| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation | ✓ Link | 78.8 | NextFlow-RL (7B) | 2026-01-05 |
| Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer | ✓ Link | 77.4 | Z-Image-Turbo | 2025-11-27 |
| FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark | ✓ Link | 74.1 | Qwen-Image | 2025-09-11 |
| FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark | ✓ Link | 68.5 | FLUX.1-dev | 2025-09-11 |
| FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark | ✓ Link | 66.1 | SD3-Medium | 2025-09-11 |
| MiniT2I: A Minimalist Baseline for Text-to-Image Generation | ✓ Link | 62.4 | MiniT2I-L/16 | 2026-06-14 |
| FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark | ✓ Link | 57.0 | SDXL | 2025-09-11 |