| VTBench | Rochester Institute of Technology | SD3.5L |
| DrawBench | Google Research | Imagen |
| Aesthetic-4K | Beihang University | SD3-F16-WLF |
| WISE | Peking University | GPT4o |
| GenEval | University of Washington | IF-XL |
| Gecko | Google DeepMind | Gecko (Gemini Flash) |
| UniGenBench | Fudan University | GPT-4o |
| GenAI-Bench | Meta | DALL-E 3 |
| HPS v2 | Shenzhen Research Institute of Big Data | SDXL Refiner 0.9 |
| EvalMuse-40K | Nankai University | Dreamina v2.0Pro |
| TIFA | University of Washington | Stable Diffusion XL |
| HPSv3 | Shanghai AI Laboratory | Kolors |
| LeX-Bench | Shanghai AI Laboratory | AnyText |
| GenAI Arena | University of Waterloo | PlayGround V2.5 |
| ComposLoRA | University of Illinois at Urbana-Champaign | LoRA Switch |
| ImagenHub | University of Waterloo | Dalle-3 |
| CUBE | Google DeepMind | Imagen 2 |
| EditVal | Meta | SINE |
| PIE-Bench | The Chinese University of Hong Kong | Direct Inversion + P2P |
| I-HallA | KAIST | Factual Image |
| DreamBench++ | Chinese Academy of Sciences | DreamBooth LoRA (SDXL v1.0) |
| Classification Accuracy Score | Google DeepMind | VQ-VAE-2 |
| CIGEVAL | Harbin Institute of Technology (Shenzhen) | Human Raters |
| EvalMi-50K | Shanghai Jiao Tong University | LMM4LMM (Ours) |
| ConceptMix | Princeton University | DALL·E 3 |
| T2I-CoReBench | University of Science and Technology of China | Nano Banana Pro |
| WorldGenBench | New York University | GPT-4o |
| MJ-Bench | University of Chicago | HPS-v2.1 |
| ICE-Bench | Alibaba Group | ACE |
| T2I-ReasonBench | The Chinese University of Hong Kong | GPT-Image-1 |
| LongBench-T2I | University of Macau | Plan2Gen (Ours) |
| DSG-1k | University of Washington | Imagen* |
| Holistic Evaluation of Text-to-Image Models | Carnegie Mellon University | DALL-E 2 |
| StructBench | National University of Singapore | Ours |
| ProductBench | Tsinghua University | IC-Custom |
| GenExam | Shanghai AI Laboratory | Gemini-3-Pro-Image-Preview |
| GenSpace | Zhejiang University | GPT-4o |
| EditBench | Google Research | Imagen Editor |
| Erasure Benchmark | East China Normal University | SLD-Max |
| IMAGINE-E | Shanghai AI Laboratory | FLUX.1 |
| DPImageBench | Microsoft | PrivImage |
| Similar Subjects Dataset | University of California, Merced | Self-Cross(Ours) |
| OneIG-Bench | StepFun | Seedream 4.0 |
| GIR-Bench | University of Science and Technology of China | Gemini-2.5-Flash-Image |
| R2I-Bench | Michigan State University | gpt-image-1 |
| MultiRef | University of Washington | Ground Truth |
| TextAtlas5M | National University of Singapore | GPT-4o |
| D-Judge | Sun Yat-Sen University | Stable Diffusion v2.1 |
| T2I-FactualBench | Alibaba Group | DALL-E 3 |
| TIIF-Bench | Hong Kong Polytechnic University | GPT-4o |
| ViStoryBench | ShanghaiTech University | QwenImageEdit2509 (base) |
| Text-Friendly Image Generation Benchmark | East China Normal University | TextCenGen (SD 1.5) |
| EntityDrawBench | Google Research | Re-Imagen |
| Taxonomy Image Generation Benchmark | HSE University | DeepFloyd |
| T2I-Eval | Beijing Institute of Technology | Ours_MiniCPM-V-2.6* |
| Distortion-5K | Peking University | ViT-HD(TST) |
| MT2IE | Université de Montréal | LDM XL |
| REAL | University of Illinois at Urbana-Champaign | Kandinsky 3 |
| CMIGBench | The Chinese University of Hong Kong | TheaterGen (SDXL) |
| PairComp | Ant Group | Janus-FocusDiff-7B |
| Magic-Bench-377 | ByteDance | GPT-4o |
| ECHO | UC Berkeley | 4o Image Gen |
| RealBench | Cornell University | RealFill |
| Semantic Drift Protocol | Center for Research in Computer Vision, University of Central Florida | BAGEL |
| TextInVision | Arizona State University | SD 3.5 |
| ScImage | Harbin Institute of Technology | GPT-4o (Python) |
| AGIQA-3K | Shanghai Jiao Tong University | StairReward |
| IDEA-Bench | Tongyi Lab | FLUX-1† |
| AGHI-QA | Shanghai Jiao Tong University | AGHI-Assessor |
| OmniGenBench | Fudan University | GPT-4o |
| COCO-IFG | National University of Singapore | IFAdapter |
| HRS-Bench | National University of Singapore | DALL.E V2 |
| MMIG-Bench | NVIDIA | HiDream-I1-Full |
| DenseLayout | Fudan University | Real Images (Upper Bound) |
| CULTDIFF | KAIST | CULTDIFF-S |
| GlyphMM | Tsinghua University | UniGlyph |
| Scene-Bench | The Hong Kong Polytechnic University | Ours (SDXL) |
| DescripBox | Chinese Academy of Sciences | MIGLoRA-JP (SD3) |
| CompAlign | UCLA | gpt-image-1-high |
| STRICT | University of Toronto | GPT-4o |
| MC++ | Harbin Institute of Technology | Mix-of-Show |
| TRIG-Bench | The Chinese University of Hong Kong | DALL-E 3 |
| Align Beyond Prompts | Chinese Academy of Sciences | GPT-4o |
| LenCom-EVAL | Georgia Institute of Technology | SA-OcrPaint |
| SridBench | Wuhan University | GPT-4o-image (Natural Science) |
| ANNA | The Pennsylvania State University | Stable Diffusion 2.1 (ReFL) |
| T2IScoreScore | University of California, Santa Barbara | CLIPScore |
| MultiBanana | Google DeepMind | GPT-Image-1 + Agent (IPR) |
| SemVarBench | Alibaba Group | CogV3-Plus |
| F-Bench | Shanghai Jiao Tong University | F-Eval |
| X-IQE | The Chinese University of Hong Kong, Shenzhen | DeepFloyd-IF-XL |
| Image Generation Diversity Benchmark | Google DeepMind | Imagen 3 |
| CC-AlignBench | NVIDIA | OMG+LoRA |
| TypeScore | Apple | ideogram |
| DetailMaster | Alibaba Group | GPT Image-1 |
| LPG-Bench | Shanghai Jiao Tong University | TIT-Score |
| VinaBench | Carnegie Mellon University | Gold Reference |
| W1KP | University of Waterloo | SDXL |
| HYPE | Stanford University | StyleGAN (truncation) |
| SVGauge | University of Modena and Reggio Emilia | ChatGPT-4o |
| T2IS-Bench | National University of Singapore | AutoT2IS + GPT-4o |
| Multi-Task Text-to-Image Benchmark | Harvard University | DALL-E 2 |
| MultiHuman-Testbench | Qualcomm AI Research | MH-Omnigen on Phi-3 |
| ENTIGEN | UCLA | minDALL·E |
| ActionBench | ETH Zurich | ADI |
| RFBench | National Taiwan University | RFNet |
| CheXGenBench | The University of Edinburgh | Sana |
| C³ | Tencent AI Lab | Stable Diffusion v1-4 (Fine-tuned w/ Ours Filter) |
| SketchRef | Peking University | CLIPasso |
| PSRBench | Zhejiang University | PSR (Ours) |
| SemGen-Bench | Chinese Academy of Sciences | UniAlignment |
| StudioGAN | POSTECH | StyleGAN-XL |
| AppIcon | Huazhong University of Science and Technology | IconGAN |
| KITTEN | Google DeepMind | Instruct-Imagen |
| ConceptBed | Arizona State University | Textual Inversion (SD) |
| LayoutBench | UNC-Chapel Hill | IterInpaint |
| Stellar | Steel Perlot Management LLC | StellarNet |
| 7Bench | University of Padova | GLIGEN |
| UniBench | Baidu Inc | Imagen |
| MedGEN-Bench | South China University of Technology | Qwen3-VL & Seedream-4.0 |
| RetriBooru | University of Pennsylvania | IP-Adapter-0.5-b |
| VISTAR | Peking University | SD 3.5 |
| TISE | VinAI Research | Real Images |
| DIMCIM | New York University | LDM2.1 |
| PIGBench | Yonsei University | PIGReward |
| UnfairFace | ETH Zurich | fair-pSp |
| FineGRAIN | Sony AI | GPT Image1 |
| GANji | Regis University | DDPM |
| CULTIVate | University of Pittsburgh | Nano Banana |
| FairJudge | Imperial College London | Gemini 1.5 pro |
| TeTIm-Eval | University of Pisa | Stable Diffusion |
| M3T2IBench | Peking University | FLUX.1-dev |