| { | |
| "leaderboard": [ | |
| { | |
| "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": 90.31, | |
| "Style": 99.17, | |
| "World Knowledge": 96.39, | |
| "Attribute-Overall": 94.57, | |
| "Quantity": 82.98, | |
| "Expression": 88.47, | |
| "Material": 95.78, | |
| "Size": 92.42, | |
| "Shape": 91.43, | |
| "Color": 98.69, | |
| "Action-Overall": 86.17, | |
| "Hand": 84.94, | |
| "Full body": 85.94, | |
| "Animal": 85.51, | |
| "Non Contact": 86.16, | |
| "Contact": 82.47, | |
| "State": 88.10, | |
| "Relationship-Overall": 91.70, | |
| "Composition": 91.33, | |
| "Similarity": 89.42, | |
| "Inclusion": 95.69, | |
| "Comparison": 90.78, | |
| "Compound-Overall": 90.16, | |
| "Imagination": 89.94, | |
| "Feature matching": 90.65, | |
| "Grammar-Overall": 84.52, | |
| "Pronoun Reference": 94.84, | |
| "Consistency": 82.94, | |
| "Negation": 76.76, | |
| "Layout-Overall": 92.22, | |
| "2D": 92.94, | |
| "3D": 91.30, | |
| "Logical Reasoning": 79.90, | |
| "Text": 88.32 | |
| }, | |
| { | |
| "model": "Nano Banana Pro", | |
| "link": "https://nano-banana.pro", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-11", | |
| "Overall": 94.20, | |
| "Style": 99.58, | |
| "World Knowledge": 97.83, | |
| "Attribute-Overall": 95.94, | |
| "Quantity": 89.36, | |
| "Expression": 90.69, | |
| "Material": 97.52, | |
| "Size": 96.97, | |
| "Shape": 91.43, | |
| "Color": 95.53, | |
| "Action-Overall": 89.19, | |
| "Hand": 86.22, | |
| "Full body": 89.69, | |
| "Animal": 90.94, | |
| "Non Contact": 89.29, | |
| "Contact": 89.37, | |
| "State": 89.38, | |
| "Relationship-Overall": 94.29, | |
| "Composition": 94.39, | |
| "Similarity": 91.99, | |
| "Inclusion": 98.28, | |
| "Comparison": 92.48, | |
| "Compound-Overall": 94.10, | |
| "Imagination": 94.92, | |
| "Feature matching": 92.29, | |
| "Grammar-Overall": 93.15, | |
| "Pronoun Reference": 99.60, | |
| "Consistency": 90.08, | |
| "Negation": 90.14, | |
| "Layout-Overall": 93.73, | |
| "2D": 93.79, | |
| "3D": 93.66, | |
| "Logical Reasoning": 87.75, | |
| "Text": 96.47 | |
| }, | |
| { | |
| "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": 80.71, | |
| "Style": 93.19, | |
| "World Knowledge": 93.93, | |
| "Attribute-Overall": 89.34, | |
| "Quantity": 82.98, | |
| "Expression": 76.11, | |
| "Material": 91.72, | |
| "Size": 87.50, | |
| "Shape": 80.77, | |
| "Color": 96.38, | |
| "Action-Overall": 74.20, | |
| "Hand": 75.64, | |
| "Full body": 74.06, | |
| "Animal": 71.01, | |
| "Non Contact": 71.43, | |
| "Contact": 66.38, | |
| "State": 77.98, | |
| "Relationship-Overall": 80.44, | |
| "Composition": 78.32, | |
| "Similarity": 73.08, | |
| "Inclusion": 87.93, | |
| "Comparison": 83.74, | |
| "Compound-Overall": 76.46, | |
| "Imagination": 77.75, | |
| "Feature matching": 73.60, | |
| "Grammar-Overall": 76.65, | |
| "Pronoun Reference": 91.27, | |
| "Consistency": 69.84, | |
| "Negation": 69.72, | |
| "Layout-Overall": 86.67, | |
| "2D": 87.71, | |
| "3D": 85.33, | |
| "Logical Reasoning": 66.18, | |
| "Text": 70.11 | |
| }, | |
| { | |
| "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": 84.34, | |
| "Style": 96.75, | |
| "World Knowledge": 95.52, | |
| "Attribute-Overall": 91.40, | |
| "Quantity": 85.64, | |
| "Expression": 81.01, | |
| "Material": 94.03, | |
| "Size": 88.17, | |
| "Shape": 87.50, | |
| "Color": 96.11, | |
| "Action-Overall": 77.55, | |
| "Hand": 73.08, | |
| "Full body": 82.91, | |
| "Animal": 77.21, | |
| "Non Contact": 71.76, | |
| "Contact": 69.83, | |
| "State": 81.27, | |
| "Relationship-Overall": 86.96, | |
| "Composition": 85.26, | |
| "Similarity": 81.41, | |
| "Inclusion": 94.48, | |
| "Comparison": 88.11, | |
| "Compound-Overall": 85.60, | |
| "Imagination": 87.55, | |
| "Feature matching": 81.31, | |
| "Grammar-Overall": 78.06, | |
| "Pronoun Reference": 92.86, | |
| "Consistency": 77.42, | |
| "Negation": 65.49, | |
| "Layout-Overall": 87.18, | |
| "2D": 88.28, | |
| "3D": 85.77, | |
| "Logical Reasoning": 71.32, | |
| "Text": 73.10 | |
| }, | |
| { | |
| "model": "Emu3", | |
| "link": "https://arxiv.org/pdf/2409.18869", | |
| "hf": "https://huggingface.co/BAAI/Emu3-Gen", | |
| "open_source": true, | |
| "release_date": "2024-09", | |
| "Overall": 50.95, | |
| "Style": 89.36, | |
| "World Knowledge": 76.16, | |
| "Attribute-Overall": 66.81, | |
| "Quantity": 44.68, | |
| "Expression": 48.47, | |
| "Material": 68.65, | |
| "Size": 73.24, | |
| "Shape": 54.29, | |
| "Color": 76.61, | |
| "Action-Overall": 43.80, | |
| "Hand": 28.85, | |
| "Full body": 46.25, | |
| "Animal": 43.48, | |
| "Non Contact": 30.49, | |
| "Contact": 25.57, | |
| "State": 56.92, | |
| "Relationship-Overall": 51.70, | |
| "Composition": 53.77, | |
| "Similarity": 42.31, | |
| "Inclusion": 59.48, | |
| "Comparison": 53.77, | |
| "Compound-Overall": 46.00, | |
| "Imagination": 51.69, | |
| "Feature matching": 33.41, | |
| "Grammar-Overall": 50.25, | |
| "Pronoun Reference": 55.95, | |
| "Consistency": 42.46, | |
| "Negation": 52.11, | |
| "Layout-Overall": 56.67, | |
| "2D": 56.36, | |
| "3D": 57.07, | |
| "Logical Reasoning": 27.43, | |
| "Text": 1.36 | |
| }, | |
| { | |
| "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": 69.60, | |
| "Style": 93.19, | |
| "World Knowledge": 84.10, | |
| "Attribute-Overall": 79.94, | |
| "Quantity": 66.49, | |
| "Expression": 72.64, | |
| "Material": 77.11, | |
| "Size": 81.06, | |
| "Shape": 72.38, | |
| "Color": 87.95, | |
| "Action-Overall": 65.81, | |
| "Hand": 63.78, | |
| "Full body": 64.38, | |
| "Animal": 67.03, | |
| "Non Contact": 62.95, | |
| "Contact": 55.17, | |
| "State": 70.85, | |
| "Relationship-Overall": 68.91, | |
| "Composition": 66.96, | |
| "Similarity": 67.31, | |
| "Inclusion": 72.99, | |
| "Comparison": 70.39, | |
| "Compound-Overall": 71.37, | |
| "Imagination": 74.16, | |
| "Feature matching": 65.19, | |
| "Grammar-Overall": 75.13, | |
| "Pronoun Reference": 84.13, | |
| "Consistency": 69.44, | |
| "Negation": 72.18, | |
| "Layout-Overall": 79.60, | |
| "2D": 83.33, | |
| "3D": 74.82, | |
| "Logical Reasoning": 57.04, | |
| "Text": 20.92 | |
| }, | |
| { | |
| "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": 76.41, | |
| "Style": 96.10, | |
| "World Knowledge": 90.17, | |
| "Attribute-Overall": 90.24, | |
| "Quantity": 73.40, | |
| "Expression": 82.08, | |
| "Material": 92.39, | |
| "Size": 89.20, | |
| "Shape": 84.44, | |
| "Color": 95.49, | |
| "Action-Overall": 73.56, | |
| "Hand": 72.12, | |
| "Full body": 76.56, | |
| "Animal": 73.19, | |
| "Non Contact": 66.96, | |
| "Contact": 65.23, | |
| "State": 77.47, | |
| "Relationship-Overall": 82.81, | |
| "Composition": 83.80, | |
| "Similarity": 78.21, | |
| "Inclusion": 84.77, | |
| "Comparison": 82.77, | |
| "Compound-Overall": 84.88, | |
| "Imagination": 85.44, | |
| "Feature matching": 83.64, | |
| "Grammar-Overall": 82.36, | |
| "Pronoun Reference": 86.11, | |
| "Consistency": 83.33, | |
| "Negation": 78.17, | |
| "Layout-Overall": 86.43, | |
| "2D": 88.70, | |
| "3D": 83.51, | |
| "Logical Reasoning": 69.42, | |
| "Text": 8.15 | |
| }, | |
| { | |
| "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": 64.67, | |
| "Style": 92.19, | |
| "World Knowledge": 86.56, | |
| "Attribute-Overall": 80.24, | |
| "Quantity": 61.70, | |
| "Expression": 62.64, | |
| "Material": 83.73, | |
| "Size": 82.01, | |
| "Shape": 73.60, | |
| "Color": 87.79, | |
| "Action-Overall": 58.59, | |
| "Hand": 58.01, | |
| "Full body": 56.56, | |
| "Animal": 54.35, | |
| "Non Contact": 42.86, | |
| "Contact": 46.55, | |
| "State": 68.18, | |
| "Relationship-Overall": 69.88, | |
| "Composition": 70.15, | |
| "Similarity": 62.82, | |
| "Inclusion": 75.86, | |
| "Comparison": 69.66, | |
| "Compound-Overall": 62.86, | |
| "Imagination": 65.61, | |
| "Feature matching": 56.78, | |
| "Grammar-Overall": 65.86, | |
| "Pronoun Reference": 79.37, | |
| "Consistency": 61.11, | |
| "Negation": 58.10, | |
| "Layout-Overall": 73.25, | |
| "2D": 73.59, | |
| "3D": 72.83, | |
| "Logical Reasoning": 45.87, | |
| "Text": 11.41 | |
| }, | |
| { | |
| "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": 71.81, | |
| "Style": 86.88, | |
| "World Knowledge": 88.58, | |
| "Attribute-Overall": 83.71, | |
| "Quantity": 74.47, | |
| "Expression": 76.11, | |
| "Material": 80.80, | |
| "Size": 84.47, | |
| "Shape": 78.67, | |
| "Color": 90.83, | |
| "Action-Overall": 69.66, | |
| "Hand": 67.63, | |
| "Full body": 71.56, | |
| "Animal": 72.46, | |
| "Non Contact": 65.18, | |
| "Contact": 57.18, | |
| "State": 74.21, | |
| "Relationship-Overall": 73.33, | |
| "Composition": 69.77, | |
| "Similarity": 72.76, | |
| "Inclusion": 82.18, | |
| "Comparison": 73.06, | |
| "Compound-Overall": 74.93, | |
| "Imagination": 77.00, | |
| "Feature matching": 70.33, | |
| "Grammar-Overall": 74.49, | |
| "Pronoun Reference": 89.68, | |
| "Consistency": 66.67, | |
| "Negation": 67.96, | |
| "Layout-Overall": 84.84, | |
| "2D": 90.11, | |
| "3D": 78.08, | |
| "Logical Reasoning": 58.01, | |
| "Text": 23.64 | |
| }, | |
| { | |
| "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": 40.10, | |
| "Style": 75.83, | |
| "World Knowledge": 52.75, | |
| "Attribute-Overall": 49.90, | |
| "Quantity": 50.53, | |
| "Expression": 37.22, | |
| "Material": 47.52, | |
| "Size": 54.55, | |
| "Shape": 40.56, | |
| "Color": 57.81, | |
| "Action-Overall": 32.42, | |
| "Hand": 16.67, | |
| "Full body": 30.63, | |
| "Animal": 38.77, | |
| "Non Contact": 19.64, | |
| "Contact": 17.24, | |
| "State": 44.17, | |
| "Relationship-Overall": 39.06, | |
| "Composition": 39.16, | |
| "Similarity": 33.97, | |
| "Inclusion": 48.56, | |
| "Comparison": 34.71, | |
| "Compound-Overall": 38.37, | |
| "Imagination": 45.99, | |
| "Feature matching": 21.50, | |
| "Grammar-Overall": 50.00, | |
| "Pronoun Reference": 53.97, | |
| "Consistency": 39.29, | |
| "Negation": 55.99, | |
| "Layout-Overall": 43.02, | |
| "2D": 47.46, | |
| "3D": 37.32, | |
| "Logical Reasoning": 19.42, | |
| "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": 71.39, | |
| "Style": 94.35, | |
| "World Knowledge": 84.83, | |
| "Attribute-Overall": 83.03, | |
| "Quantity": 66.49, | |
| "Expression": 73.89, | |
| "Material": 81.78, | |
| "Size": 81.63, | |
| "Shape": 77.80, | |
| "Color": 90.93, | |
| "Action-Overall": 66.57, | |
| "Hand": 67.31, | |
| "Full body": 64.06, | |
| "Animal": 65.22, | |
| "Non Contact": 64.29, | |
| "Contact": 54.60, | |
| "State": 72.13, | |
| "Relationship-Overall": 73.06, | |
| "Composition": 67.73, | |
| "Similarity": 72.76, | |
| "Inclusion": 81.90, | |
| "Comparison": 75.97, | |
| "Compound-Overall": 70.49, | |
| "Imagination": 72.47, | |
| "Feature matching": 66.12, | |
| "Grammar-Overall": 76.40, | |
| "Pronoun Reference": 84.52, | |
| "Consistency": 75.79, | |
| "Negation": 69.72, | |
| "Layout-Overall": 80.63, | |
| "2D": 82.20, | |
| "3D": 78.62, | |
| "Logical Reasoning": 56.55, | |
| "Text": 27.99 | |
| }, | |
| { | |
| "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": 78.45, | |
| "Style": 94.10, | |
| "World Knowledge": 93.79, | |
| "Attribute-Overall": 89.55, | |
| "Quantity": 81.38, | |
| "Expression": 76.81, | |
| "Material": 91.34, | |
| "Size": 88.64, | |
| "Shape": 85.31, | |
| "Color": 95.44, | |
| "Action-Overall": 76.28, | |
| "Hand": 75.00, | |
| "Full body": 76.25, | |
| "Animal": 72.46, | |
| "Non Contact": 69.20, | |
| "Contact": 72.99, | |
| "State": 80.43, | |
| "Relationship-Overall": 81.73, | |
| "Composition": 80.87, | |
| "Similarity": 73.08, | |
| "Inclusion": 88.22, | |
| "Comparison": 84.47, | |
| "Compound-Overall": 80.67, | |
| "Imagination": 80.59, | |
| "Feature matching": 80.84, | |
| "Grammar-Overall": 75.25, | |
| "Pronoun Reference": 91.27, | |
| "Consistency": 74.21, | |
| "Negation": 61.97, | |
