# EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation

arXiv: https://arxiv.org/abs/2412.18150 · HTML: https://mlsanity.com/paper/2412.18150/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 48 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Builds on (most cited first, 17 of 17)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [PixArt-Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation](https://mlsanity.com/paper/2403.04692/) (2024)
- [Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://mlsanity.com/paper/2405.08748/) (2024)
- [mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models](https://mlsanity.com/paper/2408.04840/) (2024)
- [SDXL-Lightning: Progressive Adversarial Diffusion Distillation](https://mlsanity.com/paper/2402.13929/) (2024)
- [Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation](https://mlsanity.com/paper/2402.17245/) (2024)
- [PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models](https://mlsanity.com/paper/2401.05252/) (2024)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss](https://mlsanity.com/paper/2401.02677/) (2024)
- [Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings](https://mlsanity.com/paper/2404.16820/) (2024)
- [EVALALIGN: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models](https://mlsanity.com/paper/2406.16562/) (2024)
- [Kandinsky 3.0 Technical Report](https://mlsanity.com/paper/2312.03511/) (2023)

## Built on by (most cited first, 30 of 39)

- [Unified Reward Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2503.05236/) (2025)
- [Seedream 3.0 Technical Report](https://mlsanity.com/paper/2504.11346/) (2025)
- [Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning](https://mlsanity.com/paper/2505.03318/) (2025)
- [OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation](https://mlsanity.com/paper/2506.07977/) (2025)
- [Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities](https://mlsanity.com/paper/2505.02567/) (2025)
- [Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model](https://mlsanity.com/paper/2503.07703/) (2025)
- [PromptEnhancer: A Simple Approach to Enhance Text-to-Image Models via Chain-of-Thought Prompt Rewriting](https://mlsanity.com/paper/2509.04545/) (2025)
- [FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark](https://mlsanity.com/paper/2509.09680/) (2025)
- [LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs](https://mlsanity.com/paper/2504.08358/) (2025)
- [Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image](https://mlsanity.com/paper/2512.16899/) (2025)
- [GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing](https://mlsanity.com/paper/2505.11493/) (2025)
- [MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models](https://mlsanity.com/paper/2505.19415/) (2025)
- [IGenBench: Benchmarking the Reliability of Text-to-Infographic Generation](https://mlsanity.com/paper/2601.04498/) (2026)
- [X2I: Seamless Integration of Multimodal Understanding into Diffusion Transformer via Attention Distillation](https://mlsanity.com/paper/2503.06134/) (2025)
- [Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences](https://mlsanity.com/paper/2510.23451/) (2025)
- [LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation](https://mlsanity.com/paper/2505.12098/) (2025)
- [NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment](https://mlsanity.com/paper/2505.16314/) (2025)
- [I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Models](https://mlsanity.com/paper/2512.04660/) (2025)
- [LLM Code Customization with Visual Results: A Benchmark on TikZ](https://mlsanity.com/paper/2505.04670/) (2025)
- [LongT2IBench: A Benchmark for Evaluating Long Text-to-Image Generation with Graph-structured Annotations](https://mlsanity.com/paper/2512.09271/) (2025)
- [TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency](https://mlsanity.com/paper/2510.02987/) (2025)
- [GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?](https://mlsanity.com/paper/2602.06013/) (2026)
- [Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric](https://mlsanity.com/paper/2509.23841/) (2025)
- [HandEval: Taking the First Step Towards Hand Quality Evaluation in Generated Images](https://mlsanity.com/paper/2510.08978/) (2025)
- [GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models](https://mlsanity.com/paper/2510.20586/) (2025)
- [REVEALER: Reinforcement-Guided Visual Reasoning for Element-Level Text-Image Alignment Evaluation](https://mlsanity.com/paper/2512.23169/) (2025)
- [TokenFocus-VQA: Enhancing Text-to-Image Alignment with Position-Aware Focus and Multi-Perspective Aggregations on LVLMs](https://mlsanity.com/paper/2504.07556/) (2025)
- [Instruction-augmented Multimodal Alignment for Image-Text and Element Matching](https://mlsanity.com/paper/2504.12018/) (2025)
- [ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images](https://mlsanity.com/paper/2508.12605/) (2025)
- [OmniQuality-R: Advancing Reward Models Through All-Encompassing Quality Assessment](https://mlsanity.com/paper/2510.10609/) (2025)

## Abstract (arXiv)

Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance comparison among these automated metrics is limited by existing small datasets. Additionally, these datasets lack the capacity to assess the performance of automated metrics at a fine-grained level. In this study, we contribute an EvalMuse-40K benchmark, gathering 40K image-text pairs with fine-grained human annotations for image-text alignment-related tasks. In the construction process, we employ various strategies such as balanced prompt sampling and data re-annotation to ensure the diversity and reliability of our benchmark. This allows us to comprehensively evaluate the effectiveness of image-text alignment metrics for T2I models. Meanwhile, we introduce two new methods to evaluate the image-text alignment capabilities of T2I models: FGA-BLIP2 which involves end-to-end fine-tuning of a vision-language model to produce fine-grained image-text alignment scores and PN-VQA which adopts a novel positive-negative VQA manner in VQA models for zero-shot fine-grained evaluation. Both methods achieve impressive performance in image-text alignment evaluations. We also use our methods to rank current AIGC models, in which the results can serve as a reference source for future study and promote the development of T2I generation. The data and code will be made publicly available.