# Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models

arXiv: https://arxiv.org/abs/2606.05949 · HTML: https://mlsanity.com/paper/2606.05949/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 19 of 19)

- [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)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [HunyuanImage 3.0 Technical Report](https://mlsanity.com/paper/2509.23951/) (2025)
- [ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty](https://mlsanity.com/paper/2408.14339/) (2024)
- [Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings](https://mlsanity.com/paper/2404.16820/) (2024)
- [T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation](https://mlsanity.com/paper/2508.17472/) (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)
- [From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing](https://mlsanity.com/paper/2411.11916/) (2024)
- [PaperBanana: Automating Academic Illustration for AI Scientists](https://mlsanity.com/paper/2601.23265/) (2026)
- [AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations](https://mlsanity.com/paper/2602.03828/) (2026)
- [SridBench: Benchmark of Scientific Research Illustration Drawing of Image Generation Model](https://mlsanity.com/paper/2505.22126/) (2025)
- [MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning](https://mlsanity.com/paper/2506.10963/) (2025)
- [Evaluating Numerical Reasoning in Text-to-Image Models](https://mlsanity.com/paper/2406.14774/) (2024)
- [BizGenEval: A Systematic Benchmark for Commercial Visual Content Generation](https://mlsanity.com/paper/2603.25732/) (2026)
- [Ovis-Image Technical Report](https://mlsanity.com/paper/2511.22982/) (2025)
- [Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility](https://mlsanity.com/paper/2601.17027/) (2026)
- [MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding](https://mlsanity.com/paper/2603.22458/) (2026)

## Abstract (arXiv)

Scientific illustrations are essential tools for communicating research findings, especially in natural science, where they visualize complex concepts and processes. As Text-to-Image (T2I) models become increasingly capable, researchers have started to use them for scientific illustration generation. However, existing benchmarks often assess outputs at a holistic level, overlooking fine-grained elements, while scientific reasoning ability and output conciseness remain under-quantified. We introduce FEPBench, a benchmark built from carefully selected high-quality scientific illustrations across multiple disciplines and layout types. With the assistance of multimodal large language models (MLLMs) and human experts, we provide fine-grained atom set annotations and systematically evaluate T2I models along three dimensions: instruction faithfulness, reasoning enrichment, and semantic precision. Our evaluation further decomposes model performance across visual, textual, relation, and layout elements. Results show that even state-of-the-art (SOTA) closed-source models, such as GPT Image 2 and Nano Banana Pro, still suffer from text-rendering bottlenecks, limited reasoning enrichment, and difficulty balancing generation richness with precision. These findings provide practical guidance for improving and deploying T2I models in scientific illustration generation. Benchmark data, atom set annotations, and evaluation code will be released by us.