| "Layout-Overall": 86.59, | |
| "2D": 85.45, | |
| "3D": 86.59, | |
| "Logical Reasoning": 65.53, | |
| "Text": 41.03 | |
| }, | |
| { | |
| "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": 67.28, | |
| "Style": 92.77, | |
| "World Knowledge": 88.44, | |
| "Attribute-Overall": 81.06, | |
| "Quantity": 70.74, | |
| "Expression": 66.67, | |
| "Material": 82.83, | |
| "Size": 82.95, | |
| "Shape": 71.15, | |
| "Color": 88.73, | |
| "Action-Overall": 63.28, | |
| "Hand": 58.65, | |
| "Full body": 60.13, | |
| "Animal": 67.75, | |
| "Non Contact": 58.48, | |
| "Contact": 52.87, | |
| "State": 69.07, | |
| "Relationship-Overall": 70.04, | |
| "Composition": 66.20, | |
| "Similarity": 67.63, | |
| "Inclusion": 78.45, | |
| "Comparison": 72.09, | |
| "Compound-Overall": 66.13, | |
| "Imagination": 68.57, | |
| "Feature matching": 60.75, | |
| "Grammar-Overall": 68.53, | |
| "Pronoun Reference": 76.59, | |
| "Consistency": 71.43, | |
| "Negation": 58.80, | |
| "Layout-Overall": 77.54, | |
| "2D": 80.93, | |
| "3D": 73.19, | |
| "Logical Reasoning": 51.46, | |
| "Text": 13.59 | |
| }, | |
| { | |
| "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": 70.33, | |
| "Style": 93.11, | |
| "World Knowledge": 88.44, | |
| "Attribute-Overall": 86.35, | |
| "Quantity": 59.04, | |
| "Expression": 71.53, | |
| "Material": 88.10, | |
| "Size": 87.31, | |
| "Shape": 81.12, | |
| "Color": 94.71, | |
| "Action-Overall": 69.02, | |
| "Hand": 53.85, | |
| "Full body": 80.00, | |
| "Animal": 69.20, | |
| "Non Contact": 60.27, | |
| "Contact": 55.75, | |
| "State": 76.68, | |
| "Relationship-Overall": 77.37, | |
| "Composition": 77.42, | |
| "Similarity": 68.59, | |
| "Inclusion": 80.17, | |
| "Comparison": 81.55, | |
| "Compound-Overall": 76.45, | |
| "Imagination": 77.64, | |
| "Feature matching": 73.83, | |
| "Grammar-Overall": 70.30, | |
| "Pronoun Reference": 87.30, | |
| "Consistency": 66.67, | |
| "Negation": 58.45, | |
| "Layout-Overall": 80.63, | |
| "2D": 80.08, | |
| "3D": 81.34, | |
| "Logical Reasoning": 59.71, | |
| "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": 62.92, | |
| "Style": 94.93, | |
| "World Knowledge": 83.67, | |
| "Attribute-Overall": 74.90, | |
| "Quantity": 61.70, | |
| "Expression": 66.39, | |
| "Material": 78.09, | |
| "Size": 82.58, | |
| "Shape": 62.24, | |
| "Color": 78.88, | |
| "Action-Overall": 58.95, | |
| "Hand": 37.82, | |
| "Full body": 59.06, | |
| "Animal": 62.32, | |
| "Non Contact": 50.89, | |
| "Contact": 43.97, | |
| "State": 71.44, | |
| "Relationship-Overall": 65.36, | |
| "Composition": 67.47, | |
| "Similarity": 62.82, | |
| "Inclusion": 63.22, | |
| "Comparison": 65.05, | |
| "Compound-Overall": 63.59, | |
| "Imagination": 72.57, | |
| "Feature matching": 43.69, | |
| "Grammar-Overall": 63.58, | |
| "Pronoun Reference": 74.21, | |
| "Consistency": 67.46, | |
| "Negation": 50.70, | |
| "Layout-Overall": 74.29, | |
| "2D": 75.28, | |
| "3D": 73.01, | |
| "Logical Reasoning": 48.06, | |
| "Text": 1.90 | |
| }, | |
| { | |
| "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": 71.26, | |
| "Style": 92.44, | |
| "World Knowledge": 89.31, | |
| "Attribute-Overall": 84.21, | |
| "Quantity": 69.68, | |
| "Expression": 70.28, | |
| "Material": 85.17, | |
| "Size": 86.17, | |
| "Shape": 76.92, | |
| "Color": 91.88, | |
| "Action-Overall": 67.62, | |
| "Hand": 68.59, | |
| "Full body": 67.19, | |
| "Animal": 68.48, | |
| "Non Contact": 58.48, | |
| "Contact": 59.77, | |
| "State": 71.94, | |
| "Relationship-Overall": 75.70, | |
| "Composition": 72.19, | |
| "Similarity": 72.12, | |
| "Inclusion": 85.92, | |
| "Comparison": 76.46, | |
| "Compound-Overall": 74.71, | |
| "Imagination": 77.32, | |
| "Feature matching": 68.93, | |
| "Grammar-Overall": 74.75, | |
| "Pronoun Reference": 87.30, | |
| "Consistency": 70.63, | |
| "Negation": 67.25, | |
| "Layout-Overall": 81.90, | |
| "2D": 83.47, | |
| "3D": 79.89, | |
| "Logical Reasoning": 59.71, | |
| "Text": 12.23 | |
| }, | |
| { | |
| "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": 67.00, | |
| "Style": 80.15, | |
| "World Knowledge": 82.37, | |
| "Attribute-Overall": 79.82, | |
| "Quantity": 66.49, | |
| "Expression": 70.83, | |
| "Material": 81.33, | |
| "Size": 81.44, | |
| "Shape": 69.93, | |
| "Color": 86.01, | |
| "Action-Overall": 61.96, | |
| "Hand": 58.97, | |
| "Full body": 63.44, | |
| "Animal": 62.68, | |
| "Non Contact": 56.25, | |
| "Contact": 48.56, | |
| "State": 68.08, | |
| "Relationship-Overall": 64.28, | |
| "Composition": 59.69, | |
| "Similarity": 58.97, | |
| "Inclusion": 67.53, | |
| "Comparison": 74.27, | |
| "Compound-Overall": 64.17, | |
| "Imagination": 65.51, | |
| "Feature matching": 61.21, | |
| "Grammar-Overall": 68.78, | |
| "Pronoun Reference":82.14, | |
| "Consistency": 61.90, | |
| "Negation": 63.03, | |
| "Layout-Overall": 73.33, | |
| "2D": 78.25, | |
| "3D": 67.03, | |
| "Logical Reasoning": 51.70, | |
| "Text": 43.48 | |
| }, | |
| { | |
| "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": 74.25, | |
| "Style": 93.11, | |
| "World Knowledge": 92.63, | |
| "Attribute-Overall": 83.49, | |
| "Quantity": 73.40, | |
| "Expression": 68.47, | |
| "Material": 83.51, | |
| "Size": 84.47, | |
| "Shape": 75.70, | |
| "Color": 92.19, | |
| "Action-Overall": 68.82, | |
| "Hand": 65.06, | |
| "Full body": 68.44, | |
| "Animal": 62.32, | |
| "Non Contact": 71.43, | |
| "Contact": 57.47, | |
| "State": 75.20, | |
| "Relationship-Overall": 74.30, | |
| "Composition": 72.07, | |
| "Similarity": 73.40, | |
| "Inclusion": 78.74, | |
| "Comparison": 75.49, | |
| "Compound-Overall": 69.77, | |
| "Imagination": 73.63, | |
| "Feature matching": 61.21, | |
| "Grammar-Overall": 72.59, | |
| "Pronoun Reference": 86.51, | |
| "Consistency": 69.84, | |
| "Negation": 62.68, | |
| "Layout-Overall": 79.92, | |
| "2D": 82.63, | |
| "3D": 76.45, | |
| "Logical Reasoning": 50.24, | |
