{ "leaderboard": [ { "model": "FLUX-2-flex", "link": "https://flux2-flex.com/", "hf": "-", "open_source": false, "release_date": "2025-11", "Overall": 87.62, "Style": 98.09, "World Knowledge": 95.99, "Attribute-Overall": 90.76, "Quantity": 87.5, "Expression": 80.26, "Material": 95.28, "Size": 93.06, "Shape": 88.68, "Color": 100.0, "Action-Overall": 89.67, "Hand": 89.74, "Full body": 92.18, "Animal": 88.24, "Non Contact": 87.76, "Contact": 82.63, "State": 95.73, "Relationship-Overall": 91.57, "Composition": 93.58, "Similarity": 86.59, "Inclusion": 94.44, "Comparison": 89.84, "Compound-Overall": 92.09, "Imagination": 94.9, "Feature matching": 89.18, "Grammar-Overall": 85.68, "Pronoun Reference": 94.32, "Consistency": 85.65, "Negation": 76.92, "Layout-Overall": 94.54, "2D": 94.4, "3D": 94.68, "Logical Reasoning": 77.08, "Text": 60.77 }, { "model": "FLUX-2-max", "link": "https://bfl.ai/models/flux-2-max", "hf": "-", "open_source": false, "release_date": "2025-12", "Overall": 88.14, "Style": 99.1, "World Knowledge": 97.28, "Attribute-Overall": 92.26, "Quantity": 90.28, "Expression": 80.26, "Material": 97.64, "Size": 95.14, "Shape": 90.0, "Color": 100.0, "Action-Overall": 90.55, "Hand": 89.1, "Full body": 94.44, "Animal": 90.44, "Non Contact": 89.8, "Contact": 85.71, "State": 92.92, "Relationship-Overall": 94.26, "Composition": 95.95, "Similarity": 88.89, "Inclusion": 98.89, "Comparison": 91.41, "Compound-Overall": 93.65, "Imagination": 95.41, "Feature matching": 91.84, "Grammar-Overall": 87.57, "Pronoun Reference": 94.32, "Consistency": 88.89, "Negation": 79.62, "Layout-Overall": 94.92, "2D": 96.64, "3D": 93.18, "Logical Reasoning": 80.0, "Text": 51.76 }, { "model": "FLUX-2-pro", "link": "https://docs.bfl.ai/flux_2/flux2_text_to_image", "hf": "-", "open_source": false, "release_date": "2025-11", "Overall": 85.4, "Style": 99.2, "World Knowledge": 96.47, "Attribute-Overall": 89.69, "Quantity": 84.72, "Expression": 77.63, "Material": 97.17, "Size": 89.58, "Shape": 88.12, "Color": 100.0, "Action-Overall": 87.5, "Hand": 83.33, "Full body": 90.56, "Animal": 88.97, "Non Contact": 88.27, "Contact": 80.95, "State": 91.51, "Relationship-Overall": 90.69, "Composition": 91.89, "Similarity": 82.22, "Inclusion": 96.67, "Comparison": 91.41, "Compound-Overall": 89.13, "Imagination": 92.35, "Feature matching": 85.83, "Grammar-Overall": 82.84, "Pronoun Reference": 91.29, "Consistency": 84.72, "Negation": 72.69, "Layout-Overall": 93.98, "2D": 93.28, "3D": 94.7, "Logical Reasoning": 75.93, "Text": 48.53 }, { "model": "FLUX.2-klein-4b", "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-4B", "open_source": true, "release_date": "2026-1", "Overall": 71.8, "Style": 97.1, "World Knowledge": 87.34, "Attribute-Overall": 83.87, "Quantity": 64.58, "Expression": 83.33, "Material": 91.98, "Size": 83.33, "Shape": 79.38, "Color": 100.0, "Action-Overall": 78.42, "Hand": 73.08, "Full body": 80.43, "Animal": 81.62, "Non Contact": 76.02, "Contact": 73.81, "State": 84.43, "Relationship-Overall": 80.84, "Composition": 85.81, "Similarity": 65.56, "Inclusion": 91.3, "Comparison": 75.78, "Compound-Overall": 76.03, "Imagination": 82.14, "Feature matching": 69.79, "Grammar-Overall": 74.87, "Pronoun Reference": 84.19, "Consistency": 76.85, "Negation": 63.46, "Layout-Overall": 82.65, "2D": 86.03, "3D": 79.17, "Logical Reasoning": 56.88, "Text": 0.0 }, { "model": "FLUX.2-klein-9b", "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-9B", "open_source": true, "release_date": "2026-1", "Overall": 75.19, "Style": 98.6, "World Knowledge": 93.67, "Attribute-Overall": 86.11, "Quantity": 75.69, "Expression": 81.41, "Material": 93.4, "Size": 