🥇 UniREditBench Leaderboard
📚 UniREditBench is a unified benchmark for reasoning-base image editing that integrates diverse prompt themes with a comprehensive suite of dual-reference evaluation pipeline.
🔧 You can use the official GitHub repo to evaluate your model on UniREditBench.
📝 To add your own model to the leaderboard, please send an Email to Feng Han and Yibin Wang, then we will help with the evaluation and updating the leaderboard.
2025-11 | ✓ | 78.87 | 84.43 | 74.06 | 85.13 | 72.08 | 74.31 | 71.95 | 83.05 | 71.17 | 72.45 | 76.52 | 84.93 | 86.93 | 61.25 | 73.76 | 87.48 | 70.65 | 93.90 | 97.73 | 74.55 | 82.27 |
📙 Citation
If you use UniREditBench in your research, please cite our work: