| { |
| "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": 81.77, |
| "Style": 95.50, |
| "World Knowledge": 91.61, |
|
|
| "Attribute-Overall": 89.21, |
| "Quantity": 83.33, |
| "Expression": 81.41, |
| "Material": 93.40, |
| "Size": 91.67, |
| "Shape": 86.88, |
| "Color": 99.17, |
| |
| "Action-Overall": 86.31, |
| "Hand": 84.62, |
| "Full body": 87.50, |
| "Animal": 92.65, |
| "Non Contact": 82.14, |
| "Contact": 83.93, |
| "State": 88.21, |
| |
| "Relationship-Overall": 90.10, |
| "Composition": 92.23, |
| "Similarity": 82.78, |
| "Inclusion": 93.48, |
| "Comparison": 90.62, |
| |
| "Compound-Overall": 84.41, |
| "Imagination": 89.80, |
| "Feature matching": 78.91, |
| |
| "Grammar-Overall": 73.80, |
| "Pronoun Reference": 89.71, |
| "Consistency": 75.00, |
| "Negation": 56.15, |
| |
| "Layout-Overall": 91.98, |
| "2D": 91.91, |
| "3D": 92.05, |
| |
| "Logical Reasoning": 72.25, |
| |
| "Text": 42.53 |
| }, |
| { |
| "model": "Nano Banana Pro", |
| "link": "https://nano-banana.pro/", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-11", |
|
|
| "Overall": 93.82, |
|
|
| "Style": 99.50, |
|
|
| "World Knowledge": 97.47, |
|
|
| "Attribute-Overall": 94.55, |
| "Quantity": 90.97, |
| "Expression": 96.15, |
| "Material": 95.75, |
| "Size": 95.14, |
| "Shape": 91.25, |
| "Color": 98.33, |
|
|
| "Action-Overall": 94.96, |
| "Hand": 94.23, |
| "Full body": 94.57, |
| "Animal": 97.06, |
| "Non Contact": 92.35, |
| "Contact": 95.24, |
| "State": 96.70, |
|
|
| "Relationship-Overall": 96.07, |
| "Composition": 96.96, |
| "Similarity": 91.67, |
| "Inclusion": 97.83, |
| "Comparison": 97.66, |
|
|
| "Compound-Overall": 94.20, |
| "Imagination": 96.68, |
| "Feature matching": 91.67, |
|
|
| "Grammar-Overall": 89.04, |
| "Pronoun Reference": 94.49, |
| "Consistency": 90.74, |
| "Negation": 81.92, |
|
|
| "Layout-Overall": 94.40, |
| "2D": 96.32, |
| "3D": 92.42, |
|
|
| "Logical Reasoning": 82.34, |
|
|
| "Text": 95.69 |
| }, |
| { |
| "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": 78.40, |
| "Style": 93.30, |
| "World Knowledge": 93.51, |
|
|
| "Attribute-Overall": 83.65, |
| "Quantity": 78.47, |
| "Expression": 75.64, |
| "Material": 90.09, |
| "Size": 84.72, |
| "Shape": 76.88, |
| "Color": 96.67, |
| |
| "Action-Overall": 76.62, |
| "Hand": 73.72, |
| "Full body": 72.28, |
| "Animal": 81.62, |
| "Non Contact": 77.04, |
| "Contact": 73.81, |
| "State": 81.13, |
| |
| "Relationship-Overall": 81.85, |
| "Composition": 80.07, |
| "Similarity": 73.33, |
| "Inclusion": 88.04, |
| "Comparison": 89.06, |
| |
| "Compound-Overall": 78.74, |
| "Imagination": 84.95, |
| "Feature matching": 72.40, |
| |
| "Grammar-Overall": 72.58, |
| "Pronoun Reference": 82.72, |
| "Consistency": 70.37, |
| "Negation": 63.67, |
| |
| "Layout-Overall": 75.93, |
| "2D": 76.10, |
| "3D": 75.76, |
| |
| "Logical Reasoning": 63.64, |
| |
| "Text": 64.22 |
| }, |
| { |
| "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": 72.40, |
| "Style": 92.80, |
| "World Knowledge": 87.66, |
|
|
| "Attribute-Overall": 84.29, |
| "Quantity": 72.92, |
| "Expression": 77.56, |
| "Material": 89.15, |
| "Size": 88.19, |
| "Shape": 80.00, |
| "Color": 99.17, |
| |
| "Action-Overall": 76.05, |
| "Hand": 73.08, |
| "Full body": 83.15, |
| "Animal": 85.29, |
| "Non Contact": 75.00, |
| "Contact": 65.48, |
| "State": 75.47, |
| |
| "Relationship-Overall": 82.23, |
| "Composition": 85.81, |
| "Similarity": 75.00, |
| "Inclusion": 88.04, |
| "Comparison": 75.78, |
| |
| "Compound-Overall": 77.96, |
| "Imagination": 82.91, |
| "Feature matching": 72.92, |
| |
| "Grammar-Overall": 75.40, |
| "Pronoun Reference": 80.15, |
| "Consistency": 77.31, |
| "Negation": 68.85, |
| |
| "Layout-Overall": 83.02, |
| "2D": 84.19, |
| "3D": 81.82, |
| |
| "Logical Reasoning": 56.82, |
| |
| "Text": 7.76 |
| }, |
| { |
| "model": "Emu3", |
| "link": "https://arxiv.org/pdf/2409.18869", |
| "hf": "https://huggingface.co/BAAI/Emu3-Gen", |
| "open_source": true, |
| "release_date": "2024-09", |
|
|
| "Overall": 33.91, |
|
|
| "Style": 78.08, |
|
|
| "World Knowledge": 55.54, |
|
|
| "Attribute-Overall": 38.29, |
| "Quantity": 27.78, |
| "Expression": 30.13, |
| "Material": 44.34, |
| "Size": 32.64, |
| "Shape": 27.67, |
| "Color": 71.67, |
|
|
| "Action-Overall": 31.18, |
| "Hand": 16.67, |
| "Full body": 36.96, |
| "Animal": 49.26, |
| "Non Contact": 26.02, |
| "Contact": 17.86, |
| "State": 40.57, |
|
|
| "Relationship-Overall": 36.68, |
| "Composition": 43.58, |
| "Similarity": 31.67, |
| "Inclusion": 38.04, |
| "Comparison": 25.78, |
|
|
| "Compound-Overall": 21.65, |
| "Imagination": 29.85, |
| "Feature matching": 13.28, |
|
|
| "Grammar-Overall": 41.31, |
| "Pronoun Reference": 41.91, |
| "Consistency": 38.89, |
| "Negation": 42.69, |
|
|
| "Layout-Overall": 22.43, |
| "2D": 17.71, |
| "3D": 27.27, |
|
|
| "Logical Reasoning": 13.90, |
|
|
| "Text": 0.00 |
| }, |
| { |
