Spaces:
Running
Running
| [ | |
| { | |
| "Model": "CLIP-v1", | |
| "Alignment": 38.1, | |
| "Safety": 12.7, | |
| "Artifact": 34.4, | |
| "Bias": { | |
| "ACC": 57.4, | |
| "NDS": 76.3, | |
| "GES": 86.9 | |
| } | |
| }, | |
| { | |
| "Model": "BLIP-v2", | |
| "Alignment": 17.3, | |
| "Safety": 44.0, | |
| "Artifact": 7.5, | |
| "Bias": { | |
| "ACC": 68.7, | |
| "NDS": 83.7, | |
| "GES": 91.3 | |
| } | |
| }, | |
| { | |
| "Model": "PickScore-v1", | |
| "Alignment": 58.8, | |
| "Safety": 37.2, | |
| "Artifact": 83.8, | |
| "Bias": { | |
| "ACC": 31.0, | |
| "NDS": 66.5, | |
| "GES": 81.1 | |
| } | |
| }, | |
| { | |
| "Model": "HPS-v2.1", | |
| "Alignment": 47.3, | |
| "Safety": 18.8, | |
| "Artifact": 67.3, | |
| "Bias": { | |
| "ACC": 55.0, | |
| "NDS": 77.9, | |
| "GES": 87.6 | |
| } | |
| }, | |
| { | |
| "Model": "ImageReward", | |
| "Alignment": 50.9, | |
| "Safety": 24.9, | |
| "Artifact": 63.5, | |
| "Bias": { | |
| "ACC": 40.9, | |
| "NDS": 73.7, | |
| "GES": 85.3 | |
| } | |
| }, | |
| { | |
| "Model": "Aesthetics", | |
| "Alignment": 32.4, | |
| "Safety": 27.0, | |
| "Artifact": 69.6, | |
| "Bias": { | |
| "ACC": 61.4, | |
| "NDS": 85.7, | |
| "GES": 92.1 | |
| } | |
| }, | |
| { | |
| "Model": "LLaVA-1.5-7b", | |
| "Alignment": 22.0, | |
| "Safety": 24.8, | |
| "Artifact": 12.4, | |
| "Bias": { | |
| "ACC": 83.7, | |
| "NDS": 70.4, | |
| "GES": 88.7 | |
| } | |
| }, | |
| { | |
| "Model": "LLaVA-1.5-13b", | |
| "Alignment": 10.3, | |
| "Safety": 30.7, | |
| "Artifact": 23.3, | |
| "Bias": { | |
| "ACC": 69.7, | |
| "NDS": 74.3, | |
| "GES": 88.6 | |
| } | |
| }, | |
| { | |
| "Model": "LLaVA-1.6-mistral-7b", | |
| "Alignment": 31.3, | |
| "Safety": 15.2, | |
| "Artifact": 45.8, | |
| "Bias": { | |
| "ACC": 69.9, | |
| "NDS": 64.3, | |
| "GES": 85.4 | |
| } | |
| }, | |
| { | |
| "Model": "LLaVA-1.6-vicuna-13b", | |
| "Alignment": 29.1, | |
| "Safety": 27.9, | |
| "Artifact": 36.8, | |
| "Bias": { | |
| "ACC": 56.3, | |
| "NDS": 64.0, | |
| "GES": 82.7 | |
| } | |
| }, | |
| { | |
| "Model": "Instructblip-7b", | |
| "Alignment": 17.1, | |
| "Safety": 26.4, | |
| "Artifact": 25.2, | |
| "Bias": { | |
| "ACC": 53.1, | |
| "NDS": 80.8, | |
| "GES": 91.2 | |
| } | |
| }, | |
| { | |
| "Model": "MiniGPT4-v2", | |
| "Alignment": 32.8, | |
| "Safety": 25.7, | |
| "Artifact": 36.7, | |
| "Bias": { | |
| "ACC": 32.6, | |
| "NDS": 67.0, | |
| "GES": 83.3 | |
| } | |
| }, | |
| { | |
| "Model": "Prometheus-Vision-7b", | |
| "Alignment": 18.8, | |
| "Safety": 7.1, | |
| "Artifact": 23.4, | |
| "Bias": { | |
| "ACC": 49.5, | |
| "NDS": 43.4, | |
| "GES": 74.4 | |
| } | |
| }, | |
| { | |
| "Model": "Prometheus-Vision-13b", | |
| "Alignment": 11.8, | |
| "Safety": 3.6, | |
| "Artifact": 8.7, | |
| "Bias": { | |
| "ACC": 66.3, | |
| "NDS": 46.3, | |
| "GES": 76.8 | |
| } | |
| }, | |
| { | |
| "Model": "Qwen-VL-Chat", | |
| "Alignment": 52.1, | |
| "Safety": 26.8, | |
| "Artifact": 23.6, | |
| "Bias": { | |
| "ACC": 71.9, | |
| "NDS": 62.8, | |
| "GES": 86.2 | |
| } | |
| }, | |
| { | |
| "Model": "Internvl-chat-v1-5", | |
| "Alignment": 55.3, | |
| "Safety": 6.3, | |
| "Artifact": 66.3, | |
| "Bias": { | |
| "ACC": 25.4, | |
| "NDS": 69.6, | |
| "GES": 84.3 | |
| } | |
| }, | |
| { | |
| "Model": "Idefics2-8b", | |
| "Alignment": 32.6, | |
| "Safety": 13.6, | |
| "Artifact": 46.1, | |
| "Bias": { | |
| "ACC": 42.1, | |
| "NDS": 58.7, | |
| "GES": 79.4 | |
| } | |
| }, | |
| { | |
| "Model": "GPT-4-vision", | |
| "Alignment": 66.1, | |
| "Safety": 26.5, | |
| "Artifact": 90.4, | |
| "Bias": { | |
| "ACC": 79.0, | |
| "NDS": 80.4, | |
| "GES": 93.2 | |
| } | |
| }, | |
| { | |
| "Model": "GPT-4o", | |
| "Alignment": 61.5, | |
| "Safety": 35.3, | |
| "Artifact": 97.6, | |
| "Bias": { | |
| "ACC": 65.8, | |
| "NDS": 82.5, | |
| "GES": 92.8 | |
| } | |
| }, | |
| { | |
| "Model": "Gemini Ultra", | |
| "Alignment": 67.2, | |
| "Safety": 13.1, | |
| "Artifact": 55.7, | |
| "Bias": { | |
| "ACC": 55.6, | |
| "NDS": 75.3, | |
| "GES": 88.6 | |
| } | |
| }, | |
| { | |
| "Model": "Claude 3 Opus", | |
| "Alignment": 57.1, | |
| "Safety": 13.4, | |
| "Artifact": 11.9, | |
| "Bias": { | |
| "ACC": 57.7, | |
| "NDS": 65.6, | |
| "GES": 85.0 | |
| } | |
| } | |
| ] |