86.11, "Shape": 80.0, "Color": 100.0, "Action-Overall": 83.08, "Hand": 76.28, "Full body": 86.41, "Animal": 88.97, "Non Contact": 78.57, "Contact": 80.36, "State": 87.74, "Relationship-Overall": 86.68, "Composition": 90.88, "Similarity": 75.56, "Inclusion": 92.93, "Comparison": 83.59, "Compound-Overall": 82.35, "Imagination": 87.24, "Feature matching": 77.34, "Grammar-Overall": 77.01, "Pronoun Reference": 86.76, "Consistency": 79.17, "Negation": 65.0, "Layout-Overall": 84.89, "2D": 88.6, "3D": 81.06, "Logical Reasoning": 58.03, "Text": 1.44 }, { "model": "FLUX.2-klein-base-4b", "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-4B", "open_source": true, "release_date": "2026-1", "Overall": 69.45, "Style": 96.9, "World Knowledge": 84.34, "Attribute-Overall": 80.77, "Quantity": 70.14, "Expression": 71.15, "Material": 90.09, "Size": 81.25, "Shape": 73.12, "Color": 99.17, "Action-Overall": 71.39, "Hand": 69.87, "Full body": 73.91, "Animal": 73.53, "Non Contact": 66.33, "Contact": 64.88, "State": 78.77, "Relationship-Overall": 79.57, "Composition": 83.45, "Similarity": 70.56, "Inclusion": 83.15, "Comparison": 78.12, "Compound-Overall": 70.49, "Imagination": 77.3, "Feature matching": 63.54, "Grammar-Overall": 75.27, "Pronoun Reference": 81.25, "Consistency": 74.54, "Negation": 69.62, "Layout-Overall": 80.04, "2D": 84.93, "3D": 75.0, "Logical Reasoning": 55.73, "Text": 0.0 }, { "model": "FLUX.2-klein-base-9b", "link": "https://bfl.ai/blog/flux2-klein-towards-interactive-visual-intelligence", "hf": "https://huggingface.co/black-forest-labs/FLUX.2-klein-base-9B", "open_source": true, "release_date": "2026-1", "Overall": 73.81, "Style": 96.7, "World Knowledge": 88.77, "Attribute-Overall": 85.79, "Quantity": 75.0, "Expression": 79.49, "Material": 91.51, "Size": 87.5, "Shape": 81.88, "Color": 100.0, "Action-Overall": 78.99, "Hand": 72.44, "Full body": 82.07, "Animal": 88.97, "Non Contact": 70.92, "Contact": 77.38, "State": 83.49, "Relationship-Overall": 84.9, "Composition": 88.85, "Similarity": 79.44, "Inclusion": 88.04, "Comparison": 78.91, "Compound-Overall": 78.09, "Imagination": 83.67, "Feature matching": 72.4, "Grammar-Overall": 77.94, "Pronoun Reference": 84.56, "Consistency": 81.02, "Negation": 68.46, "Layout-Overall": 83.96, "2D": 88.24, "3D": 79.55, "Logical Reasoning": 60.09, "Text": 2.87 }, { "model": "GPT-4o-1.5", "link": "https://developers.openai.com/api/docs/models/gpt-image-1.5", "hf": "-", "open_source": false, "release_date": "2025-12", "Overall": 95.62, "Style": 99.49, "World Knowledge": 99.68, "Attribute-Overall": 96.55, "Quantity": 92.14, "Expression": 94.23, "Material": 98.08, "Size": 99.31, "Shape": 95.62, "Color": 100.0, "Action-Overall": 95.52, "Hand": 96.15, "Full body": 98.91, "Animal": 96.32, "Non Contact": 93.81, "Contact": 92.86, "State": 95.28, "Relationship-Overall": 97.83, "Composition": 97.97, "Similarity": 97.22, "Inclusion": 100.0, "Comparison": 95.31, "Compound-Overall": 97.13, "Imagination": 99.23, "Feature matching": 94.95, "Grammar-Overall": 91.98, "Pronoun Reference": 95.9, "Consistency": 92.13, "Negation": 87.7, "Layout-Overall": 93.8, "2D": 93.28, "3D": 94.32, "Logical Reasoning": 90.6, "Text": 93.6 }, { "model": "LongCat-Image", "link": "https://arxiv.org/pdf/2512.07584", "hf": "https://huggingface.co/meituan-longcat/LongCat-Image", "open_source": true, "release_date": "2025-12", "Overall": 75.97, "Style": 87.6, "World Knowledge": 92.09, "Attribute-Overall": 79.17, "Quantity": 71.53, "Expression": 77.56, "Material": 88.21, "Size": 77.78, "Shape": 63.75, "Color": 96.67, "Action-Overall": 77.0, "Hand": 76.92, "Full body": 78.8, "Animal": 85.29, "Non Contact": 71.43, "Contact": 67.26, "State": 83.02, "Relationship-Overall": 79.95, "Composition": 80.41, "Similarity": 70.56, "Inclusion": 86.96, "Comparison": 82.03, "Compound-Overall": 66.62, "Imagination": 69.13, "Feature matching": 64.06, "Grammar-Overall": 65.64, "Pronoun Reference": 79.78, "Consistency": 63.43, "Negation": 52.69, "Layout-Overall": 79.29, "2D": 78.31, "3D": 80.3, "Logical Reasoning": 49.31, "Text": 83.05 }, { "model": "Seedream-4-5-251128", "link": "https://seed.bytedance.com/en/seedream4_5", "hf": "-", "open_source": false, "release_date": "2025-11", "Overall": 89.58, "Style": 98.9, "World Knowledge": 96.2, "Attribute-Overall": 92.31, "Quantity": 87.5, "Expression": 87.82, "Material": 99.53, "Size": 89.58, "Shape": 88.12, "Color": 100.0, "Action-Overall": 89.54, "Hand": 85.26, "Full body": 94.02, "Animal": 91.91, "Non Contact": 82.14, "Contact": 86.31, "State": 96.7, "Relationship-Overall": 90.48, "Composition": 88.85, "Similarity": 89.44, "Inclusion": 94.02, "Comparison": 90.62, "Compound-Overall": 88.66, "Imagination": 91.84, "Feature matching": 85.42, "Grammar-Overall": 84.22, "Pronoun Reference": 90.81, "Consistency": 84.26, "Negation": 77.31, "Layout-Overall": 91.04, "2D": 91.54, "3D": 90.53, "Logical Reasoning": 71.1, "Text": 93.39 }, { "model": "Z-Image", "link": "https://arxiv.org/pdf/2511.22699", "hf": "https://huggingface.co/Tongyi-MAI/Z-Image", "open_source": true, "release_date": "2026-1", "Overall": 81.69, "Style": 96.3, "World Knowledge": 94.62, "Attribute-Overall": 86.11, "Quantity": 83.33, "Expression": 74.36, "Material": 95.28, "Size": 85.42, "Shape": 79.38, "Color": 98.33, "Action-Overall": 82.6, "Hand": 81.41, "Full body": 85.33, "Animal": 83.82, "Non Contact": 81.63, "Contact": 76.19, "State": 86.32, "Relationship-Overall": 84.64, "Composition": 88.51, "Similarity": 75.0, "Inclusion": 90.22, "Comparison": 81.25, "Compound-Overall": 79.51, "Imagination": 83.16, "Feature matching": 75.78, "Grammar-Overall": 71.26, "Pronoun Reference": 84.19, "Consistency": 73.61, "Negation": 55.77, "Layout-Overall": 86.57, "2D": 86.76, "3D": 86.36, "Logical Reasoning": 54.82, "Text": 80.46 }, { "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": 74.18, "Style": 91.7, "World Knowledge": 90.98, "Attribute-Overall": 76.92, "Quantity": 75.69, "Expression": 66.03, "Material": 88.21, "Size": 77.78, "Shape": 60.0, "Color": 94.17, "Action-Overall": 74.71, "Hand": 71.15, "Full body": 79.89, "Animal": 80.15, "Non Contact": 69.39, "Contact": 72.02, "State": 76.42, "Relationship-Overall": 72.08, "Composition": 75.0, "Similarity": 61.11, "Inclusion": 77.17, "Comparison": 73.44, "Compound-Overall": 65.85, "Imagination": 69.39, "Feature matching": 62.24, "Grammar-Overall": 65.51, "Pronoun Reference": 79.04, "Consistency": 64.35, "Negation": 52.31, "Layout-Overall": 80.97, "2D": 82.72, "3D": 79.17, "Logical Reasoning": 50.69, "Text": 72.41 }, { "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": 81.44, "Style": 95.7, "World Knowledge": 93.2, "Attribute-Overall": 90.49, "Quantity": 86.81, "Expression": 83.97, "Material": 96.23, "Size": 89.58, "Shape": 86.25, "Color": 100.0, "Action-Overall": 87.55, "Hand": 87.18, "Full body": 91.3, "Animal": 87.5, "Non Contact": 82.14, "Contact": 86.9, "State": 90.09, "Relationship-Overall": 89.34, "Composition": 94.26, "Similarity": 82.78, "Inclusion": 93.48, "Comparison": 81.25, "Compound-Overall": 84.02, "Imagination": 86.73, "Feature matching": 81.25, "Grammar-Overall": 76.2, "Pronoun Reference": 90.81, "Consistency": 82.41, "Negation": 55.77, "Layout-Overall": 90.49, "2D": 91.54, "3D": 89.39, "Logical Reasoning": 68.35, "Text": 39.08 }, { "model": "Nano