| "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": 15.21, |
| "Style": 49.40, |
| "World Knowledge": 16.61, |
|
|
| "Attribute-Overall": 15.06, |
| "Quantity": 14.58, |
| "Expression": 19.87, |
| "Material": 8.02, |
| "Size": 13.19, |
| "Shape": 5.00, |
| "Color": 37.50, |
| |
| "Action-Overall": 14.64, |
| "Hand": 9.62, |
| "Full body": 17.93, |
| "Animal": 18.38, |
| "Non Contact": 9.69, |
| "Contact": 6.55, |
| "State": 24.06, |
| |
| "Relationship-Overall": 11.80, |
| "Composition": 16.55, |
| "Similarity": 6.67, |
| "Inclusion": 12.50, |
| "Comparison": 7.03, |
| |
| "Compound-Overall": 4.38, |
| "Imagination": 6.63, |
| "Feature matching": 2.08, |
| |
| "Grammar-Overall": 27.81, |
| "Pronoun Reference": 19.85, |
| "Consistency": 16.20, |
| "Negation": 45.77, |
| |
| "Layout-Overall": 9.14, |
| "2D": 8.09, |
| "3D": 10.23, |
| |
| "Logical Reasoning": 2.95, |
| |
| "Text": 0.29 |
| }, |
| { |
| "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": 58.35, |
| "Style": 80.90, |
| "World Knowledge": 69.46, |
|
|
| "Attribute-Overall": 75.64, |
| "Quantity": 62.50, |
| "Expression": 71.79, |
| "Material": 77.83, |
| "Size": 78.47, |
| "Shape": 70.00, |
| "Color": 96.67, |
| |
| "Action-Overall": 61.12, |
| "Hand": 42.95, |
| "Full body": 61.41, |
| "Animal": 76.47, |
| "Non Contact": 58.67, |
| "Contact": 51.79, |
| "State": 74.06, |
| |
| "Relationship-Overall": 67.13, |
| "Composition": 68.58, |
| "Similarity": 62.78, |
| "Inclusion": 76.09, |
| "Comparison": 57.03, |
| |
| "Compound-Overall": 56.06, |
| "Imagination": 56.96, |
| "Feature matching": 52.34, |
| |
| "Grammar-Overall": 64.84, |
| "Pronoun Reference": 76.10, |
| "Consistency": 70.37, |
| "Negation": 48.46, |
| |
| "Layout-Overall": 69.22, |
| "2D": 73.53, |
| "3D": 64.77, |
| |
| "Logical Reasoning": 39.09, |
| |
| "Text": 0.00 |
| }, |
| { |
| "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": 44.00, |
| "Style": 78.20, |
| "World Knowledge": 52.06, |
|
|
| "Attribute-Overall": 55.24, |
| "Quantity": 52.78, |
| "Expression": 33.97, |
| "Material": 58.49, |
| "Size": 61.11, |
| "Shape": 45.00, |
| "Color": 86.67, |
| |
| "Action-Overall": 43.44, |
| "Hand": 24.36, |
| "Full body": 54.35, |
| "Animal": 47.06, |
| "Non Contact": 31.63, |
| "Contact": 29.17, |
| "State": 67.92, |
| |
| "Relationship-Overall": 56.22, |
| "Composition": 59.80, |
| "Similarity": 52.22, |
| "Inclusion": 60.87, |
| "Comparison": 46.88, |
| |
| "Compound-Overall": 32.86, |
| "Imagination": 39.29, |
| "Feature matching": 26.30, |
| |
| "Grammar-Overall": 58.56, |
| "Pronoun Reference": 59.93, |
| "Consistency": 46.30, |
| "Negation": 67.31, |
| |
| "Layout-Overall": 37.31, |
| "2D": 38.97, |
| "3D": 35.61, |
| |
| "Logical Reasoning": 26.14, |
| |
| "Text": 0.00 |
| }, |
| { |
| "model": "OmniGen2", |
| "link": "https://arxiv.org/pdf/2506.18871", |
| "hf": "https://huggingface.co/OmniGen2/OmniGen2", |
| "open_source": true, |
| "release_date": "2025-06", |
|
|
| "Overall": 63.20, |
| "Style": 93.00, |
| "World Knowledge": 86.39, |
|
|
| "Attribute-Overall": 75.43, |
| "Quantity": 67.36, |
| "Expression": 69.87, |
| "Material": 78.30, |
| "Size": 77.78, |
| "Shape": 68.75, |
| "Color": 93.33, |
| |
| "Action-Overall": 66.54, |
| "Hand": 64.10, |
| "Full body": 69.57, |
| "Animal": 74.26, |
| "Non Contact": 61.73, |
| "Contact": 55.95, |
| "State": 73.58, |
| |
| "Relationship-Overall": 70.69, |
| "Composition": 77.03, |
| "Similarity": 66.67, |
| "Inclusion": 71.74, |
| "Comparison": 60.16, |
| |
| "Compound-Overall": 59.92, |
| "Imagination": 66.33, |
| "Feature matching": 53.39, |
| |
| "Grammar-Overall": 65.64, |
| "Pronoun Reference": 71.69, |
| "Consistency": 71.30, |
| "Negation": 54.62, |
| |
| "Layout-Overall": 69.96, |
| "2D": 76.84, |
| "3D": 62.88, |
| |
| "Logical Reasoning": 44.09, |
| |
| "Text": 0.29 |
| }, |
| { |
| "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": 58.50, |
| "Style": 94.40, |
| "World Knowledge": 86.55, |
|
|
| "Attribute-Overall": 63.89, |
| "Quantity": 56.94, |
| "Expression": 66.03, |
| "Material": 73.58, |
| "Size": 65.28, |
| "Shape": 38.75, |
| "Color": 84.17, |
| |
| "Action-Overall": 63.12, |
| "Hand": 42.31, |
| "Full body": 75.00, |
| "Animal": 80.88, |
| "Non Contact": 61.22, |
| "Contact": 44.05, |
| "State": 73.58, |
| |
| "Relationship-Overall": 67.39, |
| "Composition": 72.64, |
| "Similarity": 61.67, |
| "Inclusion": 69.57, |
| "Comparison": 60.16, |
| |
| "Compound-Overall": 51.55, |
| "Imagination": 63.52, |
| "Feature matching": 39.32, |
| |
| "Grammar-Overall": 59.00, |
| "Pronoun Reference": 64.34, |
| "Consistency": 60.19, |
| "Negation": 52.69, |
| |
| "Layout-Overall": 60.45, |
| "2D": 61.76, |
| "3D": 59.09, |
| |
| "Logical Reasoning": 38.64, |
| |
| "Text": 0.00 |
|
|
| }, |
| { |
| "model": "X-Omni", |
| "link": "https://arxiv.org/pdf/2507.22058", |
| "hf": "https://huggingface.co/X-Omni/X-Omni-Zh", |
| "open_source": true, |
| "release_date": "2025-08", |
|
|
| "Overall": 53.69, |
| "Style": 70.07, |
| "World Knowledge": 71.52, |
|
|
| "Attribute-Overall": 63.85, |
| "Quantity": 61.81, |
| "Expression": 52.56, |
| "Material": 63.51, |
| "Size": 67.36, |
| "Shape": 57.50, |
| "Color": 85.83, |
| |
| "Action-Overall": 58.37, |
| "Hand": 48.72, |
| "Full body": 68.48, |
| "Animal": 63.97, |
| "Non Contact": 56.53, |
| "Contact": 43.45, |
| "State": 66.51, |
| |
| "Relationship-Overall": 59.77, |
| "Composition": 60.14, |
| "Similarity": 60.00, |
| "Inclusion": 62.50, |
| "Comparison": 54.69, |
| |
| "Compound-Overall": 41.75, |
| "Imagination": 48.72, |
| "Feature matching": 34.64, |
| |
| "Grammar-Overall": 56.28, |
| "Pronoun Reference": 63.97, |
| "Consistency": 53.70, |
| "Negation": 50.38, |
| |
| "Layout-Overall": 59.51, |
| "2D": 66.91, |
| "3D": 51.89, |
| |
| "Logical Reasoning": 34.77, |
| |
| "Text": 20.98 |
| }, |
| { |
| "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": 65.69, |
| "Style": 92.30, |
| "World Knowledge": 86.71, |
| |
| "Attribute-Overall": 75.21, |
| "Quantity": 64.58, |
| "Expression": 63.46, |
| "Material": 83.49, |
| "Size": 79.86, |
| "Shape": 66.25, |
| "Color": 95.00, |
| |
| "Action-Overall": 65.78, |
| "Hand": 61.54, |
| "Full body": 63.59, |
| "Animal": 75.74, |
| "Non Contact": 65.31, |
| "Contact": 61.90, |
| "State": 67.92, |
| |
| "Relationship-Overall": 75.38, |
| "Composition": 77.70, |
| "Similarity": 67.78, |
| "Inclusion": 82.07, |
| "Comparison": 71.09, |
| |
| "Compound-Overall": 69.85, |
| "Imagination": 79.59, |
| "Feature matching": 59.90, |
| |
| "Grammar-Overall": 69.52, |
| "Pronoun Reference": 73.16, |
| "Consistency": 75.00, |
| "Negation": 61.15, |
| |
| "Layout-Overall": 77.61, |
| "2D": 82.72, |
| "3D": 72.35, |
| |
| "Logical Reasoning": 37.95, |
| |
| "Text": 6.61 |
| }, |
| { |
| "model": "HiDream-I1-Full", |
| "link": "https://arxiv.org/pdf/2505.22705", |
| "hf": "https://huggingface.co/HiDream-ai/HiDream-I1-Full", |
| "open_source": true, |
| "release_date": "2025-05", |
|
|
| "Overall": 50.65, |
| "Style": 83.30, |
| "World Knowledge": 78.32, |
|
|
| "Attribute-Overall": 62.18, |
| "Quantity": 69.44, |
| "Expression": 45.51, |
| "Material": 55.66, |
| "Size": 70.14, |
| "Shape": 55.00, |
| "Color": 86.67, |
| |
| "Action-Overall": 53.71, |
| "Hand": 44.23, |
| "Full body": 57.61, |
| "Animal": 55.88, |
| "Non Contact": 53.06, |
| "Contact": 47.62, |
| "State": 61.32, |
| |
| "Relationship-Overall": 57.23, |
| "Composition": 57.77, |
| "Similarity": 52.78, |
| "Inclusion": 63.04, |
| "Comparison": 53.91, |
| |
| "Compound-Overall": 34.54, |
| "Imagination": 38.01, |
| "Feature matching": 30.99, |
| |
| "Grammar-Overall": 53.88, |
| "Pronoun Reference": 62.13, |
| "Consistency": 51.85, |
| "Negation": 46.92, |
| |
| "Layout-Overall": 59.70, |
| "2D": 63.60, |
| "3D": 55.68, |
| |
| "Logical Reasoning": 23.64, |
| |
| "Text": 0.00 |
| }, |
| { |
| "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": 77.76, |
| "Style": 92.20, |
| "World Knowledge": 90.51, |
| "Attribute-Overall": 84.19, |
| "Quantity": 87.50, |
| "Expression": 80.77, |
| "Material": 82.55, |
| "Size": 86.11, |
| "Shape": 75.00, |
| "Color": 97.50, |
| |
| "Action-Overall": 80.51, |
| "Hand": 76.28, |
| "Full body": 84.24, |
| "Animal": 85.29, |
| "Non Contact": 78.06, |
| "Contact": 79.17, |
| "State": 80.66, |
| |
| "Relationship-Overall": 82.74, |
| "Composition": 80.74, |
| "Similarity": 80.56, |
| "Inclusion": 87.50, |
| "Comparison": 83.59, |
| |
| "Compound-Overall": 70.62, |
| "Imagination": 71.68, |
| "Feature matching": 69.53, |
| |
| "Grammar-Overall": 61.50, |
| "Pronoun Reference": 80.15, |
| "Consistency": 67.13, |
| "Negation": 37.31, |
| |
| "Layout-Overall": 85.45, |
| "2D": 88.24, |
| "3D": 82.58, |
| |
| "Logical Reasoning": 50.23, |
| |
| "Text": 79.60 |
| }, |
| { |
| "model": "BLIP3-o", |
| "link": "https://arxiv.org/pdf/2505.09568", |
| "hf": "https://huggingface.co/BLIP3o/BLIP3o-NEXT-SFT-3B", |
| "open_source": true, |
| "release_date": "2025-08", |
|
|
| "Overall": 59.25, |
| "Style": 92.60, |
| "World Knowledge": 81.17, |
| "Attribute-Overall": 66.56, |
| "Quantity": 57.64, |
| "Expression": 65.38, |
| "Material": 67.92, |
| "Size": 77.08, |
| "Shape": 47.50, |
| "Color": 89.17, |
| |
| "Action-Overall": 64.35, |
| "Hand": 57.69, |
| "Full body": 73.37, |
| "Animal": 68.38, |
| "Non Contact": 59.18, |
| "Contact": 55.95, |
| "State": 70.28, |
| |
| "Relationship-Overall": 65.36, |
| "Composition": 69.26, |
| "Similarity": 58.33, |
| "Inclusion": 63.04, |
| "Comparison": 69.53, |
| |
| "Compound-Overall": 51.80, |
| "Imagination": 61.99, |
| "Feature matching": 41.41, |
| |
| "Grammar-Overall": 63.37, |
| "Pronoun Reference": 70.22, |
| "Consistency": 57.41, |
| "Negation": 61.16, |
| |
| "Layout-Overall": 65.67, |
| "2D": 69.12, |
| "3D": 62.12, |
| |
| "Logical Reasoning": 41.59, |
| |
| "Text": 0.00 |
| }, |
| { |
| "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": 44.48, |
| "Style": 74.60, |
| "World Knowledge": 50.00, |
| "Attribute-Overall": 55.98, |
| "Quantity": 44.44, |
| "Expression": 57.69, |
| "Material": 56.13, |
| "Size": 63.89, |
| "Shape": 48.12, |
| "Color": 68.33, |
| |
| "Action-Overall": 47.62, |
| "Hand": 37.82, |
| "Full body": 61.41, |
| "Animal": 45.59, |
| "Non Contact": 45.41, |
| "Contact": 36.90, |
| "State": 54.72, |
| |
| "Relationship-Overall": 53.55, |
| "Composition": 54.05, |
| "Similarity": 48.33, |
| "Inclusion": 50.00, |
| "Comparison": 64.84, |
| |
| "Compound-Overall": 26.55, |
| "Imagination": 32.14, |
| "Feature matching": 20.83, |
| |
| "Grammar-Overall": 54.14, |
| "Pronoun Reference": 65.07, |
| "Consistency": 49.54, |
| "Negation": 46.54, |
| |
| "Layout-Overall": 54.85, |
| "2D": 58.82, |
| "3D": 50.76, |
| |
| "Logical Reasoning": 27.50, |
| |
| "Text": 0.00 |
| }, |
| { |
| "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": 20.93, |
|
|
| "Style": 58.50, |
|
|
| "World Knowledge": 18.67, |
|
|
| "Attribute-Overall": 19.23, |
| "Quantity": 22.92, |
| "Expression": 10.90, |
| "Material": 21.70, |
| "Size": 24.31, |
| "Shape": 8.12, |
| "Color": 30.00, |
|
|
| "Action-Overall": 22.05, |
| "Hand": 4.49, |
| "Full body": 31.52, |
| "Animal": 22.06, |
| "Non Contact": 14.80, |
| "Contact": 19.05, |
| "State": 35.85, |
|
|
| "Relationship-Overall": 19.54, |
| "Composition": 23.65, |
| "Similarity": 16.11, |
| "Inclusion": 20.11, |
| "Comparison": 14.06, |
|
|
| "Compound-Overall": 10.70, |
| "Imagination": 19.13, |
| "Feature matching": 2.08, |
|
|
| "Grammar-Overall": 35.03, |
| "Pronoun Reference": 32.72, |
| "Consistency": 16.67, |
| "Negation": 52.69, |
|
|
| "Layout-Overall": 14.93, |
| "2D": 12.13, |
| "3D": 17.80, |
|
|
| "Logical Reasoning": 10.68, |
|
|
| "Text": 0.00 |
| }, |
| { |
| "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": 55.14, |
| "Style": 82.40, |
| "World Knowledge": 84.18, |
| "Attribute-Overall": 63.35, |
| "Quantity": 68.75, |
| "Expression": 44.87, |
| "Material": 56.60, |
| "Size": 72.92, |
| "Shape": 53.75, |
| "Color": 94.17, |
| |
| "Action-Overall": 61.69, |
| "Hand": 61.54, |
| "Full body": 66.30, |
| "Animal": 64.71, |
| "Non Contact": 52.04, |
| "Contact": 54.76, |
| "State": 70.28, |
| |
| "Relationship-Overall": 61.68, |
| "Composition": 61.82, |
| "Similarity": 62.22, |
| "Inclusion": 63.59, |
| "Comparison": 57.81, |
| |
| "Compound-Overall": 45.75, |
| "Imagination": 51.02, |
| "Feature matching": 40.36, |
| |
| "Grammar-Overall": 54.55, |
| "Pronoun Reference": 67.65, |
| "Consistency": 57.41, |
| "Negation": 38.46, |
| |
| "Layout-Overall": 65.30, |
| "2D": 75.00, |
| "3D": 55.30, |
| |
| "Logical Reasoning": 30.23, |
| |
| "Text": 2.30 |
| }, |
| { |
| "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": 30.98, |
|
|
| "Style": 78.10, |
|
|
| "World Knowledge": 27.85, |
|
|
| "Attribute-Overall": 30.88, |
| "Quantity": 29.17, |
| "Expression": 17.31, |
| "Material": 35.85, |
| "Size": 45.83, |
| "Shape": 14.37, |
| "Color": 17.31, |
|
|
| "Action-Overall": 31.37, |
| "Hand": 14.10, |
| "Full body": 38.59, |
| "Animal": 42.65, |
| "Non Contact": 24.49, |
| "Contact": 23.21, |
| "State": 43.40, |
|
|
| "Relationship-Overall": 30.58, |
| "Composition": 32.43, |
| "Similarity": 32.22, |
| "Inclusion": 27.72, |
| "Comparison": 28.12, |
|
|
| "Compound-Overall": 17.53, |
| "Imagination": 25.26, |
| "Feature matching": 9.64, |
|
|
| "Grammar-Overall": 48.40, |
| "Pronoun Reference": 48.53, |
| "Consistency": 33.33, |
| "Negation": 60.77, |
|
|
| "Layout-Overall": 31.72, |
| "2D": 31.25, |
| "3D": 32.20, |
|
|
| "Logical Reasoning": 13.41, |
|
|
| "Text": 0.00 |
| }, |
| { |
| "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": 30.83, |
| "Style": 75.60, |
| "World Knowledge": 39.08, |
| "Attribute-Overall": 33.12, |
| "Quantity": 24.31, |
| "Expression": 19.23, |
| "Material": 43.87, |
| "Size": 45.14, |
| "Shape": 18.75, |
| "Color": 47.50, |
| |
| "Action-Overall": 26.33, |
| "Hand": 13.46, |
| "Full body": 26.09, |
| "Animal": 34.56, |
| "Non Contact": 22.45, |
| "Contact": 20.83, |
| "State": 38.68, |
| |
| "Relationship-Overall": 32.74, |
| "Composition": 38.85, |
| "Similarity": 35.56, |
| "Inclusion": 26.09, |
| "Comparison": 24.22, |
| |
| "Compound-Overall": 24.48, |
| "Imagination": 33.42, |
| "Feature matching": 15.36, |
| |
| "Grammar-Overall": 36.63, |
| "Pronoun Reference": 36.76, |
| "Consistency": 31.94, |
| "Negation": 40.38, |
| |
| "Layout-Overall": 30.04, |
| "2D": 29.78, |
| "3D": 30.30, |
| |
| "Logical Reasoning": 10.23, |
| |
| "Text": 0.00 |
| }, |
| { |
| "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": 58.80, |
| "Style": 85.20, |
| "World Knowledge": 86.23, |
|
|
| "Attribute-Overall": 69.34, |
| "Quantity": 70.14, |
| "Expression": 51.92, |
| "Material": 73.11, |
| "Size": 77.78, |
