "Feature matching": 82.03, | |
| "Grammar-Overall": 77.41, | |
| "Pronoun Reference": 88.60, | |
| "Consistency": 78.70, | |
| "Negation": 64.62, | |
| "Layout-Overall": 89.55, | |
| "2D": 87.87, | |
| "3D": 91.29, | |
| "Logical Reasoning": 62.84, | |
| "Text": 85.34 | |
| }, | |
| { | |
| "model": "Nano Banana Pro", | |
| "link": "https://nano-banana.pro", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-11", | |
| "Overall": 92.72, | |
| "Style": 99.30, | |
| "World Knowledge": 97.47, | |
| "Attribute-Overall": 91.95, | |
| "Quantity": 90.28, | |
| "Expression": 85.53, | |
| "Material": 97.64, | |
| "Size": 93.75, | |
| "Shape": 85.00, | |
| "Color": 99.17, | |
| "Action-Overall": 91.38, | |
| "Hand": 89.47, | |
| "Full body": 91.11, | |
| "Animal": 90.44, | |
| "Non Contact": 89.80, | |
| "Contact": 94.05, | |
| "State": 92.92, | |
| "Relationship-Overall": 95.43, | |
| "Composition": 96.96, | |
| "Similarity": 96.11, | |
| "Inclusion": 92.39, | |
| "Comparison": 95.31, | |
| "Compound-Overall": 92.91, | |
| "Imagination": 95.15, | |
| "Feature matching": 90.62, | |
| "Grammar-Overall": 89.59, | |
| "Pronoun Reference": 94.49, | |
| "Consistency": 87.96, | |
| "Negation": 85.71, | |
| "Layout-Overall": 93.28, | |
| "2D": 92.65, | |
| "3D": 93.94, | |
| "Logical Reasoning": 80.24, | |
| "Text": 95.65 | |
| }, | |
| { | |
| "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": 78.17, | |
| "Style": 93.15, | |
| "World Knowledge": 95.22, | |
| "Attribute-Overall": 81.06, | |
| "Quantity": 75.00, | |
| "Expression": 67.95, | |
| "Material": 91.04, | |
| "Size": 85.29, | |
| "Shape": 77.50, | |
| "Color": 87.50, | |
| "Action-Overall": 74.23, | |
| "Hand": 61.18, | |
| "Full body": 75.00, | |
| "Animal": 76.47, | |
| "Non Contact": 75.00, | |
| "Contact": 72.02, | |
| "State": 82.55, | |
| "Relationship-Overall": 82.23, | |
| "Composition": 85.14, | |
| "Similarity": 75.00, | |
| "Inclusion": 82.07, | |
| "Comparison": 85.94, | |
| "Compound-Overall": 76.23, | |
| "Imagination": 79.38, | |
| "Feature matching": 73.04, | |
| "Grammar-Overall": 73.59, | |
| "Pronoun Reference": 84.07, | |
| "Consistency": 73.15, | |
| "Negation": 63.08, | |
| "Layout-Overall": 77.61, | |
| "2D": 75.74, | |
| "3D": 79.55, | |
| "Logical Reasoning": 56.36, | |
| "Text": 71.97 | |
| }, | |
| { | |
| "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": 69.12, | |
| "Style": 92.20, | |
| "World Knowledge": 90.51, | |
| "Attribute-Overall": 79.06, | |
| "Quantity": 70.14, | |
| "Expression": 71.15, | |
| "Material": 84.91, | |
| "Size": 83.33, | |
| "Shape": 68.75, | |
| "Color": 98.33, | |
| "Action-Overall": 68.92, | |
| "Hand": 66.03, | |
| "Full body": 66.30, | |
| "Animal": 77.94, | |
| "Non Contact": 67.86, | |
| "Contact": 59.52, | |
| "State": 75.94, | |
| "Relationship-Overall": 76.52, | |
| "Composition": 81.76, | |
| "Similarity": 70.56, | |
| "Inclusion": 77.72, | |
| "Comparison": 71.09, | |
| "Compound-Overall": 71.78, | |
| "Imagination": 76.79, | |
| "Feature matching": 66.67, | |
| "Grammar-Overall": 75.13, | |
| "Pronoun Reference": 80.51, | |
| "Consistency": 74.54, | |
| "Negation": 70.00, | |
| "Layout-Overall": 82.28, | |
| "2D": 87.13, | |
| "3D": 77.27, | |
| "Logical Reasoning": 44.77, | |
| "Text": 10.06 | |
| }, | |
| { | |
| "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": 63.11, | |
| "Style": 91.10, | |
| "World Knowledge": 82.91, | |
| "Attribute-Overall": 70.62, | |
| "Quantity": 70.14, | |
| "Expression": 64.74, | |
| "Material": 61.32, | |
| "Size": 72.22, | |
| "Shape": 66.25, | |
| "Color": 99.17, | |
| "Action-Overall": 67.21, | |
| "Hand": 55.13, | |
| "Full body": 72.28, | |
| "Animal": 73.53, | |
| "Non Contact": 63.78, | |
| "Contact": 61.90, | |
| "State": 75.00, | |
| "Relationship-Overall": 67.13, | |
| "Composition": 72.30, | |
| "Similarity": 63.33, | |
| "Inclusion": 64.67, | |
| "Comparison": 64.06, | |
| "Compound-Overall": 54.51, | |
| "Imagination": 58.16, | |
| "Feature matching": 50.78, | |
| "Grammar-Overall": 63.77, | |
| "Pronoun Reference": 74.26, | |
| "Consistency": 64.35, | |
| "Negation": 52.31, | |
| "Layout-Overall": 69.03, | |
| "2D": 73.90, | |
| "3D": 64.02, | |
| "Logical Reasoning": 38.41, | |
| "Text": 26.44 | |
| }, | |
| { | |
| "model": "SD-3.5-Medium", | |
| "link": "https://stability.ai/news/introducing-stable-diffusion-3-5", | |
| "hf": "stabilityai/stable-diffusion-3.5-medium", | |
| "open_source": true, | |
| "release_date": "2024-10", | |
| "Overall": 60.71, | |
| "Style": 89.80, | |
| "World Knowledge": 84.34, | |
| "Attribute-Overall": 66.99, | |
| "Quantity": 59.72, | |
| "Expression": 51.92, | |
| "Material": 67.92, | |
| "Size": 70.83, | |
| "Shape": 63.75, | |
| "Color": 93.33, | |
| "Action-Overall": 60.65, | |
| "Hand": 50.00, | |
| "Full body": 63.04, | |
| "Animal": 69.12, | |
| "Non Contact": 55.61, | |
| "Contact": 52.98, | |
| "State": 71.70, | |
| "Relationship-Overall": 68.78, | |
| "Composition": 74.66, | |
| "Similarity": 61.67, | |
| "Inclusion": 73.37, | |
| "Comparison": 58.59, | |
| "Compound-Overall": 53.35, | |
| "Imagination": 58.16, | |
| "Feature matching": 48.44, | |
| "Grammar-Overall": 59.89, | |
| "Pronoun Reference": 73.53, | |
| "Consistency": 61.57, | |
| "Negation": 44.23, | |
| "Layout-Overall": 70.34, | |
| "2D": 72.06, | |
| "3D": 68.56, | |
| "Logical Reasoning": 37.73, | |
| "Text": 15.23 | |
| }, | |
| { | |
| "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": 71.12, | |
| "Style": 89.70, | |
| "World Knowledge": 90.03, | |
| "Attribute-Overall": 81.62, | |
| "Quantity": 69.44, | |
| "Expression": 85.90, | |
| "Material": 81.60, | |
| "Size": 76.39, | |
| "Shape": 80.00, | |
| "Color": 99.17, | |
| "Action-Overall": 73.76, | |
| "Hand": 64.10, | |
| "Full body": 78.80, | |
| "Animal": 75.74, | |
| "Non Contact": 73.98, | |
| "Contact": 64.88, | |
| "State": 82.08, | |
| "Relationship-Overall": 78.43, | |
| "Composition": 83.45, | |
| "Similarity": 74.44, | |
| "Inclusion": 81.52, | |
| "Comparison": 67.97, | |
| "Compound-Overall": 73.32, | |
| "Imagination": 78.83, | |
| "Feature matching": 67.71, | |
| "Grammar-Overall": 70.45, | |
| "Pronoun Reference": 81.99, | |
| "Consistency": 77.78, | |
| "Negation": 52.31, | |
| "Layout-Overall": 82.84, | |
| "2D": 84.93, | |
| "3D": 80.68, | |
| "Logical Reasoning": 45.45, | |
| "Text": 25.57 | |
| }, | |
| { | |
| "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": 41.35, | |
| "Style": 82.40, | |
| "World Knowledge": 56.65, | |
| "Attribute-Overall": 48.93, | |
| "Quantity": 45.83, | |
| "Expression": 29.49, | |
| "Material": 54.25, | |
| "Size": 49.31, | |
| "Shape": 44.38, | |
| "Color": 74.17, | |
| "Action-Overall": 37.83, | |
| "Hand": 15.38, | |
| "Full body": 40.22, | |
| "Animal": 52.94, | |
| "Non Contact": 33.16, | |
| "Contact": 25.60, | |
| "State": 56.60, | |
| "Relationship-Overall": 50.25, | |
| "Composition": 55.07, | |
| "Similarity": 57.22, | |
| "Inclusion": 47.28, | |
| "Comparison": 33.59, | |
| "Compound-Overall": 32.35, | |
| "Imagination": 40.56, | |
| "Feature matching": 23.96, | |
| "Grammar-Overall": 55.75, | |
| "Pronoun Reference": 59.19, | |
| "Consistency": 40.28, | |
| "Negation": 65.00, | |
| "Layout-Overall": 30.22, | |
| "2D": 30.15, | |
| "3D": 30.30, | |
| "Logical Reasoning": 17.95, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "OmniGen2", | |
| "link": "https://arxiv.org/pdf/2506.18871", | |
| "hf": "https://huggingface.co/OmniGen2/OmniGen2", | |
| "open_source": true, | |
| "release_date": "2025-06", | |
| "Overall": 63.09, | |
| "Style": 91.90, | |
| "World Knowledge": 86.39, | |
| "Attribute-Overall": 72.12, | |
| "Quantity": 67.36, | |
| "Expression": 73.08, | |
| "Material": 66.04, | |
| "Size": 72.22, | |
| "Shape": 66.25, | |
| "Color": 95.00, | |
| "Action-Overall": 62.83, | |
| "Hand": 55.77, | |
| "Full body": 69.02, | |
| "Animal": 68.38, | |
| "Non Contact": 62.24, | |
| "Contact": 54.17, | |
| "State": 66.51, | |
| "Relationship-Overall": 68.27, | |
| "Composition": 68.24, | |
| "Similarity": 67.78, | |
| "Inclusion": 71.20, | |
| "Comparison": 64.84, | |
| "Compound-Overall": 56.31, | |
| "Imagination": 62.24, | |
| "Feature matching": 50.26, | |
| "Grammar-Overall": 59.89, | |
| "Pronoun Reference": 71.32, | |
| "Consistency": 60.65, | |
| "Negation": 47.31, | |
| "Layout-Overall": 71.64, | |
| "2D": 78.31, | |
| "3D": 64.77, | |
| "Logical Reasoning": 32.50, | |
| "Text": 29.02 | |
| }, | |
| { | |
| "model": "Infinity", | |
| "link": "https://arxiv.org/pdf/2412.04431", | |
| "hf": "https://huggingface.co/FoundationVision/Infinity/tree/main/infinity_8b_512x512_weights", | |
| "open_source": true, | |
| "release_date": "2024-12", | |
| "Overall": 59.81, | |
| "Style": 90.80, | |
| "World Knowledge": 87.97, | |
| "Attribute-Overall": 68.06, | |
| "Quantity": 66.67, | |
| "Expression": 53.21, | |
| "Material": 66.04, | |
| "Size": 77.78, | |
| "Shape": 58.75, | |
| "Color": 93.33, | |
| "Action-Overall": 60.17, | |
| "Hand": 55.13, | |
| "Full body": 65.22, | |
| "Animal": 72.06, | |
| "Non Contact": 58.16, | |
| "Contact": 49.40, | |
| "State": 62.26, | |
| "Relationship-Overall": 69.16, | |
| "Composition": 73.31, | |
| "Similarity": 65.00, | |
| "Inclusion": 67.39, | |
| "Comparison": 67.97, | |
| "Compound-Overall": 51.42, | |
| "Imagination": 55.87, | |
| "Feature matching": 46.88, | |
| "Grammar-Overall": 60.16, | |
| "Pronoun Reference": 73.16, | |
| "Consistency": 65.74, | |
| "Negation": 41.92, | |
| "Layout-Overall": 66.60, | |
| "2D": 71.69, | |
| "3D": 61.36, | |
| "Logical Reasoning": 31.36, | |
| "Text": 12.36 | |
| }, | |
| { | |
| "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": 58.28, | |
| "Style": 93.30, | |
| "World Knowledge": 82.28, | |
| "Attribute-Overall": 63.46, | |
| "Quantity": 59.42, | |
| "Expression": 58.33, | |
| "Material": 67.45, | |
| "Size": 65.97, | |
| "Shape": 42.50, | |
| "Color": 92.50, | |
| "Action-Overall": 58.56, | |
| "Hand": 35.90, | |
| "Full body": 65.22, | |
| "Animal": 69.12, | |
| "Non Contact": 57.65, | |
| "Contact": 48.81, | |
| "State": 71.23, | |
| "Relationship-Overall": 68.15, | |
| "Composition": 78.04, | |
| "Similarity": 69.44, | |
| "Inclusion": 62.50, | |
| "Comparison": 51.56, | |
| "Compound-Overall": 56.96, | |
| "Imagination": 66.33, | |
| "Feature matching": 47.40, | |
| "Grammar-Overall": 60.83, | |
| "Pronoun Reference": 70.59, | |
| "Consistency": 59.72, | |
| "Negation": 51.54, | |
| "Layout-Overall": 64.74, | |
| "2D": 64.34, | |
| "3D": 65.15, | |
| "Logical Reasoning": 33.41, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "X-Omni", | |
| "link": "https://arxiv.org/pdf/2507.22058", | |
| "hf": "https://huggingface.co/X-Omni/X-Omni-En", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 53.77, | |
| "Style": 72.70, | |
| "World Knowledge": 76.27, | |
| "Attribute-Overall": 60.04, | |
| "Quantity": 63.19, | |
| "Expression": 53.21, | |
| "Material": 58.96, | |
| "Size": 55.56, | |
| "Shape": 53.75, | |
| "Color": 80.83, | |
| "Action-Overall": 54.47, | |
| "Hand": 46.79, | |
| "Full body": 56.52, | |
| "Animal": 62.50, | |
| "Non Contact": 56.63, | |
| "Contact": 42.26, | |
| "State": 60.85, | |
| "Relationship-Overall": 56.60, | |
| "Composition": 61.82, | |
| "Similarity": 56.11, | |
| "Inclusion": 51.09, | |
| "Comparison": 53.12, | |
| "Compound-Overall": 41.75, | |
| "Imagination": 47.45, | |
| "Feature matching": 35.94, | |
| "Grammar-Overall": 59.09, | |
| "Pronoun Reference": 66.91, | |
| "Consistency": 54.17, | |
| "Negation": 55.00, | |
| "Layout-Overall": 62.69, | |
| "2D": 69.49, | |
| "3D": 55.68, | |
| "Logical Reasoning": 29.09, | |
| "Text": 25.00 | |
| }, | |
| { | |
| "model": "FLUX.1-Krea-dev", | |
| "link": "https://www.krea.ai/blog/flux-krea-open-source-release", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.1-Krea-dev", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 69.88, | |
| "Style": 88.70, | |
| "World Knowledge": 92.56, | |
| "Attribute-Overall": 75.96, | |
| "Quantity": 70.83, | |
| "Expression": 60.90, | |
| "Material": 77.36, | |
| "Size": 79.17, | |
| "Shape": 73.12, | |
| "Color": 99.17, | |
| "Action-Overall": 71.01, | |
| "Hand": 64.74, | |
| "Full body": 70.11, | |
| "Animal": 77.94, | |
| "Non Contact": 72.96, | |
| "Contact": 67.26, | |
| "State": 73.11, | |
| "Relationship-Overall": 73.98, | |
| "Composition": 76.35, | |
| "Similarity": 66.11, | |
| "Inclusion": 77.17, | |
| "Comparison": 75.00, | |
| "Compound-Overall": 64.43, | |
| "Imagination": 67.35, | |
| "Feature matching": 61.46, | |
| "Grammar-Overall": 63.37, | |
| "Pronoun Reference": 77.21, | |
| "Consistency": 67.13, | |
| "Negation": 45.77, | |
| "Layout-Overall": 84.14, | |
| "2D": 86.76, | |
| "3D": 81.44, | |
| "Logical Reasoning": 39.77, | |
| "Text": 44.83 | |
| }, | |
| { | |
| "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": 74.64, | |
| "Style": 90.88, | |
| "World Knowledge": 92.06, | |
| "Attribute-Overall": 79.66, | |
| "Quantity": 86.62, | |
| "Expression": 72.44, | |
| "Material": 78.77, | |
| "Size": 78.47, | |
| "Shape": 68.12, | |
| "Color": 99.17, | |
| "Action-Overall": 77.81, | |
| "Hand": 75.00, | |
| "Full body": 80.98, | |
| "Animal": 82.35, | |
| "Non Contact": 73.71, | |
| "Contact": 72.02, | |
| "State": 82.55, | |
| "Relationship-Overall": 77.54, | |
| "Composition": 78.38, | |
| "Similarity": 70.56, | |
| "Inclusion": 84.78, | |
| "Comparison": 75.00, | |
| "Compound-Overall": 64.82, | |
| "Imagination": 64.54, | |
| "Feature matching": 65.10, | |
| "Grammar-Overall": 62.83, | |
| "Pronoun Reference": 77.94, | |
| "Consistency": 66.20, | |
| "Negation": 44.23, | |
| "Layout-Overall": 84.14, | |
| "2D": 86.76, | |
| "3D": 81.44, | |
| "Logical Reasoning": 46.59, | |
| "Text": 70.11 | |
| }, | |
| { | |
| "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": 65.15, | |
| "Style": 91.00, | |
| "World Knowledge": 86.71, | |
| "Attribute-Overall": 70.94, | |
| "Quantity": 67.36, | |
| "Expression": 73.72, | |
| "Material": 70.28, | |
| "Size": 76.39, | |
| "Shape": 60.62, | |
| "Color": 80.00, | |
| "Action-Overall": 66.83, | |
| "Hand": 57.69, | |
| "Full body": 75.00, | |
| "Animal": 73.53, | |
| "Non Contact": 67.35, | |
| "Contact": 57.74, | |
| "State": 68.87, | |
| "Relationship-Overall": 73.60, | |
| "Composition": 76.01, | |
| "Similarity": 65.00, | |
| "Inclusion": 77.17, | |
| "Comparison": 75.00, | |
| "Compound-Overall": 64.82, | |
| "Imagination": 73.72, | |
| "Feature matching": 55.73, | |
| "Grammar-Overall": 68.05, | |
| "Pronoun Reference": 76.47, | |
| "Consistency": 67.13, | |
| "Negation": 60.00, | |
| "Layout-Overall": 76.31, | |
| "2D": 80.15, | |
| "3D": 72.35, | |
| "Logical Reasoning": 48.64, | |
| "Text": 4.60 | |
| }, | |
| { | |
| "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": 45.47, | |
| "Style": 84.40, | |
| "World Knowledge": 77.22, | |
| "Attribute-Overall": 54.17, | |
| "Quantity": 62.50, | |
| "Expression": 33.33, | |
| "Material": 51.89, | |
| "Size": 62.50, | |
| "Shape": 40.62, | |
| "Color": 83.33, | |
| "Action-Overall": 48.00, | |
| "Hand": 42.95, | |
| "Full body": 42.39, | |
| "Animal": 56.62, | |
| "Non Contact": 45.92, | |
| "Contact": 39.88, | |
| "State": 59.43, | |
| "Relationship-Overall": 52.79, | |
| "Composition": 55.41, | |
| "Similarity": 53.89, | |
| "Inclusion": 51.63, | |
| "Comparison": 46.88, | |
| "Compound-Overall": 33.63, | |
| "Imagination": 41.33, | |
| "Feature matching": 25.78, | |
| "Grammar-Overall": 46.66, | |
| "Pronoun Reference": 56.62, | |
| "Consistency": 47.22, | |
| "Negation": 35.77, | |
| "Layout-Overall": 42.91, | |
| "2D": 43.01, | |
| "3D": 42.80, | |
| "Logical Reasoning": 19.77, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "Seedream-4.0", | |
| "link": "https://www.volcengine.com/docs/82379/1541523", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-09", | |
| "Overall": 87.35, | |
| "Style": 98.80, | |
| "World Knowledge": 95.41, | |
| "Attribute-Overall": 88.57, | |
| "Quantity": 86.81, | |
| "Expression": 85.90, | |
| "Material": 97.17, | |
| "Size": 84.03, | |
| "Shape": 76.88, | |
| "Color": 100.0, | |
| "Action-Overall": 85.65, | |
| "Hand": 77.56, | |
| "Full body": 87.50, | |
| "Animal": 88.24, | |
| "Non Contact": 80.10, | |
| "Contact": 83.93, | |
| "State": 94.81, | |
| "Relationship-Overall": 87.69, | |
| "Composition": 88.18, | |
| "Similarity": 80.56, | |
| "Inclusion": 94.02, | |
| "Comparison": 87.50, | |
| "Compound-Overall": 86.08, | |
| "Imagination": 88.27, | |
| "Feature matching": 83.85, | |
| "Grammar-Overall": 78.88, | |
| "Pronoun Reference": 84.93, | |
| "Consistency": 79.17, | |
| "Negation": 72.31, | |
| "Layout-Overall": 90.67, | |
| "2D": 90.81, | |
| "3D": 90.53, | |
| "Logical Reasoning": 67.73, | |
| "Text": 93.97 | |
| }, | |
| { | |
| "model": "Imagen-4.0-generate-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-01", | |
| "Overall": 85.84, | |
| "Style": 97.80, | |
| "World Knowledge": 96.36, | |
| "Attribute-Overall": 84.94, | |
| "Quantity": 84.03, | |
| "Expression": 76.92, | |
| "Material": 90.57, | |
| "Size": 89.58, | |
| "Shape": 71.88, | |
| "Color": 98.33, | |
| "Action-Overall": 88.40, | |
| "Hand": 86.54, | |
| "Full body": 94.02, | |
| "Animal": 88.97, | |
| "Non Contact": 85.71, | |
| "Contact": 83.33, | |
| "State": 91.04, | |
| "Relationship-Overall": 89.34, | |
| "Composition": 93.58, | |
| "Similarity": 78.89, | |
| "Inclusion": 95.11, | |
| "Comparison": 85.94, | |
| "Compound-Overall": 85.31, | |
| "Imagination": 90.31, | |
| "Feature matching": 80.21, | |
| "Grammar-Overall": 79.68, | |
| "Pronoun Reference": 86.76, | |
| "Consistency": 77.31, | |
| "Negation": 74.23, | |
| "Layout-Overall": 88.81, | |
| "2D": 88.24, | |
| "3D": 89.39, | |
| "Logical Reasoning": 70.45, | |
| "Text": 77.30 | |
| }, | |
| { | |
| "model": "Runway-Gen4-Image", | |
| "link": "https://docs.dev.runwayml.com/api/#tag/Start-generating/paths/~1v1~1text_to_image/post", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-11", | |
| "Overall": 69.75, | |
| "Style": 93.44, | |
| "World Knowledge": 90.36, | |
| "Attribute-Overall": 74.03, | |
| "Quantity": 72.86, | |
| "Expression": 51.97, | |
| "Material": 89.42, | |
| "Size": 68.06, | |
| "Shape": 65.62, | |
| "Color": 95.00, | |
| "Action-Overall": 70.21, | |
| "Hand": 62.18, | |
| "Full body": 79.35, | |
| "Animal": 82.35, | |
| "Non Contact": 66.15, | |
| "Contact": 60.37, | |
| "State": 71.70, | |
| "Relationship-Overall": 72.56, | |
| "Composition": 74.32, | |
| "Similarity": 62.22, | |
| "Inclusion": 77.84, | |
| "Comparison": 75.78, | |
| "Compound-Overall": 67.76, | |
| "Imagination": 71.65, | |
| "Feature matching": 63.71, | |
| "Grammar-Overall": 70.08, | |
| "Pronoun Reference": 71.21, | |
| "Consistency": 67.59, | |
| "Negation": 71.03, | |
| "Layout-Overall": 76.33, | |
| "2D": 77.61, | |
| "3D": 75.00, | |
| "Logical Reasoning": 49.31, | |
| "Text": 33.43 | |
| }, | |
| { | |
| "model": "Nano Banana", | |
| "link": "https://ainanobanana.io/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-08", | |
| "Overall": 87.45, | |
| "Style": 98.87, | |
| "World Knowledge": 96.32, | |
| "Attribute-Overall": 87.84, | |
| "Quantity": 85.00, | |
| "Expression": 83.33, | |
| "Material": 88.50, | |
| "Size": 95.74, | |
| "Shape": 78.21, | |
| "Color": 99.17, | |
| "Action-Overall": 86.83, | |
| "Hand": 82.05, | |
| "Full body": 93.41, | |
| "Animal": 86.03, | |
| "Non Contact": 82.47, | |
| "Contact": 83.33, | |
| "State": 91.98, | |
| "Relationship-Overall": 92.00, | |
| "Composition": 94.76, | |
| "Similarity": 86.52, | |
| "Inclusion": 91.26, | |
| "Comparison": 94.53, | |
| "Compound-Overall": 87.83, | |
| "Imagination": 89.66, | |
| "Feature matching": 86.02, | |
| "Grammar-Overall": 83.36, | |
| "Pronoun Reference": 90.71, | |
| "Consistency": 82.08, | |
| "Negation": 76.59, | |
| "Layout-Overall": 91.96, | |
| "2D": 92.65, | |
| "3D": 91.25, | |
| "Logical Reasoning": 74.26, | |
| "Text": 75.22 | |
| }, | |
| { | |
| "model": "Stability-AI-stable-image-ultra", | |
| "link": "https://platform.stability.ai/docs/api-reference#tag/Generate/paths/~1v2beta~1stable-image~1generate~1ultra/post", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-06", | |
| "Overall": 61.96, | |
| "Style": 87.20, | |
| "World Knowledge": 87.18, | |
| "Attribute-Overall": 66.35, | |
| "Quantity": 67.36, | |
| "Expression": 48.08, | |
| "Material": 64.15, | |
| "Size": 69.44, | |
| "Shape": 64.38, | |
| "Color": 91.67, | |
| "Action-Overall": 59.22, | |
| "Hand": 55.77, | |
| "Full body": 58.15, | |
| "Animal": 63.24, | |
| "Non Contact": 61.22, | |
| "Contact": 51.79, | |
| "State": 64.15, | |
| "Relationship-Overall": 69.04, | |
| "Composition": 72.64, | |
| "Similarity": 66.67, | |
| "Inclusion": 70.11, | |
| "Comparison": 62.50, | |
| "Compound-Overall": 54.25, | |
| "Imagination": 60.97, | |
| "Feature matching": 47.40, | |
| "Grammar-Overall": 61.10, | |
| "Pronoun Reference": 78.68, | |
| "Consistency": 58.33, | |
| "Negation": 45.00, | |
| "Layout-Overall": 64.55, | |
| "2D": 67.28, | |
| "3D": 61.74, | |
| "Logical Reasoning": 31.59, | |
| "Text": 39.08 | |
| }, | |
| { | |
| "model": "HiDream_v2L", | |
| "link": "https://hidreamai.com/doc/txt2img/request", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-07", | |
| "Overall": 61.64, | |
| "Style": 87.99, | |
| "World Knowledge": 89.62, | |
| "Attribute-Overall": 64.38, | |
| "Quantity": 65.71, | |
| "Expression": 44.87, | |
| "Material": 57.82, | |
| "Size": 74.26, | |
| "Shape": 59.87, | |
| "Color": 94.92, | |
| "Action-Overall": 59.50, | |
| "Hand": 51.28, | |
| "Full body": 58.56, | |
| "Animal": 67.65, | |
| "Non Contact": 61.98, | |
| "Contact": 51.52, | |
| "State": 65.09, | |
| "Relationship-Overall": 66.62, | |
| "Composition": 71.23, | |
| "Similarity": 64.20, | |
| "Inclusion": 65.93, | |
| "Comparison": 60.32, | |
| "Compound-Overall": 49.28, | |
| "Imagination": 53.75, | |
| "Feature matching": 44.76, | |
| "Grammar-Overall": 58.86, | |
| "Pronoun Reference": 72.35, | |
| "Consistency": 60.00, | |
| "Negation": 44.23, | |
| "Layout-Overall": 69.06, | |
| "2D": 70.41, | |
| "3D": 67.68, | |
| "Logical Reasoning": 26.73, | |
| "Text": 44.31 | |
| }, | |
| { | |
| "model": "Imagen-4.0-Fast-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-01", | |
| "Overall": 77.75, | |
| "Style": 92.00, | |
| "World Knowledge": 94.78, | |
| "Attribute-Overall": 83.65, | |
| "Quantity": 77.08, | |
| "Expression": 75.00, | |
| "Material": 85.85, | |
| "Size": 89.58, | |
| "Shape": 78.75, | |
| "Color": 98.33, | |
| "Action-Overall": 79.85, | |
| "Hand": 73.72, | |
| "Full body": 84.24, | |
| "Animal": 81.62, | |
| "Non Contact": 76.53, | |
| "Contact": 76.79, | |
| "State": 84.91, | |
| "Relationship-Overall": 82.36, | |
| "Composition": 83.45, | |
| "Similarity": 73.89, | |
| "Inclusion": 89.13, | |
| "Comparison": 82.03, | |
| "Compound-Overall": 74.10, | |
| "Imagination": 80.10, | |
| "Feature matching": 67.97, | |
| "Grammar-Overall": 76.74, | |
| "Pronoun Reference": 86.03, | |
| "Consistency": 75.00, | |
| "Negation": 68.46, | |
| "Layout-Overall": 86.19, | |
| "2D": 88.24, | |
| "3D": 84.09, | |
| "Logical Reasoning": 56.36, | |
| "Text": 51.44 | |
| }, | |
| { | |
| "model": "Recraft", | |
| "link": "https://www.recraft.ai/docs#generate-image", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-12", | |
| "Overall": 62.63, | |
| "Style": 87.20, | |
| "World Knowledge": 90.19, | |
| "Attribute-Overall": 68.16, | |
| "Quantity": 68.06, | |
| "Expression": 56.41, | |
| "Material": 70.75, | |
| "Size": 65.97, | |
| "Shape": 57.50, | |
| "Color": 95.83, | |
| "Action-Overall": 60.55, | |
| "Hand": 50.00, | |
| "Full body": 70.65, | |
| "Animal": 76.47, | |
| "Non Contact": 55.61, | |
| "Contact": 48.81, | |
| "State": 63.21, | |
| "Relationship-Overall": 62.56, | |
| "Composition": 64.53, | |
| "Similarity": 59.44, | |
| "Inclusion": 59.24, | |
| "Comparison": 67.19, | |
| "Compound-Overall": 44.85, | |
| "Imagination": 43.37, | |
| "Feature matching": 46.35, | |
| "Grammar-Overall": 63.64, | |
| "Pronoun Reference": 73.16, | |
| "Consistency": 58.33, | |
| "Negation": 58.08, | |
| "Layout-Overall": 57.84, | |
| "2D": 58.82, | |
| "3D": 56.82, | |
| "Logical Reasoning": 29.55, | |
| "Text": 61.78 | |
| }, | |
| { | |
| "model": "FLUX-kontext-max", | |
| "link": "https://bfl.ai/models/flux-kontext", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-05", | |
| "Overall": 80.00, | |
| "Style": 96.59, | |
| "World Knowledge": 94.19, | |
| "Attribute-Overall": 80.93, | |
| "Quantity": 75.69, | |
| "Expression": 74.32, | |
| "Material": 82.55, | |
| "Size": 86.81, | |
| "Shape": 74.38, | |
| "Color": 94.17, | |
| "Action-Overall": 77.38, | |
| "Hand": 67.95, | |
| "Full body": 83.15, | |
| "Animal": 77.94, | |
| "Non Contact": 77.04, | |
| "Contact": 70.83, | |
| "State": 84.43, | |
| "Relationship-Overall": 85.08, | |
| "Composition": 87.50, | |
| "Similarity": 78.89, | |
| "Inclusion": 90.00, | |
| "Comparison": 81.25, | |
| "Compound-Overall": 78.99, | |
| "Imagination": 83.93, | |
| "Feature matching": 73.96, | |
| "Grammar-Overall": 78.53, | |
| "Pronoun Reference": 84.23, | |
| "Consistency": 78.70, | |
| "Negation": 72.69, | |
| "Layout-Overall": 85.04, | |
| "2D": 86.74, | |
| "3D": 88.33, | |
| "Logical Reasoning": 61.36, | |
| "Text": 61.92 | |
| }, | |
| { | |
| "model": "FLUX-kontext-pro", | |
| "link": "https://bfl.ai/models/flux-kontext", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-05", | |
| "Overall": 75.84, | |
| "Style": 94.78, | |
| "World Knowledge": 91.61, | |
| "Attribute-Overall": 79.20, | |
| "Quantity": 75.00, | |
| "Expression": 71.62, | |
| "Material": 76.89, | |
| "Size": 84.72, | |
| "Shape": 74.38, | |
| "Color": 97.50, | |
| "Action-Overall": 77.66, | |
| "Hand": 75.00, | |
| "Full body": 79.35, | |
| "Animal": 80.88, | |
| "Non Contact": 71.94, | |
| "Contact": 73.21, | |
| "State": 84.91, | |
| "Relationship-Overall": 79.34, | |
| "Composition": 81.42, | |
| "Similarity": 75.56, | |
| "Inclusion": 83.33, | |
| "Comparison": 74.22, | |
| "Compound-Overall": 72.68, | |
| "Imagination": 75.00, | |
| "Feature matching": 70.31, | |
| "Grammar-Overall": 72.69, | |
| "Pronoun Reference": 84.23, | |
| "Consistency": 76.85, | |
| "Negation": 57.69, | |
| "Layout-Overall": 84.47, | |
| "2D": 85.98, | |
| "3D": 82.95, | |
| "Logical Reasoning": 55.68, | |
| "Text": 50.29 | |
| }, | |
| { | |
| "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": 64.82, | |
| "Style": 91.10, | |
| "World Knowledge": 87.34, | |
| "Attribute-Overall": 70.19, | |
| "Quantity": 76.39, | |
| "Expression": 55.77, | |
| "Material": 66.51, | |
| "Size": 71.53, | |
| "Shape": 64.38, | |
| "Color": 94.17, | |
| "Action-Overall": 68.00, | |
| "Hand": 58.33, | |
| "Full body": 75.82, | |
| "Animal": 69.12, | |
| "Non Contact": 68.88, | |
| "Contact": 57.74, | |
| "State": 75.00, | |
| "Relationship-Overall": 73.03, | |
| "Composition": 70.27, | |
| "Similarity": 67.98, | |
| "Inclusion": 77.72, | |
| "Comparison": 76.69, | |
| "Compound-Overall": 61.37, | |
| "Imagination": 66.92, | |
| "Feature matching": 55.73, | |
| "Grammar-Overall": 66.53, | |
| "Pronoun Reference": 73.90, | |
| "Consistency": 56.74, | |
| "Negation": 66.92, | |
| "Layout-Overall": 74.77, | |
| "2D": 77.49, | |
| "3D": 71.97, | |
| "Logical Reasoning": 42.05, | |
| "Text": 13.83 | |
| }, | |
| { | |
| "model": "FLUX.1-dev", | |
| "link": "https://bfl.ai/blog/24-08-01-bfl", | |
| "hf": "https://huggingface.co/black-forest-labs/FLUX.1-dev", | |
| "open_source": true, | |
| "release_date": "2024-08", | |
| "Overall": 61.30, | |
| "Style": 83.90, | |
| "World Knowledge": 88.92, | |
| "Attribute-Overall": 67.84, | |
| "Quantity": 72.22, | |
| "Expression": 53.85, | |
| "Material": 58.96, | |
| "Size": 75.00, | |
| "Shape": 65.00, | |
| "Color": 91.67, | |
| "Action-Overall": 62.17, | |
| "Hand": 51.28, | |
| "Full body": 67.39, | |
| "Animal": 69.85, | |
| "Non Contact": 59.69, | |
| "Contact": 58.93, | |
| "State": 65.57, | |
| "Relationship-Overall": 67.26, | |
| "Composition": 62.50, | |
| "Similarity": 66.67, | |
| "Inclusion": 72.83, | |
| "Comparison": 62.50, | |
| "Compound-Overall": 47.04, | |
| "Imagination": 47.96, | |
| "Feature matching": 46.09, | |
| "Grammar-Overall": 60.96, | |
| "Pronoun Reference": 73.16, | |
| "Consistency": 63.43, | |
| "Negation": 46.15, | |
| "Layout-Overall": 71.83, | |
| "2D": 74.26, | |
| "3D": 69.32, | |
| "Logical Reasoning": 30.91, | |
| "Text": 32.18 | |
| }, | |
| { | |
| "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": 71.81, | |
| "Style": 92.50, | |
| "World Knowledge": 94.15, | |
| "Attribute-Overall": 72.97, | |
| "Quantity": 73.61, | |
| "Expression": 59.62, | |
| "Material": 72.17, | |
| "Size": 79.17, | |
| "Shape": 61.88, | |
| "Color": 98.33, | |
| "Action-Overall": 73.00, | |
| "Hand": 62.18, | |
| "Full body": 76.09, | |
| "Animal": 73.53, | |
| "Non Contact": 74.49, | |
| "Contact": 70.24, | |
| "State": 78.77, | |
| "Relationship-Overall": 75.38, | |
| "Composition": 79.05, | |
| "Similarity": 68.33, | |
| "Inclusion": 78.26, | |
| "Comparison": 72.66, | |
| "Compound-Overall": 62.63, | |
| "Imagination": 64.29, | |
| "Feature matching": 60.94, | |
| "Grammar-Overall": 63.24, | |
| "Pronoun Reference": 83.09, | |
| "Consistency": 65.74, | |
| "Negation": 40.38, | |
| "Layout-Overall": 78.17, | |
| "2D": 82.72, | |
| "3D": 73.48, | |
| "Logical Reasoning": 41.14, | |
| "Text": 64.94 | |
| }, | |
| { | |
| "model": "Pref-GRPO", | |
| "link": "https://github.com/CodeGoat24/UnifiedReward", | |
| "hf": "https://huggingface.co/CodeGoat24/FLUX.1-dev-PrefGRPO", | |
| "open_source": true, | |
| "release_date": "2025-08", | |
| "Overall": 69.46, | |
| "Style": 88.40, | |
| "World Knowledge": 90.35, | |
| "Attribute-Overall": 75.00, | |
| "Quantity": 71.53, | |
| "Expression": 60.90, | |
| "Material": 73.11, | |
| "Size": 77.08, | |
| "Shape": 74.38, | |
| "Color": 99.17, | |
| "Action-Overall": 69.77, | |
| "Hand": 60.90, | |
| "Full body": 72.28, | |
| "Animal": 77.21, | |
| "Non Contact": 68.37, | |
| "Contact": 64.88, | |
| "State": 74.53, | |
| "Relationship-Overall": 76.52, | |
| "Composition": 81.42, | |
| "Similarity": 76.67, | |
| "Inclusion": 76.09, | |
| "Comparison": 65.62, | |
| "Compound-Overall": 63.27, | |
| "Imagination": 65.56, | |
| "Feature matching": 60.94, | |
| "Grammar-Overall": 62.43, | |
| "Pronoun Reference": 79.04, | |
| "Consistency": 66.20, | |
| "Negation": 41.92, | |
| "Layout-Overall": 77.61, | |
| "2D": 82.35, | |
| "3D": 72.73, | |
| "Logical Reasoning": 47.13, | |
| "Text": 47.13 | |
| }, | |
| { | |
| "model": "SD-3.5-Large", | |
| "link": "https://stability.ai/news/introducing-stable-diffusion-3-5", | |
| "hf": "https://huggingface.co/stabilityai/stable-diffusion-3.5-large", | |
| "open_source": true, | |
| "release_date": "2024-10", | |
| "Overall": 62.99, | |
| "Style": 88.60, | |
| "World Knowledge": 88.92, | |
| "Attribute-Overall": 68.59, | |
| "Quantity": 71.53, | |
| "Expression": 51.92, | |
| "Material": 68.87, | |
| "Size": 68.06, | |
| "Shape": 65.62, | |
| "Color": 90.83, | |
| "Action-Overall": 62.17, | |
| "Hand": 57.05, | |
| "Full body": 61.96, | |
| "Animal": 63.24, | |
| "Non Contact": 62.24, | |
| "Contact": 59.52, | |
| "State": 67.45, | |
| "Relationship-Overall": 69.80, | |
| "Composition": 75.34, | |
| "Similarity": 68.33, | |
| "Inclusion": 68.48, | |
| "Comparison": 60.94, | |
| "Compound-Overall": 58.76, | |
| "Imagination": 64.80, | |
| "Feature matching": 52.60, | |
| "Grammar-Overall": 58.96, | |
| "Pronoun Reference": 74.63, | |
| "Consistency": 61.11, | |
