List your company

Aesthetic Classification on A3-Dataset

87Image FidelityA3-Align
32.19246.42160.6574.879Mar 25, 2026

Evaluation results

MethodLinks
A3-AlignModel Category=Ours, Thinking Mode=false2026.038782.491.782.4888799.192.6
Gemini 2.5 pro-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0377.865.775.980.65068.589.847.2
Gemini 2.5 proModel Category=Closed-source Models, Thinking Mode=false2026.037573.280.680.650.9758746.3
Gemini 2.5 flash-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0369.25769.473.644.356.180.216
Gemini 2.5 flashModel Category=Closed-source Models, Thinking Mode=false2026.0366.753.170.863.347.356.86814
Gemma-3-27B-itModel Category=Open-source Models, Thinking Mode=false2026.0364.857.472.263.958.369.466.733.3
Qwen3-VL-32B-InstructModel Category=Open-source Models, Thinking Mode=false2026.0360.258.351.869.457.448.28825.9
Claude Haiku 4.5-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0356.56262.673.248.254.688.939.8
Qwen3-VL-32B-thinkingModel Category=Open-source Models - Thinking, Thinking Mode=true2026.0355.648.148.167.65048.18722.2
Claude Haiku 4.5Model Category=Closed-source Models, Thinking Mode=false2026.0355.663.958.977.850.953.784.340.7
Claude Sonnet 4.5-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0355.654.668.975.757.462.681.547.2
Llama-4-Scout-109BModel Category=Open-source Models, Thinking Mode=false2026.0354.654.649.154.647.251.969.441.7
Qwen3-VL-235B-A22B-thinkingModel Category=Open-source Models - Thinking, Thinking Mode=true2026.0354.660.26374.16363.976.912
Claude Sonnet 4.5Model Category=Closed-source Models, Thinking Mode=false2026.0354.652.860.873.261.156.182.447.2
Mistral medium 3.1Model Category=Closed-source Models, Thinking Mode=false2026.0353.757.45059.344.453.78736.1
Doubao seed 1.6-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0353.745.457.969.450.960.28836.1
ChatGPT o4 mini highModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0353.77564.882.257.460.887.978
Claude Opus 4.1Model Category=Closed-source Models, Thinking Mode=false2026.0352.856.575.776.870.46383.335.2
Llama-4-Maverick-400BModel Category=Open-source Models, Thinking Mode=false2026.0351.849.150.96347.249.167.625.9
ChatGPT 4oModel Category=Closed-source Models, Thinking Mode=false2026.0351.852.947.26248.153.777.822.2
Claude Opus 4.1-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0351.859.363.681.57563.679.643.5
Qwen2.5-VL-72B-InstructModel Category=Open-source Models, Thinking Mode=false2026.0350.93848.167.646.351.882.434.3
Doubao 1.5 vision proModel Category=Closed-source Models, Thinking Mode=false2026.0350.963.949.573.260.261.180.64.6
ChatGPT 5Model Category=Closed-source Models, Thinking Mode=false2026.0350.964.85069.45053.791.725
ChatGPT 5 highModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0350.96250.969.45057.691.528.8
Glm-4.5v-106BModel Category=Open-source Models, Thinking Mode=false2026.035050.948.661.552.350.96510.7
ChatGPT o3Model Category=Closed-source Models - Thinking, Thinking Mode=true2026.03507557.47555.661.788.844.9
Grok 4Model Category=Closed-source Models, Thinking Mode=false2026.0349.161.160.272.242.652.876.845.4
Doubao seed 1.6 visionModel Category=Closed-source Models, Thinking Mode=false2026.0348.152.846.754.647.247.270.441.7
Doubao 1.5 vision pro-thinkingModel Category=Closed-source Models - Thinking, Thinking Mode=true2026.0347.248.246.767.644.447.283.310.2
Qwen3-VL-8B-InstructModel Category=Open-source Models, Thinking Mode=false2026.0345.449.146.349.144.447.261.115.7
ChatGPT 4.1Model Category=Closed-source Models, Thinking Mode=false2026.0334.329.633.36241.748.169.427.8