| "Shape": 56.25, |
| "Color": 91.67, |
| |
| "Action-Overall": 65.02, |
| "Hand": 58.33, |
| "Full body": 59.24, |
| "Animal": 71.32, |
| "Non Contact": 63.78, |
| "Contact": 57.54, |
| "State": 77.83, |
| |
| "Relationship-Overall": 67.13, |
| "Composition": 71.96, |
| "Similarity": 69.44, |
| "Inclusion": 67.39, |
| "Comparison": 52.34, |
| |
| "Compound-Overall": 66.03, |
| "Imagination": 64.80, |
| "Feature matching": 45.05, |
| |
| "Grammar-Overall": 56.68, |
| "Pronoun Reference": 67.28, |
| "Consistency": 59.26, |
| "Negation": 43.46, |
| |
| "Layout-Overall": 62.31, |
| "2D": 58.82, |
| "3D": 65.91, |
| |
| "Logical Reasoning": 36.14, |
| |
| "Text": 4.89 |
| }, |
| { |
| "model": "Seedream-4.0", |
| "link": "https://www.volcengine.com/docs/82379/1541523", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-09", |
|
|
| "Overall": 87.31, |
|
|
| "Style": 99.00, |
|
|
| "World Knowledge": 94.94, |
|
|
| "Attribute-Overall": 90.06, |
| "Quantity": 86.81, |
| "Expression": 85.90, |
| "Material": 97.64, |
| "Size": 86.81, |
| "Shape": 83.12, |
| "Color": 99.17, |
|
|
| "Action-Overall": 87.55, |
| "Hand": 82.69, |
| "Full body": 90.22, |
| "Animal": 91.91, |
| "Non Contact": 84.69, |
| "Contact": 82.74, |
| "State": 92.45, |
|
|
| "Relationship-Overall": 88.58, |
| "Composition": 85.14, |
| "Similarity": 84.44, |
| "Inclusion": 95.65, |
| "Comparison": 92.19, |
|
|
| "Compound-Overall": 81.57, |
| "Imagination": 85.20, |
| "Feature matching": 77.86, |
|
|
| "Grammar-Overall": 78.48, |
| "Pronoun Reference": 89.71, |
| "Consistency": 75.00, |
| "Negation": 69.62, |
|
|
| "Layout-Overall": 90.30, |
| "2D": 90.81, |
| "3D": 89.77, |
|
|
| "Logical Reasoning": 68.64, |
|
|
| "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": 79.52, |
|
|
| "Style": 97.50, |
|
|
| "World Knowledge": 96.84, |
|
|
| "Attribute-Overall": 86.22, |
| "Quantity": 83.33, |
| "Expression": 77.56, |
| "Material": 92.92, |
| "Size": 93.75, |
| "Shape": 72.50, |
| "Color": 98.33, |
|
|
| "Action-Overall": 90.40, |
| "Hand": 89.10, |
| "Full body": 89.67, |
| "Animal": 93.38, |
| "Non Contact": 86.73, |
| "Contact": 90.48, |
| "State": 93.40, |
|
|
| "Relationship-Overall": 90.74, |
| "Composition": 91.55, |
| "Similarity": 83.33, |
| "Inclusion": 94.57, |
| "Comparison": 93.75, |
|
|
| "Compound-Overall": 85.70, |
| "Imagination": 92.60, |
| "Feature matching": 78.65, |
|
|
| "Grammar-Overall": 82.89, |
| "Pronoun Reference": 92.65, |
| "Consistency": 82.87, |
| "Negation": 72.69, |
|
|
| "Layout-Overall": 89.18, |
| "2D": 91.54, |
| "3D": 86.74, |
|
|
| "Logical Reasoning": 73.18, |
|
|
| "Text": 2.59 |
| }, |
| { |
| "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": 54.93, |
|
|
| "Style": 64.75, |
|
|
| "World Knowledge": 71.05, |
|
|
| "Attribute-Overall": 60.43, |
| "Quantity": 54.29, |
| "Expression": 46.05, |
| "Material": 72.60, |
| "Size": 57.64, |
| "Shape": 50.62, |
| "Color": 81.90, |
|
|
| "Action-Overall": 60.42, |
| "Hand": 52.63, |
| "Full body": 65.22, |
| "Animal": 75.00, |
| "Non Contact": 51.56, |
| "Contact": 54.37, |
| "State": 65.09, |
|
|
| "Relationship-Overall": 65.90, |
| "Composition": 66.89, |
| "Similarity": 51.11, |
| "Inclusion": 74.43, |
| "Comparison": 72.66, |
|
|
| "Compound-Overall": 61.00, |
| "Imagination": 68.22, |
| "Feature matching": 53.49, |
|
|
| "Grammar-Overall": 58.38, |
| "Pronoun Reference": 55.38, |
| "Consistency": 55.09, |
| "Negation": 64.29, |
|
|
| "Layout-Overall": 64.71, |
| "2D": 59.93, |
| "3D": 69.62, |
|
|
| "Logical Reasoning": 42.03, |
|
|
| "Text": 0.59 |
| }, |
| { |
| "model": "HiDream_v2L", |
| "link": "https://hidreamai.com/doc/txt2img/request", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-07", |
|
|
| "Overall": 59.95, |
|
|
| "Style": 89.34, |
|
|
| "World Knowledge": 91.02, |
|
|
| "Attribute-Overall": 67.87, |
| "Quantity": 71.43, |
| "Expression": 42.31, |
| "Material": 70.59, |
| "Size": 70.00, |
| "Shape": 64.52, |
| "Color": 94.17, |
|
|
| "Action-Overall": 64.90, |
| "Hand": 48.72, |
| "Full body": 65.22, |
| "Animal": 75.00, |
| "Non Contact": 71.88, |
| "Contact": 55.95, |
| "State": 71.15, |
|
|
| "Relationship-Overall": 72.67, |
| "Composition": 78.82, |
| "Similarity": 65.00, |
| "Inclusion": 75.56, |
| "Comparison": 65.32, |
|
|
| "Compound-Overall": 53.19, |
| "Imagination": 62.63, |
| "Feature matching": 43.55, |
|
|
| "Grammar-Overall": 62.57, |
| "Pronoun Reference": 75.38, |
| "Consistency": 68.75, |
| "Negation": 44.53, |
|
|
| "Layout-Overall": 64.77, |
| "2D": 66.29, |
| "3D": 63.26, |
|
|
| "Logical Reasoning": 32.01, |
|
|
| "Text": 1.16 |
| }, |
| { |
| "model": "FLUX-kontext-pro", |
| "link": "https://bfl.ai/models/flux-kontext", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-05", |
|
|
| "Overall": 1.27, |
| "Style": 6.93, |
| "World Knowledge": 0.00, |
|
|
| "Attribute-Overall": 0.11, |
| "Quantity": 0.69, |
| "Expression": 0.00, |
| "Material": 0.00, |
