Text-to-Image Preference Prediction on Pick-a-Pic
73.4AccuracyDyCoRM
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DyCoRMModel Category=Reward Models2026.05 | 73.4 | 71.7 | |
| HPSV3Model Category=Reward Models2026.05 | 72.8 | 71.2 | |
| PICKSCOREModel Category=Reward Models2026.05 | 70.5 | 67.2 | |
| HPSModel Category=Reward Models2026.05 | 66.7 | 64.2 | |
| HPSV2Model Category=Reward Models2026.05 | 63.8 | 62.1 | |
| MPSModel Category=Reward Models2026.05 | 63.1 | 61.2 | |
| IMAGEREWARDModel Category=Reward Models2026.05 | 61.1 | 58.2 | |
| GPT-5 (25-08-07)Model Category=General LMMs2026.05 | 60.8 | 57.8 | |
| CLIPSCOREModel Category=Reward Models2026.05 | 60.8 | 57.1 | |
| GEMINI-3.0-PROModel Category=General LMMs2026.05 | 59.2 | 56.2 | |
| GPT-4O (24-11-20)Model Category=General LMMs2026.05 | 58.1 | 55.1 | |
| AESTHETIC SCORE PREDICTORModel Category=Reward Models2026.05 | 56.8 | 54.1 | |
| QWEN3VL-8BModel Category=General LMMs2026.05 | 55 | 52 | |
| INTERNVL3.5-14BModel Category=General LMMs2026.05 | 54.8 | 51.8 | |
| INTERNVL3.5-8BModel Category=General LMMs2026.05 | 54.2 | 51.2 | |
| LLAVA-ONEVISION-1.5-7BModel Category=General LMMs2026.05 | 53.8 | 50.8 | |
| QWEN3VL-4BModel Category=General LMMs2026.05 | 52.8 | 49.8 |