| "Negation": 40.77, | |
| "Layout-Overall": 69.03, | |
| "2D": 70.96, | |
| "3D": 67.05, | |
| "Logical Reasoning": 32.27, | |
| "Text": 32.76 | |
| }, | |
| { | |
| "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": 61.61, | |
| "Style": 90.80, | |
| "World Knowledge": 86.71, | |
| "Attribute-Overall": 67.74, | |
| "Quantity": 56.25, | |
| "Expression": 55.77, | |
| "Material": 71.70, | |
| "Size": 73.61, | |
| "Shape": 61.88, | |
| "Color": 90.83, | |
| "Action-Overall": 64.26, | |
| "Hand": 50.64, | |
| "Full body": 63.04, | |
| "Animal": 75.00, | |
| "Non Contact": 62.24, | |
| "Contact": 56.55, | |
| "State": 76.42, | |
| "Relationship-Overall": 68.40, | |
| "Composition": 76.01, | |
| "Similarity": 56.11, | |
| "Inclusion": 75.00, | |
| "Comparison": 58.59, | |
| "Compound-Overall": 62.11, | |
| "Imagination": 69.64, | |
| "Feature matching": 54.43, | |
| "Grammar-Overall": 64.44, | |
| "Pronoun Reference": 75.37, | |
| "Consistency": 66.20, | |
| "Negation": 51.54, | |
| "Layout-Overall": 72.01, | |
| "2D": 74.63, | |
| "3D": 69.32, | |
| "Logical Reasoning": 37.05, | |
| "Text": 2.59 | |
| }, | |
| { | |
| "model": "Show-o2", | |
| "link": "https://arxiv.org/pdf/2506.15564", | |
| "hf": "https://huggingface.co/showlab/show-o2-7B", | |
| "open_source": true, | |
| "release_date": "2025-06", | |
| "Overall": 62.73, | |
| "Style": 87.20, | |
| "World Knowledge": 86.08, | |
| "Attribute-Overall": 70.51, | |
| "Quantity": 59.03, | |
| "Expression": 63.46, | |
| "Material": 73.58, | |
| "Size": 72.92, | |
| "Shape": 63.12, | |
| "Color": 95.00, | |
| "Action-Overall": 69.58, | |
| "Hand": 56.41, | |
| "Full body": 77.72, | |
| "Animal": 72.79, | |
| "Non Contact": 70.41, | |
| "Contact": 52.38, | |
| "State": 83.02, | |
| "Relationship-Overall": 70.18, | |
| "Composition": 79.05, | |
| "Similarity": 61.11, | |
| "Inclusion": 70.11, | |
| "Comparison": 62.50, | |
| "Compound-Overall": 64.69, | |
| "Imagination": 69.90, | |
| "Feature matching": 59.38, | |
| "Grammar-Overall": 61.63, | |
| "Pronoun Reference": 75.37, | |
| "Consistency": 65.28, | |
| "Negation": 44.23, | |
| "Layout-Overall": 75.37, | |
| "2D": 77.94, | |
| "3D": 72.73, | |
| "Logical Reasoning": 40.91, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "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": 61.53, | |
| "Style": 90.20, | |
| "World Knowledge": 85.60, | |
| "Attribute-Overall": 67.74, | |
| "Quantity": 59.03, | |
| "Expression": 50.00, | |
| "Material": 72.64, | |
| "Size": 76.39, | |
| "Shape": 59.38, | |
| "Color": 93.33, | |
| "Action-Overall": 61.98, | |
| "Hand": 52.56, | |
| "Full body": 60.87, | |
| "Animal": 69.12, | |
| "Non Contact": 62.24, | |
| "Contact": 58.93, | |
| "State": 67.45, | |
| "Relationship-Overall": 70.69, | |
| "Composition": 76.35, | |
| "Similarity": 70.56, | |
| "Inclusion": 69.57, | |
| "Comparison": 59.38, | |
| "Compound-Overall": 58.12, | |
| "Imagination": 67.35, | |
| "Feature matching": 48.70, | |
| "Grammar-Overall": 66.44, | |
| "Pronoun Reference": 71.69, | |
| "Consistency": 68.52, | |
| "Negation": 59.23, | |
| "Layout-Overall": 76.49, | |
| "2D": 79.04, | |
| "3D": 73.86, | |
| "Logical Reasoning": 30.23, | |
| "Text": 7.76 | |
| }, | |
| { | |
| "model": "BLIP3-o", | |
| "link": "https://arxiv.org/pdf/2505.09568", | |
| "hf": "https://huggingface.co/BLIP3o/BLIP3o-Model-8B", | |
| "open_source": true, | |
| "release_date": "2025-05", | |
| "Overall": 59.87, | |
| "Style": 92.80, | |
| "World Knowledge": 80.22, | |
| "Attribute-Overall": 63.89, | |
| "Quantity": 51.39, | |
| "Expression": 60.26, | |
| "Material": 64.62, | |
| "Size": 75.00, | |
| "Shape": 54.37, | |
| "Color": 81.67, | |
| "Action-Overall": 63.97, | |
| "Hand": 58.33, | |
| "Full body": 70.11, | |
| "Animal": 70.59, | |
| "Non Contact": 60.20, | |
| "Contact": 51.79, | |
| "State": 71.70, | |
| "Relationship-Overall": 66.50, | |
| "Composition": 70.61, | |
| "Similarity": 60.00, | |
| "Inclusion": 67.39, | |
| "Comparison": 64.84, | |
| "Compound-Overall": 53.74, | |
| "Imagination": 61.73, | |
| "Feature matching": 45.57, | |
| "Grammar-Overall": 68.58, | |
| "Pronoun Reference": 79.04, | |
| "Consistency": 61.11, | |
| "Negation": 63.85, | |
| "Layout-Overall": 68.47, | |
| "2D": 72.79, | |
| "3D": 64.02, | |
| "Logical Reasoning": 39.55, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "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": 56.30, | |
| "Style": 82.00, | |
| "World Knowledge": 83.07, | |
| "Attribute-Overall": 63.25, | |
| "Quantity": 71.53, | |
| "Expression": 44.23, | |
| "Material": 55.19, | |
| "Size": 72.22, | |
| "Shape": 57.50, | |
| "Color": 89.17, | |
| "Action-Overall": 57.51, | |
| "Hand": 53.85, | |
| "Full body": 59.78, | |
| "Animal": 68.38, | |
| "Non Contact": 50.51, | |
| "Contact": 51.19, | |
| "State": 62.74, | |
| "Relationship-Overall": 62.44, | |
| "Composition": 60.47, | |
| "Similarity": 60.00, | |
| "Inclusion": 69.57, | |
| "Comparison": 60.16, | |
| "Compound-Overall": 44.72, | |
| "Imagination": 47.19, | |
| "Feature matching": 42.19, | |
| "Grammar-Overall": 54.81, | |
| "Pronoun Reference": 69.49, | |
| "Consistency": 56.02, | |
| "Negation": 38.46, | |
| "Layout-Overall": 69.22, | |
| "2D": 77.21, | |
| "3D": 60.98, | |
| "Logical Reasoning": 28.18, | |
| "Text": 17.82 | |
| }, | |
| { | |
| "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": 51.38, | |
| "Style": 94.10, | |
| "World Knowledge": 80.70, | |
| "Attribute-Overall": 62.71, | |
| "Quantity": 67.36, | |
| "Expression": 44.23, | |
| "Material": 71.70, | |
| "Size": 61.81, | |
| "Shape": 47.50, | |
| "Color": 86.67, | |
| "Action-Overall": 49.05, | |
| "Hand": 35.90, | |
| "Full body": 54.89, | |
| "Animal": 54.41, | |
| "Non Contact": 46.94, | |
| "Contact": 35.71, | |
| "State": 62.74, | |
| "Relationship-Overall": 59.64, | |
| "Composition": 60.14, | |
| "Similarity": 64.44, | |
| "Inclusion": 60.33, | |
| "Comparison": 50.78, | |
| "Compound-Overall": 41.62, | |
| "Imagination": 46.68, | |
| "Feature matching": 36.46, | |
| "Grammar-Overall": 55.48, | |
| "Pronoun Reference": 62.87, | |
| "Consistency": 57.87, | |
| "Negation": 45.77, | |
| "Layout-Overall": 44.78, | |
| "2D": 39.34, | |
| "3D": 50.38, | |
| "Logical Reasoning": 24.55, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "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": 51.23, | |
