Image Generation Evaluation on ICC
97.7A@1GPT-4o+DALL-E
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o+DALL-EJudge=InternVL trained2025.06 | 97.7 | |
| GPT-4o+DALL-EJudge=QwenVL trained2025.06 | 97.4 | |
| SEIRJudge=InternVL trained2025.06 | 97.3 | |
| Gemini+FluxJudge=InternVL trained2025.06 | 97 | |
| Gemini+FluxJudge=QwenVL trained2025.06 | 96.9 | |
| SEIRJudge=QwenVL trained2025.06 | 96.7 | |
| LiquidJudge=InternVL trained2025.06 | 96.4 | |
| GPT-4o+DALL-EJudge=GPT-4o2025.06 | 96.1 | |
| Emu3Judge=QwenVL trained2025.06 | 96.1 | |
| VARGPTJudge=QwenVL trained2025.06 | 95.9 | |
| GPT-4o+DALL-EJudge=InternVL2025.06 | 95.6 | |
| DDiTJudge=InternVL trained2025.06 | 95.5 | |
| DDiTJudge=QwenVL trained2025.06 | 95.4 | |
| VARGPTJudge=InternVL trained2025.06 | 95.3 | |
| GPT-4o+DALL-EJudge=QwenVL2025.06 | 94.9 | |
| LiquidJudge=QwenVL trained2025.06 | 94.8 | |
| Show-oJudge=InternVL trained2025.06 | 94.7 | |
| SEIRJudge=InternVL2025.06 | 94.6 | |
| Gemini+FluxJudge=InternVL2025.06 | 94.5 | |
| Emu3Judge=InternVL trained2025.06 | 94.2 | |
| Gemini+FluxJudge=GPT-4o2025.06 | 94.1 | |
| AnoleJudge=QwenVL trained2025.06 | 93.7 | |
| SEIRJudge=GPT-4o2025.06 | 93.6 | |
| Show-o-TurboJudge=QwenVL trained2025.06 | 93.6 | |
| Show-oJudge=QwenVL trained2025.06 | 93.5 | |
| Janus-ProJudge=QwenVL trained2025.06 | 93.3 | |
| Janus-ProJudge=InternVL trained2025.06 | 93.2 | |
| AnoleJudge=InternVL trained2025.06 | 93 | |
| Show-o-TurboJudge=InternVL trained2025.06 | 92.6 | |
| VARGPTJudge=QwenVL2025.06 | 92.6 | |
| VILA-UJudge=InternVL trained2025.06 | 92.6 | |
| SEIRJudge=QwenVL2025.06 | 92.5 | |
| VARGPTJudge=GPT-4o2025.06 | 92.4 | |
| VARGPTJudge=InternVL2025.06 | 92.4 | |
| VILA-UJudge=QwenVL trained2025.06 | 91.5 | |
| Gemini+FluxJudge=QwenVL2025.06 | 90.5 | |
| DDiTJudge=InternVL2025.06 | 90.1 | |
| Emu3Judge=InternVL2025.06 | 89.9 | |
| Show-o-TurboJudge=InternVL2025.06 | 89.5 | |
| LiquidJudge=InternVL2025.06 | 89 | |
| LiquidJudge=QwenVL2025.06 | 88.1 | |
| LiquidJudge=GPT-4o2025.06 | 88 | |
| Show-oJudge=InternVL2025.06 | 87.4 | |
| Emu3Judge=QwenVL2025.06 | 87.1 | |
| VILA-UJudge=InternVL2025.06 | 86.8 | |
| Emu3Judge=GPT-4o2025.06 | 86.7 | |
| Show-o-TurboJudge=GPT-4o2025.06 | 86.1 | |
| AnoleJudge=InternVL2025.06 | 85.9 | |
| Show-oJudge=QwenVL2025.06 | 85.2 | |
| DDiTJudge=QwenVL2025.06 | 85 | |
| AnoleJudge=GPT-4o2025.06 | 84.8 | |
| Show-o-TurboJudge=QwenVL2025.06 | 84.8 | |
| DDiTJudge=GPT-4o2025.06 | 84.6 | |
| Janus-ProJudge=InternVL2025.06 | 84.6 | |
| Show-oJudge=GPT-4o2025.06 | 84.2 | |
| VILA-UJudge=GPT-4o2025.06 | 83.2 | |
| VILA-UJudge=QwenVL2025.06 | 81.8 | |
| AnoleJudge=QwenVL2025.06 | 81.6 | |
| Janus-ProJudge=GPT-4o2025.06 | 80.6 | |
| Janus-ProJudge=QwenVL2025.06 | 74.3 |