🥇 UniGenBench Leaderboard
📚 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.
📝 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.
2025-04 | ✗ | 92.77 | 98.57 | 98.87 | 84.97 | 89.24 | 93.59 | 90.00 | 94.70 | 94.20 | 91.61 | 92.50 | 100.00 | 90.79 | 89.74 | 92.22 | 87.12 | 90.43 | 89.82 | 93.75 | 94.97 | 96.23 | 95.00 | 94.89 | 92.19 | 93.55 | 95.64 | 91.40 | 91.76 | 92.91 | 91.67 | 90.57 | 91.35 | 91.04 | 91.67 |