| "Style": 89.90, | |
| "World Knowledge": 73.58, | |
| "Attribute-Overall": 54.81, | |
| "Quantity": 37.50, | |
| "Expression": 37.82, | |
| "Material": 58.96, | |
| "Size": 65.97, | |
| "Shape": 47.50, | |
| "Color": 86.67, | |
| "Action-Overall": 50.38, | |
| "Hand": 32.69, | |
| "Full body": 51.63, | |
| "Animal": 61.76, | |
| "Non Contact": 48.47, | |
| "Contact": 38.10, | |
| "State": 66.51, | |
| "Relationship-Overall": 55.08, | |
| "Composition": 56.76, | |
| "Similarity": 53.89, | |
| "Inclusion": 59.24, | |
| "Comparison": 46.88, | |
| "Compound-Overall": 46.65, | |
| "Imagination": 58.16, | |
| "Feature matching": 34.90, | |
| "Grammar-Overall": 59.09, | |
| "Pronoun Reference": 66.18, | |
| "Consistency": 51.39, | |
| "Negation": 58.08, | |
| "Layout-Overall": 54.85, | |
| "2D": 57.72, | |
| "3D": 51.89, | |
| "Logical Reasoning": 26.82, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "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": 46.39, | |
| "Style": 86.20, | |
| "World Knowledge": 62.50, | |
| "Attribute-Overall": 47.97, | |
| "Quantity": 43.06, | |
| "Expression": 30.77, | |
| "Material": 55.19, | |
| "Size": 55.56, | |
| "Shape": 30.00, | |
| "Color": 78.33, | |
| "Action-Overall": 43.35, | |
| "Hand": 23.08, | |
| "Full body": 48.37, | |
| "Animal": 58.82, | |
| "Non Contact": 36.73, | |
| "Contact": 36.31, | |
| "State": 55.66, | |
| "Relationship-Overall": 50.00, | |
| "Composition": 59.80, | |
| "Similarity": 38.89, | |
| "Inclusion": 51.63, | |
| "Comparison": 40.62, | |
| "Compound-Overall": 45.10, | |
| "Imagination": 57.65, | |
| "Feature matching": 32.29, | |
| "Grammar-Overall": 60.29, | |
| "Pronoun Reference": 66.18, | |
| "Consistency": 48.61, | |
| "Negation": 63.85, | |
| "Layout-Overall": 46.46, | |
| "2D": 49.26, | |
| "3D": 43.56, | |
| "Logical Reasoning": 21.14, | |
| "Text": 0.86 | |
| }, | |
| { | |
| "model": "Emu3", | |
| "link": "https://arxiv.org/pdf/2409.18869", | |
| "hf": "https://huggingface.co/BAAI/Emu3-Gen", | |
| "open_source": true, | |
| "release_date": "2024-09", | |
| "Overall": 46.02, | |
| "Style": 86.80, | |
| "World Knowledge": 77.06, | |
| "Attribute-Overall": 51.39, | |
| "Quantity": 44.44, | |
| "Expression": 45.51, | |
| "Material": 53.77, | |
| "Size": 43.06, | |
| "Shape": 46.25, | |
| "Color": 80.00, | |
| "Action-Overall": 40.11, | |
| "Hand": 25.00, | |
| "Full body": 47.28, | |
| "Animal": 50.74, | |
| "Non Contact": 35.20, | |
| "Contact": 27.98, | |
| "State": 52.36, | |
| "Relationship-Overall": 49.75, | |
| "Composition": 56.76, | |
| "Similarity": 46.67, | |
| "Inclusion": 48.37, | |
| "Comparison": 39.84, | |
| "Compound-Overall": 36.86, | |
| "Imagination": 41.33, | |
| "Feature matching": 32.29, | |
| "Grammar-Overall": 52.94, | |
| "Pronoun Reference": 59.56, | |
| "Consistency": 53.70, | |
| "Negation": 45.38, | |
| "Layout-Overall": 44.78, | |
| "2D": 45.22, | |
| "3D": 44.32, | |
| "Logical Reasoning": 19.32, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "Playground2.5", | |
| "link": "https://arxiv.org/pdf/2402.17245", | |
| "hf": "https://huggingface.co/playgroundai/playground-v2.5-1024px-aesthetic", | |
| "open_source": true, | |
| "release_date": "2024-02", | |
| "Overall": 45.61, | |
| "Style": 89.50, | |
| "World Knowledge": 76.11, | |
| "Attribute-Overall": 52.78, | |
| "Quantity": 58.33, | |
| "Expression": 43.59, | |
| "Material": 57.08, | |
| "Size": 44.44, | |
| "Shape": 41.25, | |
| "Color": 75.83, | |
| "Action-Overall": 42.68, | |
| "Hand": 28.85, | |
| "Full body": 50.00, | |
| "Animal": 52.21, | |
| "Non Contact": 35.20, | |
| "Contact": 29.17, | |
| "State": 58.02, | |
| "Relationship-Overall": 51.52, | |
| "Composition": 60.14, | |
| "Similarity": 49.44, | |
| "Inclusion": 48.37, | |
| "Comparison": 39.06, | |
| "Compound-Overall": 35.44, | |
| "Imagination": 43.88, | |
| "Feature matching": 26.82, | |
| "Grammar-Overall": 53.21, | |
| "Pronoun Reference": 58.82, | |
| "Consistency": 50.00, | |
| "Negation": 50.00, | |
| "Layout-Overall": 37.13, | |
| "2D": 34.56, | |
| "3D": 39.77, | |
| "Logical Reasoning": 16.59, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "SDXL", | |
| "link": "https://arxiv.org/pdf/2307.01952", | |
| "hf": "https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0", | |
| "open_source": true, | |
| "release_date": "2023-07", | |
| "Overall": 39.75, | |
| "Style": 87.40, | |
| "World Knowledge": 72.63, | |
| "Attribute-Overall": 44.34, | |
| "Quantity": 44.44, | |
| "Expression": 25.00, | |
| "Material": 52.83, | |
| "Size": 44.44, | |
| "Shape": 33.75, | |
| "Color": 68.33, | |
| "Action-Overall": 34.22, | |
| "Hand": 19.23, | |
| "Full body": 35.33, | |
| "Animal": 43.38, | |
| "Non Contact": 26.53, | |
| "Contact": 24.40, | |
| "State": 53.30, | |
| "Relationship-Overall": 44.92, | |
| "Composition": 53.72, | |
| "Similarity": 38.33, | |
| "Inclusion": 39.67, | |
| "Comparison": 41.41, | |
| "Compound-Overall": 26.68, | |
| "Imagination": 33.93, | |
| "Feature matching": 19.27, | |
| "Grammar-Overall": 47.33, | |
| "Pronoun Reference": 50.37, | |
| "Consistency": 42.59, | |
| "Negation": 48.08, | |
| "Layout-Overall": 29.85, | |
| "2D": 26.47, | |
| "3D": 33.33, | |
| "Logical Reasoning": 9.55, | |
| "Text": 1.15 | |
| }, | |
| { | |
| "model": "GPT-4o", | |
| "link": "https://platform.openai.com/docs/guides/image-generation", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-03", | |
| "Overall": 92.77, | |
| "Style": 98.57, | |
| "World Knowledge": 98.87, | |
| "Attribute-Overall": 93.59, | |
| "Quantity": 90.00, | |
| "Expression": 94.70, | |
| "Material": 94.20, | |
| "Size": 91.61, | |
| "Shape": 92.50, | |
| "Color": 99.17, | |
| "Action-Overall": 90.79, | |
| "Hand": 89.74, | |
| "Full body": 92.22, | |
| "Animal": 87.12, | |
| "Non Contact": 90.43, | |
| "Contact": 89.82, | |
| "State": 93.75, | |
| "Relationship-Overall": 94.97, | |
| "Composition": 96.23, | |
| "Similarity": 95.00, | |
| "Inclusion": 94.89, | |
| "Comparison": 92.19, | |
| "Compound-Overall": 93.55, | |
| "Imagination": 95.64, | |
| "Feature matching": 91.40, | |
| "Grammar-Overall": 91.76, | |
| "Pronoun Reference": 92.91, | |
| "Consistency": 91.67, | |
| "Negation": 90.57, | |
| "Layout-Overall": 91.35, | |
| "2D": 91.04, | |
| "3D": 91.67, | |