| "Text": 57.61 | |
| }, | |
| { | |
| "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": 82.19, | |
| "Style": 94.52, | |
| "World Knowledge": 93.35, | |
| "Attribute-Overall": 92.81, | |
| "Quantity": 86.17, | |
| "Expression": 85.56, | |
| "Material": 93.75, | |
| "Size": 90.34, | |
| "Shape": 87.24, | |
| "Color": 97.90, | |
| "Action-Overall": 81.14, | |
| "Hand": 82.05, | |
| "Full body": 81.88, | |
| "Animal": 79.71, | |
| "Non Contact": 76.79, | |
| "Contact": 75.00, | |
| "State": 84.09, | |
| "Relationship-Overall": 85.13, | |
| "Composition": 83.93, | |
| "Similarity": 78.53, | |
| "Inclusion": 92.82, | |
| "Comparison": 85.92, | |
| "Compound-Overall": 82.49, | |
| "Imagination": 82.28, | |
| "Feature matching": 82.94, | |
| "Grammar-Overall": 77.41, | |
| "Pronoun Reference": 91.27, | |
| "Consistency": 75.79, | |
| "Negation": 66.55, | |
| "Layout-Overall": 88.65, | |
| "2D": 90.25, | |
| "3D": 86.59, | |
| "Logical Reasoning": 68.20, | |
| "Text": 58.15 | |
| }, | |
| { | |
| "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": 61.01, | |
| "Style": 91.61, | |
| "World Knowledge": 74.42, | |
| "Attribute-Overall": 71.28, | |
| "Quantity": 54.26, | |
| "Expression": 61.81, | |
| "Material": 70.93, | |
| "Size": 78.22, | |
| "Shape": 57.87, | |
| "Color": 78.88, | |
| "Action-Overall": 55.38, | |
| "Hand": 48.08, | |
| "Full body": 54.69, | |
| "Animal": 61.23, | |
| "Non Contact": 46.88, | |
| "Contact": 35.92, | |
| "State": 64.82, | |
| "Relationship-Overall": 62.61, | |
| "Composition": 60.97, | |
| "Similarity": 57.69, | |
| "Inclusion": 62.36, | |
| "Comparison": 69.66, | |
| "Compound-Overall": 65.55, | |
| "Imagination": 70.89, | |
| "Feature matching": 53.74, | |
| "Grammar-Overall": 65.36, | |
| "Pronoun Reference": 74.60, | |
| "Consistency": 62.30, | |
| "Negation": 59.86, | |
| "Layout-Overall": 74.21, | |
| "2D": 77.40, | |
| "3D": 70.11, | |
| "Logical Reasoning": 48.30, | |
| "Text": 1.36 | |
| }, | |
| { | |
| "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": 54.80, | |
| "Style": 88.70, | |
| "World Knowledge": 65.90, | |
| "Attribute-Overall": 63.60, | |
| "Quantity": 42.55, | |
| "Expression": 43.89, | |
| "Material": 63.18, | |
| "Size": 71.59, | |
| "Shape": 45.98, | |
| "Color": 76.47, | |
| "Action-Overall": 48.68, | |
| "Hand": 26.60, | |
| "Full body": 50.94, | |
| "Animal": 53.26, | |
| "Non Contact": 39.29, | |
| "Contact": 35.92, | |
| "State": 59.98, | |
| "Relationship-Overall": 58.24, | |
| "Composition": 58.55, | |
| "Similarity": 52.88, | |
| "Inclusion": 60.34, | |
| "Comparison": 59.95, | |
| "Compound-Overall": 55.16, | |
| "Imagination": 62.34, | |
| "Feature matching": 39.25, | |
| "Grammar-Overall": 63.83, | |
| "Pronoun Reference": 71.03, | |
| "Consistency": 50.00, | |
| "Negation": 69.72, | |
| "Layout-Overall": 60.48, | |
| "2D": 60.03, | |
| "3D": 61.05, | |
| "Logical Reasoning": 41.75, | |
| "Text": 1.63 | |
| }, | |
| { | |
| "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": 71.03, | |
| "Style": 94.60, | |
| "World Knowledge": 88.87, | |
| "Attribute-Overall": 80.57, | |
| "Quantity": 70.74, | |
| "Expression": 80.00, | |
| "Material": 81.93, | |
| "Size": 86.36, | |
| "Shape": 71.85, | |
| "Color": 81.81, | |
| "Action-Overall": 70.18, | |
| "Hand": 65.71, | |
| "Full body": 68.44, | |
| "Animal": 73.55, | |
| "Non Contact": 60.71, | |
| "Contact": 60.63, | |
| "State": 76.58, | |
| "Relationship-Overall": 74.68, | |
| "Composition": 72.32, | |
| "Similarity": 70.19, | |
| "Inclusion": 81.03, | |
| "Comparison": 77.18, | |
| "Compound-Overall": 74.27, | |
| "Imagination": 78.80, | |
| "Feature matching": 64.25, | |
| "Grammar-Overall": 76.02, | |
| "Pronoun Reference": 83.33, | |
| "Consistency": 73.02, | |
| "Negation": 72.18, | |
| "Layout-Overall": 80.71, | |
| "2D": 82.20, | |
| "3D": 78.80, | |
| "Logical Reasoning": 65.53, | |
| "Text": 4.89 | |
| }, | |
| { | |
| "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": 60.37, | |
| "Style": 92.03, | |
| "World Knowledge": 73.27, | |
| "Attribute-Overall": 70.67, | |
| "Quantity": 42.55, | |
| "Expression": 48.61, | |
| "Material": 71.31, | |
| "Size": 79.17, | |
| "Shape": 57.69, | |
| "Color": 82.86, | |
| "Action-Overall": 55.78, | |
| "Hand": 39.42, | |
| "Full body": 57.19, | |
| "Animal": 64.86, | |
| "Non Contact": 51.34, | |
| "Contact": 40.23, | |
| "State": 64.23, | |
| "Relationship-Overall": 63.25, | |
| "Composition": 62.76, | |
| "Similarity": 60.26, | |
| "Inclusion": 67.82, | |
| "Comparison": 62.62, | |
| "Compound-Overall": 61.85, | |
| "Imagination": 69.73, | |
| "Feature matching": 44.39, | |
| "Grammar-Overall": 67.26, | |
| "Pronoun Reference": 74.21, | |
| "Consistency": 59.52, | |
| "Negation": 67.96, | |
| "Layout-Overall": 64.13, | |
| "2D": 62.85, | |
| "3D": 65.76, | |
| "Logical Reasoning": 54.37, | |
| "Text": 1.09 | |
| }, | |
| { | |
| "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": 41.48, | |
| "Style": 81.81, | |
| "World Knowledge": 69.51, | |
| "Attribute-Overall": 54.31, | |
| "Quantity": 39.36, | |
| "Expression": 44.03, | |
| "Material": 58.89, | |
| "Size": 58.14, | |
| "Shape": 43.01, | |
| "Color": 58.81, | |
| "Action-Overall": 31.18, | |
| "Hand": 19.23, | |
| "Full body": 29.69, | |
| "Animal": 29.35, | |
| "Non Contact": 17.41, | |
| "Contact": 16.67, | |
| "State": 43.87, | |
| "Relationship-Overall": 36.26, | |
| "Composition": 41.07, | |
| "Similarity": 27.88, | |
| "Inclusion": 42.24, | |
| "Comparison": 28.40, | |
| "Compound-Overall": 34.30, | |
| "Imagination": 41.24, | |
| "Feature matching": 18.93, | |
| "Grammar-Overall": 46.83, | |
| "Pronoun Reference": 53.57, | |
| "Consistency": 37.70, | |
| "Negation": 48.94, | |
| "Layout-Overall": 40.40, | |
| "2D": 39.12, | |
| "3D": 42.03, | |
| "Logical Reasoning": 19.42, | |
| "Text": 0.82 | |
| }, | |
| { | |
| "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": 67.68, | |
| "Style": 88.29, | |
| "World Knowledge": 89.45, | |
| "Attribute-Overall": 80.57, | |
| "Quantity": 74.47, | |
| "Expression": 66.53, | |
| "Material": 79.74, | |
| "Size": 83.14, | |
| "Shape": 74.30, | |
| "Color": 88.21, | |
| "Action-Overall": 64.33, | |
| "Hand": 68.91, | |
| "Full body": 60.31, | |
| "Animal": 65.94, | |
| "Non Contact": 53.12, | |
| "Contact": 56.32, | |
| "State": 68.97, | |
| "Relationship-Overall": 66.97, | |
| "Composition": 61.86, | |
| "Similarity": 64.10, | |
| "Inclusion": 76.44, | |
| "Comparison": 70.87, | |
| "Compound-Overall": 66.86, | |
| "Imagination": 68.99, | |
| "Feature matching": 62.15, | |
| "Grammar-Overall": 71.70, | |
| "Pronoun Reference": 86.51, | |
| "Consistency": 67.46, | |
| "Negation": 62.32, | |
| "Layout-Overall": 79.84, | |
| "2D": 83.62, | |
| "3D": 75.00, | |
| "Logical Reasoning": 49.76, | |
| "Text": 19.02 | |
| }, | |
| { | |
| "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": 53.60, | |
| "Style": 86.54, | |
| "World Knowledge": 76.01, | |
| "Attribute-Overall": 68.12, | |
| "Quantity": 61.17, | |
| "Expression": 50.42, | |
| "Material": 72.67, | |
| "Size": 71.97, | |
| "Shape": 58.74, | |
| "Color": 74.06, | |
| "Action-Overall": 49.96, | |
| "Hand": 39.74, | |
| "Full body": 38.44, | |
| "Animal": 50.36, | |
| "Non Contact": 44.64, | |
| "Contact": 34.20, | |
| "State": 63.24, | |
| "Relationship-Overall": 58.51, | |
| "Composition": 58.04, | |
| "Similarity": 58.01, | |
| "Inclusion": 62.36, | |
| "Comparison": 56.55, | |
| "Compound-Overall": 47.24, | |
| "Imagination": 52.11, | |
| "Feature matching": 36.45, | |
| "Grammar-Overall": 55.20, | |
| "Pronoun Reference": 72.22, | |
| "Consistency": 53.57, | |
| "Negation": 41.55, | |
| "Layout-Overall": 60.95, | |
| "2D": 61.02, | |
| "3D": 60.87, | |
| "Logical Reasoning": 31.31, | |
| "Text": 2.17 | |
| }, | |
| { | |
| "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": 71.11, | |
| "Style": 94.02, | |
| "World Knowledge": 88.15, | |
| "Attribute-Overall": 81.81, | |
| "Quantity": 62.23, | |
| "Expression": 66.39, | |
| "Material": 83.43, | |
| "Size": 85.42, | |
| "Shape": 75.87, | |
| "Color": 89.20, | |
| "Action-Overall": 69.14, | |
| "Hand": 57.69, | |
| "Full body": 73.44, | |
| "Animal": 76.09, | |
| "Non Contact": 62.95, | |
| "Contact": 61.21, | |
| "State": 73.52, | |
| "Relationship-Overall": 77.96, | |
| "Composition": 77.42, | |
| "Similarity": 71.15, | |
| "Inclusion": 82.18, | |
| "Comparison": 80.58, | |
| "Compound-Overall": 76.53, | |
| "Imagination": 80.59, | |
| "Feature matching": 67.52, | |
| "Grammar-Overall": 74.62, | |
| "Pronoun Reference": 87.30, | |
| "Consistency": 73.81, | |
| "Negation": 64.08, | |
| "Layout-Overall": 82.14, | |
| "2D": 81.78, | |
| "3D": 82.61, | |
| "Logical Reasoning": 62.62, | |
| "Text": 4.08 | |
| }, | |
| { | |
| "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": 64.35, | |
| "Style": 88.12, | |
| "World Knowledge": 88.15, | |
| "Attribute-Overall": 78.78, | |
| "Quantity": 68.62, | |
| "Expression": 62.22, | |
| "Material": 81.85, | |
| "Size": 78.79, | |
| "Shape": 70.63, | |
| "Color": 86.32, | |
| "Action-Overall": 59.63, | |
| "Hand": 57.69, | |
| "Full body": 52.81, | |
| "Animal": 57.25, | |
| "Non Contact": 50.89, | |
| "Contact": 48.85, | |
| "State": 68.68, | |
| "Relationship-Overall": 67.62, | |
| "Composition": 70.15, | |
| "Similarity": 62.18, | |
| "Inclusion": 70.11, | |
| "Comparison": 64.81, | |
| "Compound-Overall": 62.21, | |
| "Imagination": 65.82, | |
| "Feature matching": 54.21, | |
| "Grammar-Overall": 65.23, | |
| "Pronoun Reference": 75.79, | |
| "Consistency": 61.51, | |
| "Negation": 59.15, | |
| "Layout-Overall": 71.19, | |
| "2D": 73.45, | |
| "3D": 68.30, | |
| "Logical Reasoning": 44.90, | |
| "Text": 17.66 | |
| }, | |
| { | |
| "model": "Seedream-4.0", | |
| "link": "https://www.volcengine.com/docs/82379/1541523", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-09", | |
| "Overall": 89.77, | |
| "Style": 98.42, | |
| "World Knowledge": 95.95, | |
| "Attribute-Overall": 95.06, | |
| "Quantity": 92.02, | |
| "Expression": 89.31, | |
| "Material": 95.26, | |
| "Size": 94.70, | |
| "Shape": 92.48, | |
| "Color": 98.27, | |
| "Action-Overall": 86.76, | |
| "Hand": 83.01, | |
| "Full body": 87.50, | |
| "Animal": 81.52, | |
| "Non Contact": 88.39, | |
| "Contact": 83.62, | |
| "State": 89.82, | |
| "Relationship-Overall": 88.69, | |
| "Composition": 87.37, | |
| "Similarity": 80.77, | |
| "Inclusion": 93.97, | |
| "Comparison": 92.72, | |
| "Compound-Overall": 87.79, | |
| "Imagination": 88.19, | |
| "Feature matching": 86.92, | |
| "Grammar-Overall": 82.74, | |
| "Pronoun Reference": 95.63, | |
| "Consistency": 83.33, | |
| "Negation": 70.77, | |
| "Layout-Overall": 92.38, | |
| "2D": 92.94, | |
| "3D": 91.67, | |
| "Logical Reasoning": 79.13, | |
| "Text": 90.76 | |
| }, | |
| { | |
| "model": "DALL-E-3", | |
| "link": "https://openai.com/zh-Hans-CN/index/dall-e-3/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2023-09", | |
| "Overall": 70.82, | |
| "Style": 95.08, | |
| "World Knowledge": 92.71, | |
| "Attribute-Overall": 84.98, | |
| "Quantity": 64.67, | |
| "Expression": 72.59, | |
| "Material": 88.72, | |
| "Size": 89.48, | |
| "Shape": 77.14, | |
| "Color": 90.15, | |
| "Action-Overall": 68.36, | |
| "Hand": 63.49, | |
| "Full body": 63.96, | |
| "Animal": 67.03, | |
| "Non Contact": 59.55, | |
| "Contact": 60.17, | |
| "State": 76.29, | |
| "Relationship-Overall": 77.90, | |
| "Composition": 80.57, | |
| "Similarity": 70.51, | |
| "Inclusion": 83.53, | |
| "Comparison": 73.76, | |
| "Compound-Overall": 73.88, | |
| "Imagination": 77.67, | |
| "Feature matching": 65.00, | |
| "Grammar-Overall": 68.19, | |
| "Pronoun Reference": 82.92, | |
| "Consistency": 66.27, | |
| "Negation": 56.99, | |
