🥇 UniGenBench Leaderboard (English Long)
📚 UniGenBench is a unified benchmark for T2I generation that integrates diverse prompt themes with a comprehensive suite of fine-grained evaluation criteria.
🔧 You can use the official GitHub repo to evaluate your model on UniGenBench.
😊 We release all generated images from the T2I models evaluated in our UniGenBench on UniGenBench-Eval-Images. Feel free to use any evaluation model that is convenient and suitable for you to assess and compare the performance of your models.
📝 To add your own model to the leaderboard, please send an Email to Yibin Wang, then we will help with the evaluation and updating the leaderboard.
2025-03 | ✗ | 92.63 | 99.08 | 97.95 | 91.02 | 83.79 | 93.53 | 86.70 | 93.44 | 92.45 | 94.89 | 92.48 | 94.95 | 87.78 | 89.94 | 87.19 | 90.94 | 89.29 | 83.05 | 87.75 | 91.13 | 89.18 | 90.71 | 96.84 | 90.29 | 93.99 | 94.39 | 93.10 | 94.46 | 95.97 | 91.67 | 95.65 | 93.59 | 94.29 | 92.70 |