Banana Pro", "link": "https://nano-banana.pro/", "hf": "-", "open_source": false, "release_date": "2025-11", "Overall": 93.82, "Style": 99.5, "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": 96.7, "Relationship-Overall": 96.07, "Composition": 96.96, "Similarity": 91.67, "Inclusion": 97.83, "Comparison": 97.66, "Compound-Overall": 94.2, "Imagination": 96.68, "Feature matching": 91.67, "Grammar-Overall": 89.04, "Pronoun Reference": 94.49, "Consistency": 90.74, "Negation": 81.92, "Layout-Overall": 94.4, "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": 78.86, "Style": 93.8, "World Knowledge": 93.04, "Attribute-Overall": 83.97, "Quantity": 79.86, "Expression": 75.64, "Material": 91.04, "Size": 84.72, "Shape": 75.62, "Color": 97.5, "Action-Overall": 76.33, "Hand": 72.44, "Full body": 76.09, "Animal": 81.62, "Non Contact": 72.45, "Contact": 75.0, "State": 80.66, "Relationship-Overall": 84.14, "Composition": 83.78, "Similarity": 75.56, "Inclusion": 88.59, "Comparison": 90.62, "Compound-Overall": 78.74, "Imagination": 84.69, "Feature matching": 72.66, "Grammar-Overall": 72.45, "Pronoun Reference": 83.09, "Consistency": 68.52, "Negation": 64.45, "Layout-Overall": 76.12, "2D": 77.94, "3D": 74.24, "Logical Reasoning": 63.99, "Text": 65.98 }, { "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": 72.4, "Style": 92.8, "World Knowledge": 87.66, "Attribute-Overall": 84.29, "Quantity": 72.92, "Expression": 77.56, "Material": 89.15, "Size": 88.19, "Shape": 80.0, "Color": 99.17, "Action-Overall": 76.05, "Hand": 73.08, "Full body": 83.15, "Animal": 85.29, "Non Contact": 75.0, "Contact": 65.48, "State": 75.47, "Relationship-Overall": 82.23, "Composition": 85.81, "Similarity": 75.0, "Inclusion": 88.04, "Comparison": 75.78, "Compound-Overall": 77.96, "Imagination": 82.91, "Feature matching": 72.92, "Grammar-Overall": 75.4, "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": 13.9, "Text": 0.0 }, { "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": 49.4, "World Knowledge": 16.61, "Attribute-Overall": 15.06, "Quantity": 14.58, "Expression": 19.87, "Material": 8.02, "Size": 13.19, "Shape": 5.0, "Color": 37.5, "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": 11.8, "Composition": 16.55, "Similarity": 6.67, "Inclusion": 12.5, "Comparison": 7.03, "Compound-Overall": 4.38, "Imagination": 6.63, "Feature matching": 2.08, "Grammar-Overall": 27.81, "Pronoun Reference": 19.85, "Consistency": 16.2, "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": 80.9, "World Knowledge": 69.46, "Attribute-Overall": 75.64, "Quantity": 62.5, "Expression": 71.79, "Material": 77.83, "Size": 78.47, "Shape": 70.0, "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": 59.69, "Feature matching": 52.34, "Grammar-Overall": 64.84, "Pronoun Reference": 76.1, "Consistency": 70.37, "Negation": 48.46, "Layout-Overall": 69.22, "2D": 73.53, "3D": 64.77, "Logical Reasoning": 39.09, "Text": 0.0 }, { "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": 44.0, "Style": 78.2, "World Knowledge": 52.06, "Attribute-Overall": 55.24, "Quantity": 52.78, "Expression": 33.97, "Material": 58.49, "Size": 61.11, "Shape": 45.0, "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": 59.8, "Similarity": 52.22, "Inclusion": 60.87, "Comparison": 46.88, "Compound-Overall": 32.86, "Imagination": 39.29, "Feature matching": 26.3, "Grammar-Overall": 58.56, "Pronoun Reference": 59.93, "Consistency": 46.3, "Negation": 67.31, "Layout-Overall": 37.31, "2D": 38.97, "3D": 35.61, "Logical Reasoning": 26.14, "Text": 0.0 }, { "model": "OmniGen2", "link": "https://arxiv.org/pdf/2506.18871", "hf": "https://huggingface.co/OmniGen2/OmniGen2", "open_source": true, "release_date": "2025-06", "Overall": 63.2, "Style": 93.0, "World Knowledge": 86.39, "Attribute-Overall": 75.43, "Quantity": 67.36, "Expression": 69.87, "Material": 78.3, "Size": 77.78, "Shape": 68.75, "Color": 93.33, "Action-Overall": 66.54, "Hand": 64.1, "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": 71.3, "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": 56.77, "Style": 94.9, "World Knowledge": 87.34, "Attribute-Overall": 64.32, "Quantity": 62.5, "Expression": 71.79, "Material": 68.4, "Size": 63.89, "Shape": 36.88, "Color": 86.67, "Action-Overall": 57.13, "Hand": 37.18, "Full body": 69.02, "Animal": 76.47, "Non Contact": 57.14, "Contact": 39.29, "State": 63.21, "Relationship-Overall": 61.8, "Composition": 68.58, "Similarity": 57.78, "Inclusion": 60.33, "Comparison": 53.91, "Compound-Overall": 46.78, "Imagination": 58.16, "Feature matching": 35.16, "Grammar-Overall": 60.83, "Pronoun Reference": 66.91, "Consistency": 62.5, "Negation": 53.08, "Layout-Overall": 60.26, "2D": 63.24, "3D": 57.2, "Logical Reasoning": 34.32, "Text": 0.0 }, { "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": 57.5, "Color": 85.83, "Action-Overall": 58.37, "Hand": 48.72, "Full body": 68.48, "Animal": 63.97, "Non Contact": 56.63, "Contact": 43.45, "State": 66.51, "Relationship-Overall": 59.77, "Composition": 60.14, "Similarity": 60.0, "Inclusion": 62.5, "Comparison": 54.69, "Compound-Overall": 41.75, "Imagination": 48.72, "Feature matching": 34.64, "Grammar-Overall": 56.28, "Pronoun Reference": 63.97, "Consistency": 53.7, "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": 92.3, "World Knowledge": 86.71, "Attribute-Overall": 75.21, "Quantity": 64.58, "Expression": 63.46, "Material": 83.49, "Size": 79.86, "Shape": 66.25, "Color": 95.0, "Action-Overall": 65.78, "Hand": 61.54, "Full body": 63.59, "Animal": 75.74, "Non Contact": 65.31, "Contact": 61.9, "State": 67.92, "Relationship-Overall": 75.38, "Composition": 77.7, "Similarity": 67.78, "Inclusion": 82.07, "Comparison": 71.09, "Compound-Overall": 69.85, "Imagination": 79.59, "Feature matching": 59.9, "Grammar-Overall": 69.52, "Pronoun Reference": 73.16, "Consistency": 75.0, "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": 83.3, "World Knowledge": 78.32, "Attribute-Overall": 62.18, "Quantity": 69.44, "Expression": 45.51, "Material": 55.66, "Size": 70.14, "Shape": 55.0, "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": 59.7, "2D": 63.6, "3D": 55.68, "Logical Reasoning": 23.64, "Text": 0.0 }, { "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": 92.2, "World Knowledge": 90.51, "Attribute-Overall": 84.19, "Quantity": 87.5, "Expression": 80.77, "Material": 82.55, "Size": 86.11, "Shape": 75.0, "Color": 97.5, "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": 87.5, "Comparison": 83.59, "Compound-Overall": 70.62, "Imagination": 71.68, "Feature matching": 69.53, "Grammar-Overall": 61.5, "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": 79.6 }, { "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": 92.6, "World Knowledge": 81.17, "Attribute-Overall": 66.56, "Quantity": 57.64, "Expression": 65.38, "Material": 67.92, "Size": 77.08, "Shape": 47.5, "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": 51.8, "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": 0.0 }, { "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": 74.6, "World Knowledge": 50.0, "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": 36.9, "State": 54.72, "Relationship-Overall": 53.55, "Composition": 54.05, "Similarity": 48.33, "Inclusion": 50.0, "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": 27.5, "Text": 0.0 }, { "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": 58.5, "World Knowledge": 18.67, "Attribute-Overall": 19.23, "Quantity": 22.92, "Expression": 10.9, "Material": 21.7, "Size": 24.31, "Shape": 8.12, "Color": 30.0, "Action-Overall": 22.05, "Hand": 4.49, "Full body": 31.52, "Animal": 22.06, "Non Contact": 14.8, "Contact": 19.05, "State": 35.85, "Relationship-Overall": 19.54, "Composition": 23.65, "Similarity": 16.11, "Inclusion": 20.11, "Comparison": 14.06, "Compound-Overall": 10.7, "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": 17.8, "Logical Reasoning": 10.68, "Text": 0.0 }, { "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": 82.4, "World Knowledge": 84.18, "Attribute-Overall": 63.35, "Quantity": 68.75, "Expression": 44.87, "Material": 56.6, "Size": 72.92, "Shape": 53.75, "Color": 94.17, "Action-Overall": 61.69, "Hand": 61.54, "Full body": 66.3, "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": 65.3, "2D": 75.0, "3D": 55.3, "Logical Reasoning": 30.23, "Text": 2.3 }, { "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": 78.1, "World Knowledge": 27.85, "Attribute-Overall": 30.88, "Quantity": 29.17, "Expression": 17.31, "Material": 35.85, "Size": 45.83, "Shape": 14.37, "Color": 45.83, "Action-Overall": 31.37, "Hand": 14.1, "Full body": 38.59, "Animal": 42.65, "Non Contact": 24.49, "Contact": 23.21, "State": 43.4, "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": 48.4, "Pronoun Reference": 48.53, "Consistency": 33.33, "Negation": 60.77, "Layout-Overall": 31.72, "2D": 31.25, "3D": 32.2, "Logical Reasoning": 13.41, "Text": 0.0 }, { "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": 75.6, "World Knowledge": 39.08, "Attribute-Overall": 33.12, "Quantity": 24.31, "Expression": 19.23, "Material": 43.87, "Size": 45.14, "Shape": 18.75, "Color": 47.5, "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": 30.3, "Logical Reasoning": 10.23, "Text": 0.0 }, { "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": 58.8, "Style": 85.2, "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": 57.74, "State": 77.83, "Relationship-Overall": 67.13, "Composition": 71.96, "Similarity": 69.44, "Inclusion": 67.39, "Comparison": 52.34, "Compound-Overall": 55.03, "Imagination": 64.8, "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": 99.0, "World Knowledge": 94.94, "Attribute-Overall": 90.06, "Quantity": 86.81, "Expression": 85.9, "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": 85.2, "Feature matching": 77.86, "Grammar-Overall": 78.48, "Pronoun Reference": 89.71, "Consistency": 75.0, "Negation": 69.62, "Layout-Overall": 90.3, "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": 97.5, "World Knowledge": 96.84, "Attribute-Overall": 86.22, "Quantity": 83.33, "Expression": 77.56, "Material": 92.92, "Size": 93.75, "Shape": 72.5, "Color": 98.33, "Action-Overall": 90.4, "Hand": 89.1, "Full body": 89.67, "Animal": 93.38, "Non Contact": 86.73, "Contact": 90.48, "State": 93.4, "Relationship-Overall": 90.74, "Composition": 91.55, "Similarity": 83.33, "Inclusion": 94.57, "Comparison": 93.75, "Compound-Overall": 85.7, "Imagination": 92.6, "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": 72.6, "Size": 57.64, "Shape": 50.62, "Color": 81.9, "Action-Overall": 60.42, "Hand": 52.63, "Full body": 65.22, "Animal": 75.0, "Non Contact": 51.56, "Contact": 54.37, "State": 65.09, "Relationship-Overall": 65.9, "Composition": 66.89, "Similarity": 51.11, "Inclusion": 74.43, "Comparison": 72.66, "Compound-Overall": 61.0, "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": 59.73, "Style": 89.55, "World Knowledge": 91.36, "Attribute-Overall": 67.87, "Quantity": 