| "Layout-Overall": 71.76, | |
| "2D": 69.22, | |
| "3D": 75.00, | |
| "Logical Reasoning": 57.11, | |
| "Text": 18.26 | |
| }, | |
| { | |
| "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": 68.29, | |
| "Style": 91.72, | |
| "World Knowledge": 88.82, | |
| "Attribute-Overall": 79.83, | |
| "Quantity": 70.65, | |
| "Expression": 65.43, | |
| "Material": 85.33, | |
| "Size": 81.01, | |
| "Shape": 67.38, | |
| "Color": 85.64, | |
| "Action-Overall": 64.30, | |
| "Hand": 55.33, | |
| "Full body": 63.92, | |
| "Animal": 70.65, | |
| "Non Contact": 56.82, | |
| "Contact": 56.10, | |
| "State": 69.76, | |
| "Relationship-Overall": 69.53, | |
| "Composition": 70.05, | |
| "Similarity": 59.09, | |
| "Inclusion": 76.76, | |
| "Comparison": 70.39, | |
| "Compound-Overall": 68.57, | |
| "Imagination": 69.47, | |
| "Feature matching": 66.50, | |
| "Grammar-Overall": 70.55, | |
| "Pronoun Reference": 76.23, | |
| "Consistency": 62.70, | |
| "Negation": 72.76, | |
| "Layout-Overall": 73.79, | |
| "2D": 72.56, | |
| "3D": 75.37, | |
| "Logical Reasoning": 48.28, | |
| "Text": 27.47 | |
| }, | |
| { | |
| "model": "Imagen-4.0-generate-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-01", | |
| "Overall": 85.34, | |
| "Style": 94.44, | |
| "World Knowledge": 97.11, | |
| "Attribute-Overall": 90.14, | |
| "Quantity": 82.45, | |
| "Expression": 77.64, | |
| "Material": 90.96, | |
| "Size": 92.23, | |
| "Shape": 86.36, | |
| "Color": 95.60, | |
| "Action-Overall": 82.62, | |
| "Hand": 83.65, | |
| "Full body": 82.81, | |
| "Animal": 78.62, | |
| "Non Contact": 85.27, | |
| "Contact": 78.74, | |
| "State": 84.09, | |
| "Relationship-Overall": 86.42, | |
| "Composition": 86.48, | |
| "Similarity": 80.13, | |
| "Inclusion": 91.38, | |
| "Comparison": 86.89, | |
| "Compound-Overall": 86.56, | |
| "Imagination": 86.81, | |
| "Feature matching": 85.98, | |
| "Grammar-Overall": 81.35, | |
| "Pronoun Reference": 94.05, | |
| "Consistency": 80.56, | |
| "Negation": 70.77, | |
| "Layout-Overall": 90.24, | |
| "2D": 90.40, | |
| "3D": 90.04, | |
| "Logical Reasoning": 72.82, | |
| "Text": 71.74 | |
| }, | |
| { | |
| "model": "Imagen-3.0-generate-002", | |
| "link": "https://arxiv.org/pdf/2408.07009", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-02", | |
| "Overall": 75.76, | |
| "Style": 92.41, | |
| "World Knowledge": 94.19, | |
| "Attribute-Overall": 86.32, | |
| "Quantity": 75.58, | |
| "Expression": 71.41, | |
| "Material": 88.34, | |
| "Size": 88.52, | |
| "Shape": 78.27, | |
| "Color": 93.13, | |
| "Action-Overall": 75.81, | |
| "Hand": 73.63, | |
| "Full body": 77.12, | |
| "Animal": 76.81, | |
| "Non Contact": 69.44, | |
| "Contact": 65.48, | |
| "State": 80.62, | |
| "Relationship-Overall": 80.76, | |
| "Composition": 80.15, | |
| "Similarity": 74.17, | |
| "Inclusion": 90.59, | |
| "Comparison": 78.54, | |
| "Compound-Overall": 78.70, | |
| "Imagination": 81.14, | |
| "Feature matching": 73.22, | |
| "Grammar-Overall": 77.96, | |
| "Pronoun Reference": 91.67, | |
| "Consistency": 76.61, | |
| "Negation": 66.67, | |
| "Layout-Overall": 86.06, | |
| "2D": 83.97, | |
| "3D": 88.69, | |
| "Logical Reasoning": 61.25, | |
| "Text": 24.18 | |
| }, | |
| { | |
| "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": 62.01, | |
| "Style": 85.63, | |
| "World Knowledge": 86.71, | |
| "Attribute-Overall": 74.73, | |
| "Quantity": 66.49, | |
| "Expression": 55.69, | |
| "Material": 76.43, | |
| "Size": 77.27, | |
| "Shape": 67.48, | |
| "Color": 83.02, | |
| "Action-Overall": 58.27, | |
| "Hand": 58.33, | |
| "Full body": 49.38, | |
| "Animal": 59.42, | |
| "Non Contact": 52.23, | |
| "Contact": 45.98, | |
| "State": 66.30, | |
| "Relationship-Overall": 63.63, | |
| "Composition": 64.92, | |
| "Similarity": 56.73, | |
| "Inclusion": 67.53, | |
| "Comparison": 63.11, | |
| "Compound-Overall": 58.28, | |
| "Imagination": 62.66, | |
| "Feature matching": 48.60, | |
| "Grammar-Overall": 65.10, | |
| "Pronoun Reference": 76.19, | |
| "Consistency": 61.11, | |
| "Negation": 58.80, | |
| "Layout-Overall": 71.67, | |
| "2D": 74.86, | |
| "3D": 67.57, | |
| "Logical Reasoning": 40.29, | |
| "Text": 15.76 | |
| }, | |
| { | |
| "model": "FLUX-pro-1.1-Ultra", | |
| "link": "https://bfl.ai/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-11", | |
| "Overall": 75.40, | |
| "Style": 91.36, | |
| "World Knowledge": 91.76, | |
| "Attribute-Overall": 84.97, | |
| "Quantity": 79.26, | |
| "Expression": 68.58, | |
| "Material": 82.98, | |
| "Size": 89.96, | |
| "Shape": 80.59, | |
| "Color": 93.01, | |
| "Action-Overall": 72.43, | |
| "Hand": 67.31, | |
| "Full body": 66.25, | |
| "Animal": 73.19, | |
| "Non Contact": 66.96, | |
| "Contact": 62.07, | |
| "State": 80.53, | |
| "Relationship-Overall": 81.90, | |
| "Composition": 81.89, | |
| "Similarity": 74.04, | |
| "Inclusion": 90.52, | |
| "Comparison": 80.58, | |
| "Compound-Overall": 78.07, | |
| "Imagination": 80.40, | |
| "Feature matching": 72.88, | |
| "Grammar-Overall": 71.94, | |
| "Pronoun Reference": 84.52, | |
| "Consistency": 68.55, | |
| "Negation": 63.73, | |
| "Layout-Overall": 82.62, | |
| "2D": 81.78, | |
| "3D": 83.70, | |
| "Logical Reasoning": 60.92, | |
| "Text": 38.04 | |
| }, | |
| { | |
| "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": 83.94, | |
| "Style": 96.93, | |
| "World Knowledge": 95.09, | |
| "Attribute-Overall": 93.65, | |
| "Quantity": 92.02, | |
| "Expression": 89.86, | |
| "Material": 94.50, | |
| "Size": 89.58, | |
| "Shape": 86.71, | |
| "Color": 97.85, | |
| "Action-Overall": 81.86, | |
| "Hand": 78.53, | |
| "Full body": 81.88, | |
| "Animal": 83.70, | |
| "Non Contact": 83.04, | |
| "Contact": 71.84, | |
| "State": 85.57, | |
| "Relationship-Overall": 83.41, | |
| "Composition": 81.76, | |
| "Similarity": 79.17, | |
| "Inclusion": 88.79, | |
| "Comparison": 85.19, | |
| "Compound-Overall": 81.98, | |
