# Visual Aesthetic Benchmark: Can Frontier Models Judge Beauty?

arXiv: https://arxiv.org/abs/2605.12684 · HTML: https://mlsanity.com/paper/2605.12684/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 12 of its 71 references that are in the map.
- First posted on arXiv 12 May 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 12 of 12)

- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception](https://mlsanity.com/paper/2401.08276/) (2024)
- [UNIAA: A Unified Multi-modal Image Aesthetic Assessment Baseline and Benchmark](https://mlsanity.com/paper/2404.09619/) (2024)
- [ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding](https://mlsanity.com/paper/2507.14533/) (2025)
- [UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment](https://mlsanity.com/paper/2406.01069/) (2024)
- [Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model](https://mlsanity.com/paper/2503.06141/) (2025)

## Built on by (most cited first, 4 of 4)

- [MemoBench: Benchmarking World Modeling in Dynamically Changing Environments](https://mlsanity.com/paper/2606.27537/) (2026)
- [Learning Heterogeneous Preferences](https://mlsanity.com/paper/2609.17847/) (2026)
- [HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection](https://mlsanity.com/paper/2609.32280/) (2026)
- [Understanding Machine Taste: Aesthetic Agreement Across Foundation Models in K-pop](https://mlsanity.com/paper/2610.17731/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) are now routinely deployed for visual understanding, generation, and curation. A substantial fraction of these applications require an explicit aesthetic judgment. Most existing solutions reduce this judgment to predicting a scalar score for a single image. We first ask whether such scores faithfully capture comparative preference: in a controlled study with eight expert annotators, score-derived rankings align poorly with the same annotators' direct comparisons, while direct ranking yields substantially higher inter-annotator agreement on best- and worst-image labels. Motivated by this finding, we introduce the Visual Aesthetic Benchmark (VAB), which casts aesthetic evaluation as comparative selection over candidate sets with matched subject matter. VAB contains 400 tasks and 1,195 images across fine art, photography, and illustration, with labels derived from the consensus of 10 independent expert judges per task. Evaluating 20 frontier MLLMs and six dedicated visual-quality reward models, we find that the strongest system identifies both the best and the worst image correctly across three random permutations of the candidate order in only 26.5% of tasks, far below the 68.9% achieved by human experts. Fine-tuning a 35B-parameter model on 2,000 expert examples brings its accuracy close to that of a 397B-parameter open-weight model, suggesting that the comparative signal in VAB is transferable. Together, these results expose a clear and measurable gap between current multimodal models and expert aesthetic judgment, and VAB provides the first set-based, expert-grounded testbed on which that gap can be tracked and closed.