71.43, "Expression": 43.59, "Material": 68.14, "Size": 72.86, "Shape": 63.87, "Color": 94.17, "Action-Overall": 64.52, "Hand": 47.44, "Full body": 66.85, "Animal": 70.45, "Non Contact": 67.71, "Contact": 58.33, "State": 73.56, "Relationship-Overall": 72.15, "Composition": 80.56, "Similarity": 63.89, "Inclusion": 76.67, "Comparison": 58.06, "Compound-Overall": 51.33, "Imagination": 59.47, "Feature matching": 43.01, "Grammar-Overall": 62.02, "Pronoun Reference": 72.69, "Consistency": 68.75, "Negation": 45.7, "Layout-Overall": 65.53, "2D": 64.77, "3D": 66.29, "Logical Reasoning": 31.54, "Text": 1.45 }, { "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": 0.0, "Attribute-Overall": 0.11, "Quantity": 0.69, "Expression": 0.0, "Material": 0.0, "Size": 0.0, "Shape": 0.0, "Color": 0.0, "Action-Overall": 0.29, "Hand": 0.0, "Full body": 0.0, "Animal": 0.0, "Non Contact": 0.0, "Contact": 0.0, "State": 1.47, "Relationship-Overall": 0.13, "Composition": 0.34, "Similarity": 0.0, "Inclusion": 0.0, "Comparison": 0.0, "Compound-Overall": 0.0, "Imagination": 0.0, "Feature matching": 0.0, "Grammar-Overall": 5.24, "Pronoun Reference": 0.0, "Consistency": 2.31, "Negation": 13.28, "Layout-Overall": 0.0, "2D": 0.0, "3D": 0.0, "Logical Reasoning": 0.0, "Text": 0.0 }, { "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": 0.0, "Expression": 0.0, "Material": 0.94, "Size": 0.0, "Shape": 0.0, "Color": 0.83, "Action-Overall": 0.0, "Hand": 0.0, "Full body": 0.0, "Animal": 0.0, "Non Contact": 0.0, "Contact": 0.0, "State": 0.0, "Relationship-Overall": 0.26, "Composition": 0.34, "Similarity": 0.57, "Inclusion": 0.0, "Comparison": 0.0, "Compound-Overall": 0.0, "Imagination": 0.0, "Feature matching": 0.0, "Grammar-Overall": 4.3, "Pronoun Reference": 0.37, "Consistency": 1.39, "Negation": 10.94, "Layout-Overall": 0.19, "2D": 0.37, "3D": 0.0, "Logical Reasoning": 0.0, "Text": 0.0 }, { "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": 95.9, "World Knowledge": 93.04, "Attribute-Overall": 78.42, "Quantity": 60.42, "Expression": 68.59, "Material": 91.04, "Size": 90.28, "Shape": 65.0, "Color": 94.17, "Action-Overall": 72.24, "Hand": 69.87, "Full body": 77.17, "Animal": 82.35, "Non Contact": 66.33, "Contact": 61.9, "State": 76.89, "Relationship-Overall": 79.95, "Composition": 81.76, "Similarity": 77.78, "Inclusion": 87.5, "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": 62.5, "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": 95.5, "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": 87.5, "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": 80.1, "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": 80.3, "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": 75.0, "Expression": 67.31, "Material": 74.06, "Size": 74.31, "Shape": 66.25, "Color": 90.83, "Action-Overall": 72.52, "Hand": 69.23, "Full body": 80.0, "Animal": 84.56, "Non Contact": 65.31, "Contact": 61.9, "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": 55.0, "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": 10.5, "World Knowledge": 0.63, "Attribute-Overall": 0.43, "Quantity": 0.0, "Expression": 1.92, "Material": 0.47, "Size": 0.0, "Shape": 0.0, "Color": 0.0, "Action-Overall": 0.95, "Hand": 1.92, "Full body": 0.54, "Animal": 0.74, "Non Contact": 0.0, "Contact": 0.0, "State": 2.36, "Relationship-Overall": 0.13, "Composition": 0.34, "Similarity": 0.0, "Inclusion": 0.0, "Comparison": 0.0, "Compound-Overall": 0.13, "Imagination": 0.26, "Feature matching": 0.0, "Grammar-Overall": 7.75, "Pronoun Reference": 0.74, "Consistency": 1.39, "Negation": 20.38, "Layout-Overall": 0.19, "2D": 0.0, "3D": 0.38, "Logical Reasoning": 