OpenCodePapers

text-to-image-generation-on-longtext-bench

Image GenerationText-to-Image Generation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
GenClaw: Code-Driven Agentic Image Generation✓ Link98.9GenClaw2026-05-28
SenseNova-U1.5: Towards Native Unified Visual Intelligence✓ Link98.8SenseNova-U1.5-8B-MoT2026-09-10
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer✓ Link98.2HiDream-O1-Image-Pro2026-05-11
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer✓ Link97.9HiDream-O1-Image2026-05-11
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture✓ Link97.9SenseNova-U1-8B-MoT2026-05-12
Emu3.5: Native Multimodal Models are World Learners✓ Link97.6Emu3.5 (34B)2025-10-30
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation✓ Link96.3JoyAI-Image2026-05-05
Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation✓ Link95.7Boogu-Image-0.1-Turbo-Thinking2026-07-14
GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation✓ Link95.2GLM-Image2026-01-14
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing✓ Link94.4Mage-Flow2026-07-21
Qwen-Image Technical Report✓ Link94.3Qwen-Image2025-08-04
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models✓ Link93.7Lens2026-05-20
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer✓ Link93.5Z-Image2025-11-27
Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers✓ Link92.9PPCL (Qwen-Image, 14B)2025-11-20
An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models92.52Ours (Z-Image pixel-space) (extra data)2026-08-17
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes✓ Link92.3LLaDA-Image2026-09-03
i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models✓ Link92.2i12026-06-09
X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again✓ Link90.0X-Omni2025-07-29
Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning✓ Link85.7Iris-3B2026-10-07
CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation✓ Link75.5CoCo2026-03-09
Check out how to contribute new results. Then edit this file on GitLab or GitHub.