Image Quality Assessment on GIER 50 user study samples
5.84Rank (B)GPT-4.1
Evaluation results
| Method | Links | |
|---|---|---|
| GPT-4.1Category=Tool-Calling Methods2026.06 | 5.84 | |
| Gemini-2.5-ProCategory=Tool-Calling Methods2026.06 | 5.79 | |
| JarvisArtCategory=Tool-Calling Methods2026.06 | 5.36 | |
| Qwen2.5-VL-7BCategory=Tool-Calling Methods2026.06 | 4.55 | |
| GPT-Image-1Category=Generative Methods2026.06 | 4.15 | |
| Qwen-Image-EditCategory=Generative Methods2026.06 | 3.74 | |
| IEACategory=Tool-Calling Methods2026.06 | 3.69 | |
| ReferenceType=Human Expert2026.06 | 2.87 |