0.0, "Text": 0.0 }, { "model": "Nano Banana", "link": "https://ainanobanana.io/", "hf": "-", "open_source": false, "release_date": "2025-08", "Overall": 80.45, "Style": 98.95, "World Knowledge": 96.32, "Attribute-Overall": 88.31, "Quantity": 83.09, "Expression": 82.78, "Material": 91.13, "Size": 95.74, "Shape": 80.13, "Color": 98.33, "Action-Overall": 86.03, "Hand": 83.33, "Full body": 89.14, "Animal": 89.71, "Non Contact": 78.87, "Contact": 82.63, "State": 92.61, "Relationship-Overall": 90.87, "Composition": 90.94, "Similarity": 83.33, "Inclusion": 94.54, "Comparison": 96.09, "Compound-Overall": 86.09, "Imagination": 88.53, "Feature matching": 83.68, "Grammar-Overall": 83.9, "Pronoun Reference": 89.18, "Consistency": 85.17, "Negation": 77.34, "Layout-Overall": 89.75, "2D": 92.19, "3D": 87.21, "Logical Reasoning": 77.26, "Text": 7.06 }, { "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": 92.5, "World Knowledge": 84.97, "Attribute-Overall": 62.93, "Quantity": 63.19, "Expression": 46.15, "Material": 72.17, "Size": 63.89, "Shape": 49.38, "Color": 85.0, "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": 0.0 }, { "model": "Recraft", "link": "https://www.recraft.ai/docs#generate-image", "hf": "-", "open_source": false, "release_date": "2024-12", "Overall": 57.67, "Style": 87.7, "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": 58.4, "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": 1.36, "Style": 8.3, "World Knowledge": 0.0, "Attribute-Overall": 0.0, "Quantity": 0.0, "Expression": 0.0, "Material": 0.0, "Size": 0.0, "Shape": 0.0, "Color": 0.0, "Action-Overall": 0.38, "Hand": 0.0, "Full body": 0.54, "Animal": 0.0, "Non Contact": 0.0, "Contact": 0.0, "State": 1.42, "Relationship-Overall": 0.13, "Composition": 0.34, "Similarity": 0.0, "Inclusion": 0.0, "Comparison": 0.0, "Compound-Overall": 0.0, "Imagination": 0.0, "Feature matching": 0.0, "Grammar-Overall": 4.81, "Pronoun Reference": 0.0, "Consistency": 0.46, "Negation": 13.46, "Layout-Overall": 0.0, "2D": 0.0, "3D": 0.0, "Logical Reasoning": 0.0, "Text": 0.0 }, { "model": "Imagen-4.0-Fast-preview-06-06", "link": "https://deepmind.google/models/imagen/", "hf": "-", "open_source": false, "release_date": "2025-06", "Overall": 71.6, "Style": 93.3, "World Knowledge": 91.3, "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": 75.6, "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": 70.0, "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": 69.9, "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": 97.5, "World Knowledge": 93.99, "Attribute-Overall": 88.03, "Quantity": 84.03, "Expression": 82.69, "Material": 94.34, "Size": 89.58, "Shape": 80.0, "Color": 97.5, "Action-Overall": 86.98, "Hand": 85.26, "Full body": 90.76, "Animal": 89.71, "Non Contact": 85.2, "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": 83.08, "Style": 99.2, "World Knowledge": 97.63, "Attribute-Overall": 91.13, "Quantity": 89.58, "Expression": 80.13, "Material": 93.4, "Size": 94.44, "Shape": 90.62, "Color": 100.0, "Action-Overall": 93.54, "Hand": 94.87, "Full body": 91.85, "Animal": 96.32, "Non Contact": 88.78, "Contact": 93.45, "State": 96.7, "Relationship-Overall": 92.89, "Composition": 91.89, "Similarity": 87.22, "Inclusion": 98.37, "Comparison": 95.31, "Compound-Overall": 89.95, "Imagination": 94.9, "Feature matching": 84.9, "Grammar-Overall": 88.64, "Pronoun Reference": 94.85, "Consistency": 87.96, "Negation": 82.69, "Layout-Overall": 91.04, "2D": 92.65, "3D": 89.39, "Logical Reasoning": 79.55, "Text": 7.18 }, { "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": 97.3, "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 } ] }