| "Logical Reasoning": 84.97, | |
| "Text": 89.24 | |
| }, | |
| { | |
| "model": "Imagen-4.0-Ultra-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 91.54, | |
| "Style": 99.20, | |
| "World Knowledge": 97.47, | |
| "Attribute-Overall": 92.52, | |
| "Quantity": 93.06, | |
| "Expression": 81.41, | |
| "Material": 94.34, | |
| "Size": 95.83, | |
| "Shape": 91.88, | |
| "Color": 100.0, | |
| "Action-Overall": 92.20, | |
| "Hand": 90.38, | |
| "Full body": 93.44, | |
| "Animal": 91.91, | |
| "Non Contact": 90.31, | |
| "Contact": 89.29, | |
| "State": 96.70, | |
| "Relationship-Overall": 93.02, | |
| "Composition": 95.27, | |
| "Similarity": 84.44, | |
| "Inclusion": 98.37, | |
| "Comparison": 92.19, | |
| "Compound-Overall": 91.37, | |
| "Imagination": 92.86, | |
| "Feature matching": 89.84, | |
| "Grammar-Overall": 87.97, | |
| "Pronoun Reference": 94.12, | |
| "Consistency": 87.04, | |
| "Negation": 82.31, | |
| "Layout-Overall": 93.10, | |
| "2D": 92.65, | |
| "3D": 93.56, | |
| "Logical Reasoning": 79.55, | |
| "Text": 89.08 | |
| }, | |
| { | |
| "model": "Seedream-3.0", | |
| "link": "https://www.byteplus.com/en/product/Seedream", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 78.95, | |
| "Style": 98.10, | |
| "World Knowledge": 95.25, | |
| "Attribute-Overall": 85.58, | |
| "Quantity": 80.56, | |
| "Expression": 82.05, | |
| "Material": 90.57, | |
| "Size": 85.42, | |
| "Shape": 78.12, | |
| "Color": 97.50, | |
| "Action-Overall": 82.98, | |
| "Hand": 75.00, | |
| "Full body": 89.67, | |
| "Animal": 85.29, | |
| "Non Contact": 75.51, | |
| "Contact": 80.95, | |
| "State": 90.09, | |
| "Relationship-Overall": 80.84, | |
| "Composition": 82.77, | |
| "Similarity": 73.89, | |
| "Inclusion": 84.24, | |
| "Comparison": 81.25, | |
| "Compound-Overall": 73.84, | |
| "Imagination": 78.57, | |
| "Feature matching": 69.01, | |
| "Grammar-Overall": 61.36, | |
| "Pronoun Reference": 79.78, | |
| "Consistency": 69.91, | |
| "Negation": 35.00, | |
| "Layout-Overall": 87.31, | |
| "2D": 86.76, | |
| "3D": 87.88, | |
| "Logical Reasoning": 52.73, | |
| "Text": 71.55 | |
| }, | |
| { | |
| "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": "DALL-E-3", | |
| "link": "https://openai.com/zh-Hans-CN/index/dall-e-3/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2023-09", | |
| "Overall": 69.18, | |
| "Style": 95.06, | |
| "World Knowledge": 93.51, | |
| "Attribute-Overall": 75.97, | |
| "Quantity": 62.14, | |
| "Expression": 59.87, | |
| "Material": 87.74, | |
| "Size": 87.50, | |
| "Shape": 65.00, | |
| "Color": 92.50, | |
| "Action-Overall": 69.83, | |
| "Hand": 60.90, | |
| "Full body": 75.00, | |
| "Animal": 76.47, | |
| "Non Contact": 66.84, | |
| "Contact": 63.41, | |
| "State": 75.47, | |
| "Relationship-Overall": 78.06, | |
| "Composition": 82.43, | |
| "Similarity": 69.44, | |
| "Inclusion": 87.78, | |
| "Comparison": 66.41, | |
| "Compound-Overall": 70.60, | |
| "Imagination": 76.79, | |
| "Feature matching": 64.21, | |
| "Grammar-Overall": 68.07, | |
| "Pronoun Reference": 74.24, | |
| "Consistency": 74.07, | |
| "Negation": 56.64, | |
| "Layout-Overall": 66.67, | |
| "2D": 57.72, | |
| "3D": 76.17, | |
| "Logical Reasoning": 48.18, | |
| "Text": 25.86 | |
| }, | |
| { | |
| "model": "FLUX-pro-1.1-Ultra", | |
| "link": "https://bfl.ai/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-11", | |
| "Overall": 70.67, | |
| "Style": 90.60, | |
| "World Knowledge": 91.61, | |
| "Attribute-Overall": 76.50, | |
| "Quantity": 75.69, | |
| "Expression": 59.62, | |
| "Material": 78.77, | |
| "Size": 77.78, | |
| "Shape": 74.38, | |
| "Color": 96.67, | |
| "Action-Overall": 76.50, | |
| "Hand": 57.69, | |
| "Full body": 68.48, | |
| "Animal": 77.21, | |
| "Non Contact": 76.53, | |
| "Contact": 64.29, | |
| "State": 76.89, | |
| "Relationship-Overall": 77.54, | |
| "Composition": 80.41, | |
| "Similarity": 72.78, | |
| "Inclusion": 82.07, | |
| "Comparison": 71.09, | |
| "Compound-Overall": 67.78, | |
| "Imagination": 74.74, | |
| "Feature matching": 60.68, | |
| "Grammar-Overall": 70.05, | |
| "Pronoun Reference": 84.56, | |
| "Consistency": 68.98, | |
| "Negation": 55.77, | |
| "Layout-Overall": 81.53, | |
| "2D": 80.15, | |
| "3D": 82.95, | |
| "Logical Reasoning": 43.18, | |
| "Text": 37.36 | |
| }, | |
| { | |
| "model": "Keling-Ketu", | |
| "link": "https://kolors.kuaishou.com/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-04", | |
| "Overall": 65.93, | |
| "Style": 92.27, | |
| "World Knowledge": 86.62, | |
| "Attribute-Overall": 71.66, | |
| "Quantity": 75.00, | |
| "Expression": 56.41, | |
| "Material": 78.77, | |
| "Size": 79.17, | |
| "Shape": 53.12, | |
| "Color": 91.38, | |
| "Action-Overall": 68.73, | |
| "Hand": 54.49, | |
| "Full body": 76.09, | |
| "Animal": 72.79, | |
| "Non Contact": 69.90, | |
| "Contact": 58.93, | |
| "State": 76.89, | |
| "Relationship-Overall": 70.94, | |
| "Composition": 68.92, | |
| "Similarity": 70.56, | |
| "Inclusion": 74.46, | |
| "Comparison": 71.09, | |
| "Compound-Overall": 60.81, | |
| "Imagination": 66.24, | |
| "Feature matching": 55.26, | |
| "Grammar-Overall": 71.26, | |
| "Pronoun Reference": 77.21, | |
| "Consistency": 67.59, | |
| "Negation": 68.08, | |
| "Layout-Overall": 77.23, | |
| "2D": 80.97, | |
| "3D": 73.36, | |
| "Logical Reasoning": 43.75, | |
| "Text": 16.03 | |
| }, | |
| { | |
| "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": 78.81, | |
| "Style": 95.10, | |
| "World Knowledge": 94.30, | |
| "Attribute-Overall": 87.61, | |
| "Quantity": 81.94, | |
| "Expression": 84.62, | |
| "Material": 91.98, | |
| "Size": 84.03, | |
| "Shape": 84.38, | |
| "Color": 99.17, | |
| "Action-Overall": 84.13, | |
| "Hand": 82.05, | |
| "Full body": 88.59, | |
| "Animal": 88.24, | |
| "Non Contact": 80.61, | |
| "Contact": 77.38, | |
| "State": 87.74, | |
| "Relationship-Overall": 79.70, | |
| "Composition": 81.76, | |
| "Similarity": 67.78, | |
| "Inclusion": 86.96, | |
| "Comparison": 81.25, | |
| "Compound-Overall": 73.32, | |
| "Imagination": 73.21, | |
| "Feature matching": 73.44, | |
| "Grammar-Overall": 60.29, | |
| "Pronoun Reference": 83.82, | |
| "Consistency": 70.37, | |
| "Negation": 27.31, | |
| "Layout-Overall": 85.52, | |
| "2D": 86.40, | |
| "3D": 85.23, | |
| "Logical Reasoning": 53.64, | |
| "Text": 76.14 | |
| } | |
| ] | |
| } | |