| "Imagination": 82.38, | |
| "Feature matching": 81.07, | |
| "Grammar-Overall": 73.86, | |
| "Pronoun Reference": 90.48, | |
| "Consistency": 78.57, | |
| "Negation": 54.93, | |
| "Layout-Overall": 88.97, | |
| "2D": 91.24, | |
| "3D": 86.05, | |
| "Logical Reasoning": 66.75, | |
| "Text": 76.90 | |
| }, | |
| { | |
| "model": "FLUX-kontext-pro", | |
| "link": "https://bfl.ai/models/flux-kontext", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-05", | |
| "Overall": 78.58, | |
| "Style": 94.83, | |
| "World Knowledge": 93.60, | |
| "Attribute-Overall": 86.24, | |
| "Quantity": 74.47, | |
| "Expression": 75.00, | |
| "Material": 85.47, | |
| "Size": 89.58, | |
| "Shape": 80.63, | |
| "Color": 92.89, | |
| "Action-Overall": 74.44, | |
| "Hand": 73.05, | |
| "Full body": 73.12, | |
| "Animal": 75.00, | |
| "Non Contact": 67.73, | |
| "Contact": 70.40, | |
| "State": 77.98, | |
| "Relationship-Overall": 78.40, | |
| "Composition": 73.85, | |
| "Similarity": 72.08, | |
| "Inclusion": 89.08, | |
| "Comparison": 82.77, | |
| "Compound-Overall": 79.75, | |
| "Imagination": 83.58, | |
| "Feature matching": 71.23, | |
| "Grammar-Overall": 77.05, | |
| "Pronoun Reference": 90.32, | |
| "Consistency": 75.40, | |
| "Negation": 66.90, | |
| "Layout-Overall": 85.46, | |
| "2D": 84.09, | |
| "3D": 87.23, | |
| "Logical Reasoning": 66.26, | |
| "Text": 49.73 | |
| }, | |
| { | |
| "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": 54.88, | |
| "Style": 92.94, | |
| "World Knowledge": 80.06, | |
| "Attribute-Overall": 69.47, | |
| "Quantity": 65.43, | |
| "Expression": 52.22, | |
| "Material": 72.14, | |
| "Size": 75.19, | |
| "Shape": 58.22, | |
| "Color": 76.31, | |
| "Action-Overall": 48.80, | |
| "Hand": 39.10, | |
| "Full body": 46.25, | |
| "Animal": 47.46, | |
| "Non Contact": 41.07, | |
| "Contact": 34.48, | |
| "State": 59.58, | |
| "Relationship-Overall": 55.66, | |
| "Composition": 56.89, | |
| "Similarity": 55.45, | |
| "Inclusion": 57.18, | |
| "Comparison": 52.18, | |
| "Compound-Overall": 50.22, | |
| "Imagination": 55.49, | |
| "Feature matching": 38.55, | |
| "Grammar-Overall": 58.76, | |
| "Pronoun Reference": 64.68, | |
| "Consistency": 59.52, | |
| "Negation": 52.82, | |
| "Layout-Overall": 61.43, | |
| "2D": 60.45, | |
| "3D": 62.68, | |
| "Logical Reasoning": 29.85, | |
| "Text": 1.63 | |
| }, | |
| { | |
| "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": 69.42, | |
| "Style": 89.29, | |
| "World Knowledge": 89.45, | |
| "Attribute-Overall": 79.90, | |
| "Quantity": 73.94, | |
| "Expression": 64.44, | |
| "Material": 80.05, | |
| "Size": 84.47, | |
| "Shape": 71.50, | |
| "Color": 87.47, | |
| "Action-Overall": 64.54, | |
| "Hand": 63.78, | |
| "Full body": 62.50, | |
| "Animal": 65.94, | |
| "Non Contact": 56.70, | |
| "Contact": 56.32, | |
| "State": 69.57, | |
| "Relationship-Overall": 69.40, | |
| "Composition": 65.05, | |
| "Similarity": 66.03, | |
| "Inclusion": 79.60, | |
| "Comparison": 71.60, | |
| "Compound-Overall": 68.46, | |
| "Imagination": 71.10, | |
| "Feature matching": 62.62, | |
| "Grammar-Overall": 70.56, | |
| "Pronoun Reference": 83.33, | |
| "Consistency": 67.46, | |
| "Negation": 61.97, | |
| "Layout-Overall": 77.54, | |
| "2D": 81.21, | |
| "3D": 72.83, | |
| "Logical Reasoning": 54.37, | |
| "Text": 30.71 | |
| }, | |
| { | |
| "model": "FLUX-kontext-max", | |
| "link": "https://bfl.ai/models/flux-kontext", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-05", | |
| "Overall": 80.88, | |
| "Style": 96.51, | |
| "World Knowledge": 93.35, | |
| "Attribute-Overall": 87.45, | |
| "Quantity": 79.79, | |
| "Expression": 76.68, | |
| "Material": 87.35, | |
| "Size": 88.83, | |
| "Shape": 81.51, | |
| "Color": 93.74, | |
| "Action-Overall": 75.52, | |
| "Hand": 73.08, | |
| "Full body": 75.94, | |
| "Animal": 74.28, | |
| "Non Contact": 66.82, | |
| "Contact": 71.55, | |
| "State": 79.76, | |
| "Relationship-Overall": 80.78, | |
| "Composition": 77.30, | |
| "Similarity": 73.05, | |
| "Inclusion": 89.94, | |
| "Comparison": 85.44, | |
| "Compound-Overall": 82.24, | |
| "Imagination": 84.75, | |
| "Feature matching": 76.65, | |
| "Grammar-Overall": 79.34, | |
| "Pronoun Reference": 90.08, | |
| "Consistency": 76.61, | |
| "Negation": 72.18, | |
| "Layout-Overall": 87.58, | |
| "2D": 85.73, | |
| "3D": 89.96, | |
| "Logical Reasoning": 71.12, | |
| "Text": 54.89 | |
| }, | |
| { | |
| "model": "Recraft", | |
| "link": "https://www.recraft.ai/docs#generate-image", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2024-12", | |
| "Overall": 60.93, | |
| "Style": 87.13, | |
| "World Knowledge": 86.99, | |
| "Attribute-Overall": 73.23, | |
| "Quantity": 56.38, | |
| "Expression": 57.22, | |
| "Material": 72.82, | |
| "Size": 76.89, | |
| "Shape": 63.64, | |
| "Color": 83.07, | |
| "Action-Overall": 51.77, | |
| "Hand": 40.06, | |
| "Full body": 54.37, | |
| "Animal": 55.07, | |
| "Non Contact": 45.09, | |
| "Contact": 37.36, | |
| "State": 60.08, | |
| "Relationship-Overall": 55.82, | |
| "Composition": 51.79, | |
| "Similarity": 46.47, | |
| "Inclusion": 66.09, | |
| "Comparison": 61.89, | |
| "Compound-Overall": 49.56, | |
| "Imagination": 50.21, | |
| "Feature matching": 48.13, | |
| "Grammar-Overall": 60.28, | |
| "Pronoun Reference": 73.41, | |
| "Consistency": 55.56, | |
| "Negation": 52.82, | |
| "Layout-Overall": 63.81, | |
| "2D": 65.96, | |
| "3D": 61.05, | |
| "Logical Reasoning": 34.22, | |
| "Text": 46.47 | |
| }, | |
| { | |
| "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": 68.76, | |
| "Style": 90.28, | |
| "World Knowledge": 87.57, | |
| "Attribute-Overall": 81.08, | |
| "Quantity": 78.19, | |
| "Expression": 69.17, | |
| "Material": 80.42, | |
| "Size": 82.77, | |
| "Shape": 73.60, | |
| "Color": 88.10, | |
| "Action-Overall": 66.49, | |
| "Hand": 64.10, | |
| "Full body": 60.94, | |
| "Animal": 70.29, | |
