Image Generation Evaluation on ITS
98.2A@1DDiT
Evaluation Results
| Method | Links | |
|---|---|---|
| DDiTJudge=QwenVL trained2025.06 | 98.2 | |
| GPT-4o+DALL-EJudge=InternVL trained2025.06 | 97.8 | |
| DDiTJudge=InternVL trained2025.06 | 97.6 | |
| SEIRJudge=QwenVL trained2025.06 | 97.4 | |
| Gemini+FluxJudge=QwenVL trained2025.06 | 97.3 | |
| SEIRJudge=InternVL trained2025.06 | 96.4 | |
| VARGPTJudge=QwenVL trained2025.06 | 96.2 | |
| GPT-4o+DALL-EJudge=QwenVL trained2025.06 | 95.9 | |
| DDiTJudge=QwenVL2025.06 | 95.8 | |
| DDiTJudge=InternVL2025.06 | 95.1 | |
| Emu3Judge=QwenVL trained2025.06 | 95 | |
| VILA-UJudge=InternVL trained2025.06 | 94.8 | |
| Gemini+FluxJudge=InternVL trained2025.06 | 94.6 | |
| VARGPTJudge=InternVL trained2025.06 | 94.4 | |
| Show-o-TurboJudge=QwenVL trained2025.06 | 94.3 | |
| GPT-4o+DALL-EJudge=GPT-4o2025.06 | 93.8 | |
| AnoleJudge=QwenVL trained2025.06 | 93.6 | |
| Gemini+FluxJudge=QwenVL2025.06 | 93.6 | |
| Show-oJudge=QwenVL trained2025.06 | 93.6 | |
| VARGPTJudge=GPT-4o2025.06 | 93.4 | |
| AnoleJudge=InternVL trained2025.06 | 93.3 | |
| GPT-4o+DALL-EJudge=InternVL2025.06 | 93.3 | |
| LiquidJudge=QwenVL trained2025.06 | 92.9 | |
| Show-o-TurboJudge=InternVL trained2025.06 | 92.8 | |
| VILA-UJudge=QwenVL trained2025.06 | 92.6 | |
| Emu3Judge=InternVL trained2025.06 | 92.5 | |
| Gemini+FluxJudge=GPT-4o2025.06 | 92.4 | |
| Janus-ProJudge=QwenVL trained2025.06 | 92.4 | |
| VARGPTJudge=InternVL2025.06 | 92.2 | |
| LiquidJudge=InternVL trained2025.06 | 91.4 | |
| Gemini+FluxJudge=InternVL2025.06 | 91.1 | |
| Janus-ProJudge=InternVL trained2025.06 | 89.7 | |
| Show-oJudge=InternVL trained2025.06 | 88.9 | |
| DDiTJudge=GPT-4o2025.06 | 88.5 | |
| VARGPTJudge=QwenVL2025.06 | 88.4 | |
| SEIRJudge=InternVL2025.06 | 88.1 | |
| VILA-UJudge=InternVL2025.06 | 87.9 | |
| SEIRJudge=GPT-4o2025.06 | 87.6 | |
| GPT-4o+DALL-EJudge=QwenVL2025.06 | 86.6 | |
| AnoleJudge=InternVL2025.06 | 85.1 | |
| SEIRJudge=QwenVL2025.06 | 84.8 | |
| Emu3Judge=InternVL2025.06 | 84.6 | |
| VILA-UJudge=QwenVL2025.06 | 84.2 | |
| Show-o-TurboJudge=InternVL2025.06 | 83.8 | |
| Show-oJudge=QwenVL2025.06 | 82.9 | |
| AnoleJudge=GPT-4o2025.06 | 82.3 | |
| Emu3Judge=QwenVL2025.06 | 81.9 | |
| Show-o-TurboJudge=GPT-4o2025.06 | 81.6 | |
| VILA-UJudge=GPT-4o2025.06 | 81.5 | |
| Emu3Judge=GPT-4o2025.06 | 81.1 | |
| Show-oJudge=InternVL2025.06 | 80.8 | |
| Show-oJudge=GPT-4o2025.06 | 80.1 | |
| Janus-ProJudge=InternVL2025.06 | 78.3 | |
| AnoleJudge=QwenVL2025.06 | 77.9 | |
| Janus-ProJudge=QwenVL2025.06 | 77.7 | |
| Janus-ProJudge=GPT-4o2025.06 | 77.5 | |
| LiquidJudge=InternVL2025.06 | 77.5 | |
| Show-o-TurboJudge=QwenVL2025.06 | 77.5 | |
| LiquidJudge=GPT-4o2025.06 | 77 | |
| LiquidJudge=QwenVL2025.06 | 71.6 |