OpenCodePapers

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

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
SenseNova-U1.5: Towards Native Unified Visual Intelligence✓ Link98.9SenseNova-U1.5-8B-MoT2026-09-10
GenClaw: Code-Driven Agentic Image Generation✓ Link98.8GenClaw2026-05-28
Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation✓ Link98.5Boogu-Image-0.1-Turbo-Thinking2026-07-14
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer✓ Link98.0HiDream-O1-Image-Pro2026-05-11
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer✓ Link97.8HiDream-O1-Image2026-05-11
Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering97.2Qwen-Image (IDSpect) (extra data)2026-09-29
Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation✓ Link96.3JoyAI-Image2026-05-05
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture✓ Link96.2SenseNova-U1-8B-MoT2026-05-12
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture✓ Link95.5SenseNova-U1 (8BA3B)2026-05-12
Qwen-Image Technical Report✓ Link94.6Qwen-Image2025-08-04
Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers✓ Link94.6PPCL (Qwen-Image, 14B)2025-11-20
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer✓ Link93.6Z-Image2025-11-27
LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes✓ Link91.3LLaDA-Image2026-09-03
LongCat-Next: Lexicalizing Modalities as Discrete Tokens✓ Link89.08LongCat-Next (A3B, 68.5B)2026-03-29
InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing✓ Link86.0InternVL-U (4B)2026-03-10
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing✓ Link82.3Mage-Flow2026-07-21
Check out how to contribute new results. Then edit this file on GitLab or GitHub.