| "Non Contact": 59.38, | |
| "Contact": 55.46, | |
| "State": 73.32, | |
| "Relationship-Overall": 72.79, | |
| "Composition": 69.13, | |
| "Similarity": 66.67, | |
| "Inclusion": 81.03, | |
| "Comparison": 77.43, | |
| "Compound-Overall": 71.73, | |
| "Imagination": 74.16, | |
| "Feature matching": 66.36, | |
| "Grammar-Overall": 70.18, | |
| "Pronoun Reference": 86.90, | |
| "Consistency": 61.11, | |
| "Negation": 63.38, | |
| "Layout-Overall": 79.13, | |
| "2D": 82.34, | |
| "3D": 75.00, | |
| "Logical Reasoning": 55.58, | |
| "Text": 12.77 | |
| }, | |
| { | |
| "model": "Nano Banana", | |
| "link": "https://ainanobanana.io/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-08", | |
| "Overall": 88.82, | |
| "Style": 98.83, | |
| "World Knowledge": 95.78, | |
| "Attribute-Overall": 93.06, | |
| "Quantity": 88.24, | |
| "Expression": 86.09, | |
| "Material": 93.05, | |
| "Size": 93.70, | |
| "Shape": 88.73, | |
| "Color": 97.31, | |
| "Action-Overall": 83.93, | |
| "Hand": 84.57, | |
| "Full body": 84.95, | |
| "Animal": 81.16, | |
| "Non Contact": 83.41, | |
| "Contact": 78.16, | |
| "State": 86.28, | |
| "Relationship-Overall": 91.59, | |
| "Composition": 90.98, | |
| "Similarity": 91.32, | |
| "Inclusion": 92.80, | |
| "Comparison": 91.91, | |
| "Compound-Overall": 90.63, | |
| "Imagination": 92.15, | |
| "Feature matching": 87.23, | |
| "Grammar-Overall": 89.33, | |
| "Pronoun Reference": 94.84, | |
| "Consistency": 89.24, | |
| "Negation": 84.51, | |
| "Layout-Overall": 94.04, | |
| "2D": 94.77, | |
| "3D": 93.12, | |
| "Logical Reasoning": 81.27, | |
| "Text": 69.75 | |
| }, | |
| { | |
| "model": "GPT-4o", | |
| "link": "https://platform.openai.com/docs/guides/image-generation", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-03", | |
| "Overall": 92.63, | |
| "Style": 99.08, | |
| "World Knowledge": 97.95, | |
| "Attribute-Overall": 93.53, | |
| "Quantity": 86.70, | |
| "Expression": 93.44, | |
| "Material": 92.45, | |
| "Size": 94.89, | |
| "Shape": 92.48, | |
| "Color": 94.95, | |
| "Action-Overall": 87.78, | |
| "Hand": 89.94, | |
| "Full body": 87.19, | |
| "Animal": 90.94, | |
| "Non Contact": 89.29, | |
| "Contact": 83.05, | |
| "State": 87.75, | |
| "Relationship-Overall": 91.13, | |
| "Composition": 89.18, | |
| "Similarity": 90.71, | |
| "Inclusion": 96.84, | |
| "Comparison": 90.29, | |
| "Compound-Overall": 93.99, | |
| "Imagination": 94.39, | |
| "Feature matching": 93.10, | |
| "Grammar-Overall": 94.46, | |
| "Pronoun Reference": 95.97, | |
| "Consistency": 91.67, | |
| "Negation": 95.65, | |
| "Layout-Overall": 93.59, | |
| "2D": 94.29, | |
| "3D": 92.70, | |
| "Logical Reasoning": 91.02, | |
| "Text": 83.79 | |
| }, | |
| { | |
| "model": "Seedream-3.0", | |
| "link": "https://www.byteplus.com/en/product/Seedream", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 80.99, | |
| "Style": 97.18, | |
| "World Knowledge": 93.79, | |
| "Attribute-Overall": 91.90, | |
| "Quantity": 83.51, | |
| "Expression": 81.25, | |
| "Material": 93.07, | |
| "Size": 88.26, | |
| "Shape": 90.03, | |
| "Color": 97.48, | |
| "Action-Overall": 79.94, | |
| "Hand": 77.88, | |
| "Full body": 84.69, | |
| "Animal": 78.26, | |
| "Non Contact": 74.11, | |
| "Contact": 71.84, | |
| "State": 83.60, | |
| "Relationship-Overall": 83.41, | |
| "Composition": 81.63, | |
| "Similarity": 79.17, | |
| "Inclusion": 87.64, | |
| "Comparison": 86.41, | |
| "Compound-Overall": 81.03, | |
| "Imagination": 80.49, | |
| "Feature matching": 82.24, | |
| "Grammar-Overall": 75.13, | |
| "Pronoun Reference": 90.48, | |
| "Consistency": 80.56, | |
| "Negation": 56.69, | |
| "Layout-Overall": 88.41, | |
| "2D": 87.85, | |
| "3D": 89.13, | |
| "Logical Reasoning": 62.62, | |
| "Text": 56.52 | |
| }, | |
| { | |
| "model": "Imagen-4.0-Fast-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 81.54, | |
| "Style": 93.77, | |
| "World Knowledge": 93.64, | |
| "Attribute-Overall": 90.33, | |
| "Quantity": 78.72, | |
| "Expression": 78.89, | |
| "Material": 91.11, | |
| "Size": 90.15, | |
| "Shape": 86.89, | |
| "Color": 96.33, | |
| "Action-Overall": 80.18, | |
| "Hand": 82.05, | |
| "Full body": 84.06, | |
| "Animal": 81.88, | |
| "Non Contact": 75.00, | |
| "Contact": 74.71, | |
| "State": 80.93, | |
| "Relationship-Overall": 84.05, | |
| "Composition": 82.53, | |
| "Similarity": 80.13, | |
| "Inclusion": 92.82, | |
| "Comparison": 82.52, | |
| "Compound-Overall": 84.01, | |
| "Imagination": 86.18, | |
| "Feature matching": 79.21, | |
| "Grammar-Overall": 79.57, | |
| "Pronoun Reference": 91.27, | |
| "Consistency": 81.35, | |
| "Negation": 67.61, | |
| "Layout-Overall": 90.48, | |
| "2D": 90.11, | |
| "3D": 90.94, | |
| "Logical Reasoning": 67.72, | |
| "Text": 51.63 | |
| }, | |
| { | |
| "model": "Imagen-4.0-Ultra-preview-06-06", | |
| "link": "https://deepmind.google/models/imagen/", | |
| "hf": "-", | |
| "open_source": false, | |
| "release_date": "2025-06", | |
| "Overall": 90.95, | |
| "Style": 97.67, | |
| "World Knowledge": 98.26, | |
| "Attribute-Overall": 93.21, | |
| "Quantity": 89.84, | |
| "Expression": 83.17, | |
| "Material": 94.20, | |
| "Size": 94.69, | |
| "Shape": 89.86, | |
| "Color": 97.22, | |
| "Action-Overall": 86.91, | |
| "Hand": 89.10, | |
| "Full body": 86.56, | |
| "Animal": 85.14, | |
| "Non Contact": 86.61, | |
| "Contact": 81.84, | |
| "State": 88.63, | |
| "Relationship-Overall": 90.57, | |
| "Composition": 90.05, | |
| "Similarity": 84.62, | |
| "Inclusion": 94.52, | |
| "Comparison": 92.72, | |
| "Compound-Overall": 91.42, | |
| "Imagination": 92.82, | |
| "Feature matching": 88.32, | |
| "Grammar-Overall": 88.07, | |
| "Pronoun Reference": 96.83, | |
| "Consistency": 87.70, | |
| "Negation": 80.63, | |
| "Layout-Overall": 93.49, | |
| "2D": 92.64, | |
| "3D": 94.57, | |
| "Logical Reasoning": 83.50, | |
| "Text": 86.41 | |
| } | |
| ] | |
| } | |