| "Size": 0.00, |
| "Shape": 0.00, |
| "Color": 0.00, |
| |
| "Action-Overall": 0.29, |
| "Hand": 0.00, |
| "Full body": 0.00, |
| "Animal": 0.00, |
| "Non Contact": 0.00, |
| "Contact": 0.00, |
| "State": 1.47, |
| |
| "Relationship-Overall": 0.13, |
| "Composition": 0.34, |
| "Similarity": 0.00, |
| "Inclusion": 0.00, |
| "Comparison": 0.00, |
| |
| "Compound-Overall": 0.00, |
| "Imagination": 0.00, |
| "Feature matching": 0.00, |
| |
| "Grammar-Overall": 5.24, |
| "Pronoun Reference": 0.00, |
| "Consistency": 2.31, |
| "Negation": 13.28, |
| |
| "Layout-Overall": 0.00, |
| "2D": 0.00, |
| "3D": 0.00, |
| |
| "Logical Reasoning": 0.00, |
| |
| "Text": 0.00 |
| }, |
| { |
| "model": "FLUX-pro-1.1-Ultra", |
| "link": "https://bfl.ai/", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2024-11", |
|
|
| "Overall": 1.31, |
|
|
| "Style": 7.63, |
|
|
| "World Knowledge": 0.32, |
|
|
| "Attribute-Overall": 0.32, |
| "Quantity": 0.00, |
| "Expression": 0.00, |
| "Material": 0.94, |
| "Size": 0.00, |
| "Shape": 0.00, |
| "Color": 0.83, |
|
|
| "Action-Overall": 0.00, |
| "Hand": 0.00, |
| "Full body": 0.00, |
| "Animal": 0.00, |
| "Non Contact": 0.00, |
| "Contact": 0.00, |
| "State": 0.00, |
|
|
| "Relationship-Overall": 0.26, |
| "Composition": 0.34, |
| "Similarity": 0.57, |
| "Inclusion": 0.00, |
| "Comparison": 0.00, |
|
|
| "Compound-Overall": 0.00, |
| "Imagination": 0.00, |
| "Feature matching": 0.00, |
|
|
| "Grammar-Overall": 4.30, |
| "Pronoun Reference": 0.37, |
| "Consistency": 1.39, |
| "Negation": 10.94, |
|
|
| "Layout-Overall": 0.19, |
| "2D": 0.37, |
| "3D": 0.00, |
|
|
| "Logical Reasoning": 0.00, |
|
|
| "Text": 0.00 |
| }, |
| { |
| "model": "DALL-E-3", |
| "link": "https://openai.com/zh-Hans-CN/index/dall-e-3/", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2023-09", |
|
|
| "Overall": 67.93, |
|
|
| "Style": 95.90, |
|
|
| "World Knowledge": 93.04, |
|
|
| "Attribute-Overall": 78.42, |
| "Quantity": 60.42, |
| "Expression": 68.59, |
| "Material": 91.04, |
| "Size": 90.28, |
| "Shape": 65.00, |
| "Color": 94.17, |
|
|
| "Action-Overall": 72.24, |
| "Hand": 69.87, |
| "Full body": 77.17, |
| "Animal": 82.35, |
| "Non Contact": 66.33, |
| "Contact": 61.90, |
| "State": 76.89, |
|
|
| "Relationship-Overall": 79.95, |
| "Composition": 81.76, |
| "Similarity": 77.78, |
| "Inclusion": 87.50, |
| "Comparison": 67.97, |
|
|
| "Compound-Overall": 72.94, |
| "Imagination": 82.14, |
| "Feature matching": 63.54, |
|
|
| "Grammar-Overall": 71.52, |
| "Pronoun Reference": 79.78, |
| "Consistency": 76.39, |
| "Negation": 58.85, |
|
|
| "Layout-Overall": 62.50, |
| "2D": 54.41, |
| "3D": 70.83, |
|
|
| "Logical Reasoning": 51.59, |
|
|
| "Text": 1.15 |
| }, |
| { |
| "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": 81.04, |
|
|
| "Style": 95.50, |
|
|
| "World Knowledge": 92.41, |
|
|
| "Attribute-Overall": 91.88, |
| "Quantity": 88.89, |
| "Expression": 91.03, |
| "Material": 96.23, |
| "Size": 90.28, |
| "Shape": 86.25, |
| "Color": 98.33, |
|
|
| "Action-Overall": 85.74, |
| "Hand": 83.33, |
| "Full body": 87.50, |
| "Animal": 89.71, |
| "Non Contact": 81.63, |
| "Contact": 82.14, |
| "State": 90.09, |
|
|
| "Relationship-Overall": 82.99, |
| "Composition": 85.47, |
| "Similarity": 73.33, |
| "Inclusion": 90.76, |
| "Comparison": 79.69, |
|
|
| "Compound-Overall": 76.16, |
| "Imagination": 80.10, |
| "Feature matching": 72.14, |
|
|
| "Grammar-Overall": 62.83, |
| "Pronoun Reference": 83.46, |
| "Consistency": 74.07, |
| "Negation": 31.92, |
|
|
| "Layout-Overall": 82.65, |
| "2D": 84.93, |
| "3D": 80.30, |
|
|
| "Logical Reasoning": 57.73, |
|
|
| "Text": 82.47 |
| }, |
| { |
| "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": 66.96, |
| "Style": 91.06, |
| "World Knowledge": 84.39, |
|
|
| "Attribute-Overall": 73.93, |
| "Quantity": 75.00, |
| "Expression": 67.31, |
| "Material": 74.06, |
| "Size": 74.31, |
| "Shape": 66.25, |
| "Color": 90.83, |
| |
| "Action-Overall": 72.52, |
| "Hand": 69.23, |
| "Full body": 80.00, |
| "Animal": 84.56, |
| "Non Contact": 65.31, |
| "Contact": 61.90, |
| "State": 75.94, |
| |
| "Relationship-Overall": 76.78, |
| "Composition": 71.28, |
| "Similarity": 72.78, |
| "Inclusion": 85.87, |
| "Comparison": 82.03, |
| |
| "Compound-Overall": 64.77, |
| "Imagination": 74.23, |
| "Feature matching": 55.00, |
| |
| "Grammar-Overall": 70.59, |
| "Pronoun Reference": 77.21, |
| "Consistency": 63.43, |
| "Negation": 69.62, |
| |
| "Layout-Overall": 71.83, |
| "2D": 73.16, |
| "3D": 70.45, |
| |
| "Logical Reasoning": 51.82, |
| |
| "Text": 11.92 |
| }, |
| { |
| "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": 2.74, |
| "Style": 10.50, |
| "World Knowledge": 0.63, |
|
|
| "Attribute-Overall": 0.43, |
| "Quantity": 0.00, |
| "Expression": 1.92, |
| "Material": 0.47, |
| "Size": 0.00, |
| "Shape": 0.00, |
| "Color": 0.00, |
| |
| "Action-Overall": 0.95, |
| "Hand": 1.92, |
