| PlanViz | Planning-oriented editing evaluation | arXiv | 2026 |
| LocateEdit | Localization instruction editing benchmark | arXiv | 2026 |
| VIBE | Visual instruction-based editing evaluation | arXiv | 2026 |
| Interaction Edit | MLLM-based object interaction editing benchmark | arXiv | 2026 |
| World-Shape | 360° panoramic editing consistency evaluation | arXiv | 2026 |
| VDE Bench | Visual document editing evaluation | arXiv | 2026 |
| HYPE-EDIT | Reliability and robustness editing evaluation | arXiv | 2026 |
| EDIR | Fine-grained composed image editing evaluation | arXiv | 2026 |
| UniPic-3.0 | Multi-image composition editing benchmark | arXiv | 2026 |
| UM-Text | Visual text and OCR editing benchmark | arXiv | 2026 |
| I2E | Interactive image-to-edit benchmark | arXiv | 2026 |
| MotionEdit | Motion-centered editing evaluation | arXiv | 2026 |
| KRIS-Bench | Next-level intelligent image editing assessment | NeurIPS | 2025 |
| CompBench | Complex instruction editing evaluation | arXiv | 2025 |
| ComplexBench | Multi-step chain robustness editing benchmark | arXiv | 2025 |
| Complex-Edit | Complexity-aware editing evaluation | arXiv | 2025 |
| GEdit-Bench | Realistic use-case editing evaluation | arXiv | 2025 |
| GPT-ImgEdit | Closed-model editing quality evaluation | arXiv | 2025 |
| IE-Bench | Human-aligned MOS editing evaluation | arXiv | 2025 |
| ImgEdit-Bench | Unified instruction-based editing evaluation | arXiv | 2025 |
| MCIE | MLLM-driven complex instruction editing benchmark | arXiv | 2025 |
| MMKE-Bench | Knowledge entity editing evaluation | arXiv | 2025 |
| PICABench | Physical realistic plausibility editing evaluation | arXiv | 2025 |
| PPTArena | Agentic PowerPoint editing evaluation | arXiv | 2025 |
| RefEdit | Reference-guided editing evaluation | arXiv | 2025 |
| SpotEdit | Visually-guided editing benchmark | arXiv | 2025 |
| UniREditBench | Reasoning-based editing evaluation | arXiv | 2025 |
| WEAVE | Interleaved in-context editing evaluation | arXiv | 2025 |
| WiseEdit | Cognition and creativity editing evaluation | arXiv | 2025 |
| EditScore | Reward model fidelity editing metric | arXiv | 2025 |
| EdiVal-Agent | Agentic multi-turn editing evaluation | arXiv | 2025 |
| AnyEdit | Unified high-quality image editing evaluation | CVPR | 2024 |
| I2EBench | 16-dimensional comprehensive editing evaluation | arXiv | 2024 |
| GIE-Bench | Grounded image editing evaluation | arXiv | 2024 |
| FSMI-Edit | Localized mask-guided editing evaluation | arXiv | 2024 |
| EditVal | Automated edit success evaluation | arXiv | 2023 |
| Emu Edit Bench | 7-task unified editing precision benchmark | arXiv | 2023 |
| PIE-Bench | Edit fidelity inversion evaluation | arXiv | 2023 |
| MagicBrush | Human-annotated editing evaluation | NeurIPS | 2023 |
| EditBench | Object rendering and inpainting benchmark | arXiv | 2022 |