# Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing

arXiv: https://arxiv.org/abs/2608.24112 · HTML: https://mlsanity.com/paper/2608.24112/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer](https://mlsanity.com/paper/2511.22699/) (2025)
- [GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation](https://mlsanity.com/paper/2406.13743/) (2024)
- [GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing](https://mlsanity.com/paper/2407.05600/) (2024)
- [X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again](https://mlsanity.com/paper/2507.22058/) (2025)
- [OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation](https://mlsanity.com/paper/2506.07977/) (2025)
- [TIIF-Bench: How Does Your T2I Model Follow Your Instructions?](https://mlsanity.com/paper/2506.02161/) (2025)
- [ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty](https://mlsanity.com/paper/2408.14339/) (2024)
- [EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation](https://mlsanity.com/paper/2412.18150/) (2024)
- [FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark](https://mlsanity.com/paper/2509.09680/) (2025)
- [Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?](https://mlsanity.com/paper/2509.03516/) (2025)
- [HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer](https://mlsanity.com/paper/2605.11061/) (2026)
- [Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation](https://mlsanity.com/paper/2605.28091/) (2026)
- [OctoT2I: A Self-Evolving Agentic Text-to-Image Router](https://mlsanity.com/paper/2606.01803/) (2026)
- [Cost-Aware Routing for Efficient Text-To-Image Generation](https://mlsanity.com/paper/2506.14753/) (2025)
- [Image-POSER: Reflective RL for Multi-Expert Image Generation and Editing](https://mlsanity.com/paper/2511.11780/) (2025)

## Abstract (arXiv)

Modern text-to-image (T2I) models often have similar total scores but different strengths, making practical selection difficult. Fine-grained benchmarks decompose prompts into questions, yet often return them to prompt scores and fixed categories, weakening attribution and ignoring complexity. Related requirements are also scored separately or as one total, obscuring basic versus compositional failure. We present QC-T2I-Bench, a question-centric framework that converts open prompts into attributed atomic questions and organizes their dependencies with Davidsonian Scene Graphs (DSGs). We use hierarchy-constrained question aggregation to exclude downstream questions after a prerequisite fails and to prevent simple and complex prompts from receiving the same total weight. We then use the DSG structure to measure joint success within prompts and compare repeated entities across prompts, separating basic realization failures from failures under additional requirements. We evaluate multiple open-source T2I models on English and Chinese prompts. The resulting question-level evidence supports reliable ranking and fine-grained diagnosis: joint completion falls from 80.7% for components with two capabilities to 37.2% for those with seven or more. Finally, we reuse the same records for training-free routing; our cost-aware router matches ERNIE's 89.51-point estimate with 21.3% less GPU-s/MP.