| "Full body": 0.54, |
| "Animal": 0.74, |
| "Non Contact": 0.00, |
| "Contact": 0.00, |
| "State": 2.36, |
| |
| "Relationship-Overall": 0.13, |
| "Composition": 0.34, |
| "Similarity": 0.00, |
| "Inclusion": 0.00, |
| "Comparison": 0.00, |
| |
| "Compound-Overall": 0.13, |
| "Imagination": 0.26, |
| "Feature matching": 0.00, |
| |
| "Grammar-Overall": 7.75, |
| "Pronoun Reference": 0.74, |
| "Consistency": 1.39, |
| "Negation": 20.38, |
| |
| "Layout-Overall": 0.19, |
| "2D": 0.00, |
| "3D": 0.38, |
| |
| "Logical Reasoning": 0.00, |
| |
| "Text": 0.00 |
| }, |
| { |
| "model": "Nano Banana", |
| "link": "https://ainanobanana.io/", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-08", |
|
|
| "Overall": 80.91, |
|
|
| "Style": 99.27, |
|
|
| "World Knowledge": 96.47, |
|
|
| "Attribute-Overall": 87.76, |
| "Quantity": 81.62, |
| "Expression": 80.79, |
| "Material": 89.66, |
| "Size": 95.74, |
| "Shape": 82.05, |
| "Color": 98.33, |
|
|
| "Action-Overall": 86.99, |
| "Hand": 86.54, |
| "Full body": 91.38, |
| "Animal": 90.44, |
| "Non Contact": 81.96, |
| "Contact": 81.44, |
| "State": 90.64, |
|
|
| "Relationship-Overall": 91.39, |
| "Composition": 92.33, |
| "Similarity": 83.89, |
| "Inclusion": 93.44, |
| "Comparison": 96.88, |
|
|
| "Compound-Overall": 86.89, |
| "Imagination": 90.40, |
| "Feature matching": 83.42, |
|
|
| "Grammar-Overall": 83.33, |
| "Pronoun Reference": 87.27, |
| "Consistency": 84.69, |
| "Negation": 78.12, |
|
|
| "Layout-Overall": 88.80, |
| "2D": 91.82, |
| "3D": 85.66, |
|
|
| "Logical Reasoning": 76.10, |
|
|
| "Text": 12.06 |
| }, |
| { |
| "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": 53.36, |
|
|
| "Style": 92.50, |
|
|
| "World Knowledge": 84.97, |
|
|
| "Attribute-Overall": 62.93, |
| "Quantity": 63.19, |
| "Expression": 46.15, |
| "Material": 72.17, |
| "Size": 63.89, |
| "Shape": 49.38, |
| "Color": 85.00, |
|
|
| "Action-Overall": 57.22, |
| "Hand": 45.51, |
| "Full body": 67.93, |
| "Animal": 61.76, |
| "Non Contact": 48.47, |
| "Contact": 47.02, |
| "State": 69.81, |
|
|
| "Relationship-Overall": 59.39, |
| "Composition": 65.88, |
| "Similarity": 64.44, |
| "Inclusion": 56.52, |
| "Comparison": 41.41, |
|
|
| "Compound-Overall": 44.59, |
| "Imagination": 52.04, |
| "Feature matching": 36.98, |
|
|
| "Grammar-Overall": 54.68, |
| "Pronoun Reference": 59.93, |
| "Consistency": 62.04, |
| "Negation": 43.08, |
|
|
| "Layout-Overall": 47.76, |
| "2D": 39.71, |
| "3D": 56.06, |
|
|
| "Logical Reasoning": 29.55, |
|
|
| "Text": 0.00 |
| }, |
| { |
| "model": "Recraft", |
| "link": "https://www.recraft.ai/docs#generate-image", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2024-12", |
|
|
| "Overall": 57.67, |
| "Style": 87.70, |
| "World Knowledge": 90.03, |
|
|
| "Attribute-Overall": 69.34, |
| "Quantity": 66.67, |
| "Expression": 59.62, |
| "Material": 66.51, |
| "Size": 73.61, |
| "Shape": 61.25, |
| "Color": 95.83, |
| |
| "Action-Overall": 63.88, |
| "Hand": 50.64, |
| "Full body": 72.28, |
| "Animal": 77.94, |
| "Non Contact": 63.78, |
| "Contact": 45.24, |
| "State": 72.17, |
| |
| "Relationship-Overall": 64.47, |
| "Composition": 65.54, |
| "Similarity": 58.89, |
| "Inclusion": 65.22, |
| "Comparison": 68.75, |
| |
| "Compound-Overall": 43.94, |
| "Imagination": 45.92, |
| "Feature matching": 41.93, |
| |
| "Grammar-Overall": 60.56, |
| "Pronoun Reference": 62.87, |
| "Consistency": 59.26, |
| "Negation": 59.23, |
| |
| "Layout-Overall": 58.40, |
| "2D": 55.15, |
| "3D": 61.74, |
| |
| "Logical Reasoning": 34.09, |
| |
| "Text": 4.31 |
| }, |
| { |
| "model": "Imagen-3.0-generate-002", |
| "link": "https://arxiv.org/pdf/2408.07009", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-02", |
|
|
| "Overall": 13.62, |
|
|
| "Style": 8.30, |
|
|
| "World Knowledge": 0.00, |
|
|
| "Attribute-Overall": 0.00, |
| "Quantity": 0.00, |
| "Expression": 0.00, |
| "Material": 0.00, |
| "Size": 0.00, |
| "Shape": 0.00, |
| "Color": 0.00, |
|
|
| "Action-Overall": 0.38, |
| "Hand": 0.00, |
| "Full body": 0.54, |
| "Animal": 0.00, |
| "Non Contact": 0.00, |
| "Contact": 0.00, |
| "State": 1.42, |
|
|
| "Relationship-Overall": 0.13, |
| "Composition": 0.34, |
| "Similarity": 0.00, |
| "Inclusion": 0.00, |
| "Comparison": 0.00, |
|
|
| "Compound-Overall": 0.00, |
| "Imagination": 0.00, |
| "Feature matching": 0.00, |
|
|
| "Grammar-Overall": 4.81, |
| "Pronoun Reference": 0.00, |
| "Consistency": 0.46, |
| "Negation": 13.46, |
|
|
| "Layout-Overall": 0.00, |
| "2D": 0.00, |
| "3D": 0.00, |
|
|
| "Logical Reasoning": 0.00, |
|
|
| "Text": 0.00 |
| }, |
| { |
| "model": "Imagen-4.0-Fast-preview-06-06", |
| "link": "https://deepmind.google/models/imagen/", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-06", |
|
|
| "Overall": 71.60, |
|
|
| "Style": 93.30, |
|
|
| "World Knowledge": 91.30, |
|
|
| "Attribute-Overall": 80.98, |
| "Quantity": 76.39, |
| "Expression": 66.03, |
| "Material": 83.49, |
| "Size": 88.19, |
| "Shape": 78.75, |
| "Color": 95.83, |
|
|
| "Action-Overall": 79.28, |
| "Hand": 74.36, |
| "Full body": 79.35, |
| "Animal": 83.82, |
| "Non Contact": 73.47, |
| "Contact": 75.60, |
| "State": 88.21, |
|
|
| "Relationship-Overall": 82.49, |
| "Composition": 82.09, |
| "Similarity": 78.33, |
| "Inclusion": 88.04, |
| "Comparison": 81.25, |
|
|
| "Compound-Overall": 73.97, |
| "Imagination": 83.67, |
| "Feature matching": 64.06, |
|
|
| "Grammar-Overall": 77.41, |
| "Pronoun Reference": 83.82, |
| "Consistency": 78.24, |
| "Negation": 70.00, |
|
|
| "Layout-Overall": 78.73, |
| "2D": 80.51, |
| "3D": 76.89, |
|
|
| "Logical Reasoning": 54.77, |
|
|
| "Text": 3.74 |
| }, |
| { |
| "model": "FLUX-kontext-max", |
| "link": "https://bfl.ai/models/flux-kontext", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-05", |
|
|
| "Overall": 71.85, |
| "Style": 96.38, |
| "World Knowledge": 92.83, |
|
|
| "Attribute-Overall": 76.41, |
| "Quantity": 65.97, |
| "Expression": 69.44, |
| "Material": 80.19, |
| "Size": 84.72, |
| "Shape": 66.67, |
| "Color": 93.33, |
| |
| "Action-Overall": 78.59, |
| "Hand": 76.32, |
| "Full body": 83.15, |
| "Animal": 83.33, |
| "Non Contact": 69.90, |
| "Contact": 73.17, |
| "State": 85.78, |
| |
| "Relationship-Overall": 83.97, |
| "Composition": 85.14, |
| "Similarity": 74.43, |
| "Inclusion": 91.67, |
| "Comparison": 83.59, |
| |
| "Compound-Overall": 75.13, |
| "Imagination": 82.65, |
| "Feature matching": 67.12, |
| |
| "Grammar-Overall": 75.68, |
| "Pronoun Reference": 79.85, |
| "Consistency": 75.46, |
| "Negation": 71.48, |
| |
| "Layout-Overall": 81.34, |
| "2D": 81.62, |
| "3D": 81.06, |
| |
| "Logical Reasoning": 56.48, |
| |
| "Text": 1.72 |
| }, |
| { |
| "model": "Seedream-3.0", |
| "link": "https://www.byteplus.com/en/product/Seedream", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-06", |
|
|
| "Overall": 81.68, |
|
|
| "Style": 97.50, |
|
|
| "World Knowledge": 93.99, |
|
|
| "Attribute-Overall": 88.03, |
| "Quantity": 84.03, |
| "Expression": 82.69, |
| "Material": 94.34, |
| "Size": 89.58, |
| "Shape": 80.00, |
| "Color": 97.50, |
|
|
| "Action-Overall": 86.98, |
| "Hand": 85.26, |
| "Full body": 90.76, |
| "Animal": 89.71, |
| "Non Contact": 85.20, |
| "Contact": 80.36, |
| "State": 90.09, |
|
|
| "Relationship-Overall": 84.39, |
| "Composition": 86.82, |
| "Similarity": 74.44, |
| "Inclusion": 90.22, |
| "Comparison": 84.38, |
|
|
| "Compound-Overall": 76.68, |
| "Imagination": 82.14, |
| "Feature matching": 71.09, |
|
|
| "Grammar-Overall": 67.25, |
| "Pronoun Reference": 84.19, |
| "Consistency": 79.17, |
| "Negation": 39.62, |
|
|
| "Layout-Overall": 84.14, |
| "2D": 89.34, |
| "3D": 78.79, |
|
|
| "Logical Reasoning": 59.09, |
|
|
| "Text": 78.74 |
| }, |
| { |
| "model": "Imagen-4.0-Ultra-preview-06-06", |
| "link": "https://deepmind.google/models/imagen/", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-06", |
|
|
| "Overall": 83.21, |
|
|
| "Style": 98.90, |
|
|
| "World Knowledge": 97.94, |
|
|
| "Attribute-Overall": 90.71, |
| "Quantity": 88.89, |
| "Expression": 79.49, |
| "Material": 94.81, |
| "Size": 93.75, |
| "Shape": 88.12, |
| "Color": 100.0, |
|
|
| "Action-Overall": 93.82, |
| "Hand": 94.87, |
| "Full body": 92.93, |
| "Animal": 95.59, |
| "Non Contact": 87.76, |
| "Contact": 95.24, |
| "State": 97.17, |
|
|
| "Relationship-Overall": 92.13, |
| "Composition": 91.22, |
| "Similarity": 87.22, |
| "Inclusion": 97.83, |
| "Comparison": 92.97, |
|
|
| "Compound-Overall": 89.95, |
| "Imagination": 94.90, |
| "Feature matching": 84.90, |
|
|
| "Grammar-Overall": 87.43, |
| "Pronoun Reference": 93.01, |
| "Consistency": 85.65, |
| "Negation": 83.08, |
|
|
| "Layout-Overall": 92.16, |
| "2D": 93.75, |
| "3D": 90.53, |
|
|
| "Logical Reasoning": 79.32, |
|
|
| "Text": 9.77 |
| }, |
| { |
| "model": "GPT-4o", |
| "link": "https://platform.openai.com/docs/guides/image-generation", |
| "hf": "-", |
| "open_source": false, |
| "release_date": "2025-03", |
|
|
| "Overall": 91.02, |
|
|
| "Style": 99.39, |
|
|
| "World Knowledge": 98.72, |
|
|
| "Attribute-Overall": 94.99, |
| "Quantity": 93.62, |
| "Expression": 94.59, |
| "Material": 96.19, |
| "Size": 93.06, |
| "Shape": 92.95, |
| "Color": 100.0, |
|
|
| "Action-Overall": 92.34, |
| "Hand": 94.08, |
| "Full body": 97.28, |
| "Animal": 90.91, |
| "Non Contact": 90.31, |
| "Contact": 88.34, |
| "State": 92.65, |
|
|
| "Relationship-Overall": 95.77, |
| "Composition": 97.30, |
| "Similarity": 93.18, |
| "Inclusion": 96.69, |
| "Comparison": 94.53, |
|
|
| "Compound-Overall": 93.91, |
| "Imagination": 95.92, |
| "Feature matching": 91.74, |
|
|
| "Grammar-Overall": 91.02, |
| "Pronoun Reference": 95.15, |
| "Consistency": 89.35, |
| "Negation": 88.05, |
|
|
| "Layout-Overall": 89.27, |
| "2D": 89.18, |
| "3D": 89.35, |
|
|
| "Logical Reasoning": 91.44, |
|
|
| "Text": 63.37 |
| } |
| ] |
| } |
|
|
