Image@1.0 Leaderboard
# Leaderboard for UEval image generation evaluation.| Rank | Model Name | Avg | Art | Diagram | Exercise | Life | Paper | Space | Tech | Textbook | Date |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 2.5 Flash | 56.4% | 51.2% | 55.7% | 36.6% | 55.2% | 59.7% | 82.6% | 48.9% | 61.5% | 1/14/2025 |
| 2 | GPT 5 Instant | 52.8% | 58.9% | 44.5% | 54.2% | 60.7% | 27.4% | 74.9% | 34.3% | 67.4% | 1/14/2025 |
| 3 | GPT 5 Thinking | 49.1% | 40.8% | 51.2% | 41.2% | 41.8% | 43.3% | 82.3% | 26.2% | 65.9% | 1/14/2025 |
| 4 | Gemini 2.0 Flash | 36.9% | 55.5% | 21.9% | 35.7% | 44.9% | 17.3% | 59.9% | 30.1% | 29.9% | 1/14/2025 |
| 5 | Emu 3.5 | 33.6% | 39.0% | 13.3% | 37.6% | 53.6% | 12.3% | 64.6% | 16.2% | 32.5% | 1/14/2025 |
| 6 | MMaDA | 15.9% | 18.9% | 9.2% | 22.1% | 21.5% | 15.6% | 5.0% | 17.3% | 17.7% | 1/14/2025 |
| 7 | Bagel | 13.6% | 19.8% | 2.8% | 15.2% | 19.1% | 4.8% | 27.6% | 5.0% | 14.5% | 1/14/2025 |
| 8 | Show o2 | 8.3% | 5.8% | 9.3% | 4.0% | 4.2% | 4.6% | 22.7% | 4.6% | 10.9% | 1/14/2025 |
| 9 | Janus Pro | 6.5% | 8.9% | 0.8% | 4.1% | 5.9% | 3.3% | 13.5% | 4.4% | 10.8% | 1/14/2025 |
Submit your results by opening an issue in our GitHub.