🥇 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.
2025-11 | ✗ | 94.20 | 99.58 | 97.83 | 87.75 | 96.47 | 95.94 | 89.36 | 90.69 | 97.52 | 96.97 | 91.43 | 95.53 | 89.19 | 86.22 | 89.69 | 90.94 | 89.29 | 89.37 | 89.38 | 94.29 | 94.39 | 91.99 | 98.28 | 92.48 | 94.10 | 94.92 | 92.29 | 93.15 | 99.60 | 90.08 | 90.14 | 93.73 | 93.79 | 93.66 |