AI Paper Atlas

Research map / Benchmarks / ImgEdit-Bench

ImgEdit-Bench leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on ImgEdit-Bench. Best overall: 4.31 (TUNA, CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

ImgEdit-Bench · overall

12 papers, each with its best reported number for its own method; higher is better.

#overall ↑MethodPaperTopic
14.31TUNATUNA: Taming Unified Visual Representations for Native Unified Multimodal Models
CVPR 2026 · Table 4
Human and embodied modeling
24.2Qwen-Image-Edit + MotionNFT
Qwen-Image-Edit
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
CVPR 2026 · Table 2
Video generation
34.01SPAR-3BSPAR: Semantic-Pixel Self-Alignment and Adaptive Routing for Unified Multimodal Models
ECCV 2026 · Table 4
Multimodal LLMs
43.88FUSEFUSE: Fine-Grained and Semantic-Aware Learning for Unified Image Understanding and Generation
AAAI 2026 · Table 3
Multimodal LLMs
53.77LightFusionLightFusion: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation
ECCV 2026 · text/Table
Multimodal LLMs
63.69OmniGen2
Qwen2.5-VL-3B + DiT
OmniGen2: Towards Instruction-Aligned Multimodal Generation
CVPR 2026 · Table 2
Multimodal LLMs
73.54HBridgeHBridge: H-Shape Bridging of Heterogeneous Experts for Unified Multimodal Understanding and Generation
CVPR 2026 · Table 3
Cross-modal learning
83.44Uni-X (extra data)
Qwen2.5-3B
Uni-X: Mitigating Modality Conflict with a Two-End-Separated Architecture for Unified Multimodal Models
ICLR 2026 · Table 4
Human and embodied modeling
93.43OneCAT-3B
Qwen2.5-3B-instruct
OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation
CVPR 2026 · Table ImgEdit
Human and embodied modeling
103.42EditVerseEditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
ICLR 2026 · Appendix table
Video generation
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.