mlsanityData to 14 Oct 2026

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

arXiv 2508.17472 ↗First posted 24 Aug 2025cs.CVcited by 38

On the map: LLM reasoning → Multimodal reasoning

Abstract (arXiv)

We propose T2I-ReasonBench, a benchmark evaluating reasoning capabilities of text-to-image (T2I) models. It consists of four dimensions: Idiom Interpretation, Textual Image Design, Entity-Reasoning and Scientific-Reasoning. We propose a two-stage evaluation protocol to assess the reasoning accuracy and image quality. We benchmark various T2I generation models, and provide comprehensive analysis on their performances.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in Multimodal reasoning, one of 17 directions in LLM reasoning. Builds on 42 of its 47 references that are in the map. First posted on arXiv 24 Aug 2025.

Builds on

42 of 47 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning22 May
  2. 2025GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing13 Mar

Other references · 40

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  7. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  8. 2025Qwen2.5-VL Technical Reportcited by 5,587
  9. 2017Neural Discrete Representation Learningcited by 4,712
  10. 2024GPT-4o System Cardcited by 4,588
  11. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
28 more
  1. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
  3. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  4. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  5. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 972
  6. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  7. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 897
  8. 2025Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scalingcited by 812
  9. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  10. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  11. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 694
  12. 2024ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignmentcited by 475
  13. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
  14. 2021InfographicVQAcited by 437
  15. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  16. 2023T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generationcited by 260
  17. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generationcited by 256
  18. 2025WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generationcited by 204
  19. 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 150
  20. 2024GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generationcited by 135
  21. 2025TIIF-Bench: How Does Your T2I Model Follow Your Instructions?cited by 69
  22. 2024ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficultycited by 61
  23. 2025Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generationcited by 58
  24. 2024Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?cited by 52
  25. 2024PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Modelscited by 36
  26. 2025POSTA: A Go-to Framework for Customized Artistic Poster Generationcited by 36
  27. 2025R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generationcited by 32
  28. 2024A High-Quality Text-Rich Image Instruction Tuning Dataset via Hybrid Instruction Generationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 16; 2026: 22.

38 papers.

Sort:

By area:

  1. 2025GenEval 2: Addressing Benchmark Drift in Text-to-Image Evaluationcited by 52
  2. 2025FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmarkcited by 38
  3. 2025RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmarkcited by 33
  4. 2025UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generationcited by 25
  5. 2025UniREditBench: A Unified Reasoning-based Image Editing Benchmarkcited by 25
  6. 2026Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generationcited by 23
  7. 2025GenExam: A Multidisciplinary Text-to-Image Examcited by 22
  8. 2025SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Modelscited by 22
  9. 2026Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluationcited by 22
  10. 2025Factuality Matters: When Image Generation and Editing Meet Structured Visualscited by 20
  11. 2025Generative Universal Verifier as Multimodal Meta-Reasonercited by 17
  12. 2025ImAgent: A Unified Multimodal Agent Framework for Test-Time Scalable Image Generationcited by 17
26 more
  1. 2025PICABench: How Far Are We from Physically Realistic Image Editing?cited by 16
  2. 2025GIR-Bench: Versatile Benchmark for Generating Images with Reasoningcited by 15
  3. 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoderscited by 15
  4. 2025MMGR: Multi-Modal Generative Reasoning Benchmark and Evaluationcited by 12
  5. 2026Quantifying the Gap between Understanding and Generation within Unified Multimodal Modelscited by 12
  6. 2025Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forwardcited by 10
  7. 2026Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utilitycited by 8
  8. 2026AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompterscited by 8
  9. 2026GRADE: Benchmarking Discipline-Informed Reasoning in Image Editingcited by 7
  10. 2026GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?cited by 4
  11. 2026MiLDEdit: Reasoning-Based Multi-Layer Design Document Editingcited by 3
  12. 2026StruVis: Enhancing Reasoning-based Text-to-Image Generation via Thinking with Structured Visioncited by 3
  13. 2025Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insightscited by 2
  14. 2025Position: Universal Aesthetic Alignment Narrows Artistic Expressioncited by 1
  15. 2026AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Modelscited by 1
  16. 2026EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesiscited by 1
  17. 2026Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Modelscited by 1
  18. 2026Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generationcited by 1
  19. 2026Do Image Editing Models Understand Lighting?cited by 1
  20. 2026SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generationcited by 1
  21. 2026Thinking in Pictures: A Systematic Benchmark for Reasoning-driven Image Generationcited by 1
  22. 2026More Than Meets the Eye: Measuring the Semiotic Gap in Vision-Language Models via Semantic Anchoragecited by 0
  23. 2026Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I modelscited by 0
  24. 2026Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoningcited by 0
  25. 2026Simile Understanding in Text-to-Image Models: An Evaluation Frameworkcited by 0
  26. 2026Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Evaluating Reasoning Fidelity in Visual Text Generation
  2. 2025WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation
  3. 2025Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
  4. 2025OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation
  5. 2025MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning
  6. 2026Tree-of-Thoughts Reasoning for Text-to-Image In-Context Learning
  7. 2025Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation
  8. 2025TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering