| { |
| "leaderboard": [ |
| { |
| "model": "GLM-Image", |
| "link": "https://z.ai/blog/glm-image", |
| "hf": "https://huggingface.co/zai-org/GLM-Image", |
| "open_source": true, |
| "release_date": "2026-1", |
| "Overall": 70.57, |
| "Style": 85.8, |
| "World Knowledge": 90.51, |
| "Attribute-Overall": 71.15, |
| "Quantity": 77.08, |
| "Expression": 63.46, |
| "Material": 74.53, |
| "Size": 73.61, |
| "Shape": 51.88, |
| "Color": 90.83, |
| "Action-Overall": 65.11, |
| "Hand": 66.03, |
| "Full body": 71.74, |
| "Animal": 66.91, |
| "Non Contact": 56.63, |
| "Contact": 57.14, |
| "State": 71.7, |
| "Relationship-Overall": 69.29, |
| "Composition": 70.95, |
| "Similarity": 68.33, |
| "Inclusion": 69.57, |
| "Comparison": 66.41, |
| "Compound-Overall": 57.86, |
| "Imagination": 62.5, |
| "Feature matching": 53.12, |
| "Grammar-Overall": 63.37, |
| "Pronoun Reference": 75.0, |
| "Consistency": 62.5, |
| "Negation": 51.92, |
| "Layout-Overall": 74.07, |
| "2D": 79.04, |
| "3D": 68.94, |
| "Logical Reasoning": 42.89, |
| "Text": 85.63 |
| }, |
| { |
| "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 |
| } |
| ] |
| } |
