# Is Nano Banana Pro a Low-Level Vision All-Rounder? A Comprehensive Evaluation on 14 Tasks and 40 Datasets

arXiv: https://arxiv.org/abs/2512.15110 · HTML: https://mlsanity.com/paper/2512.15110/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2025.

## Built on by (most cited first, 20 of 20)

- [Image Generators are Generalist Vision Learners](https://mlsanity.com/paper/2604.20329/) (2026)
- [PaperBanana: Automating Academic Illustration for AI Scientists](https://mlsanity.com/paper/2601.23265/) (2026)
- [SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation](https://mlsanity.com/paper/2603.16864/) (2026)
- [Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration](https://mlsanity.com/paper/2603.29590/) (2026)
- [Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks](https://mlsanity.com/paper/2604.03061/) (2026)
- [Open-Source Image Editing Models Are Zero-Shot Vision Learners](https://mlsanity.com/paper/2605.04566/) (2026)
- [Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch](https://mlsanity.com/paper/2603.13028/) (2026)
- [Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro](https://mlsanity.com/paper/2604.03400/) (2026)
- [MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings](https://mlsanity.com/paper/2604.19902/) (2026)
- [Generative AI for Visualizing Highway Construction Hazards Through Synthetic Images and Temporal Sequences](https://mlsanity.com/paper/2605.11276/) (2026)
- [LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models](https://mlsanity.com/paper/2606.02535/) (2026)
- [Image-Space Rule Discovery](https://mlsanity.com/paper/2608.00490/) (2026)
- [MieDB-100k: A Comprehensive Dataset for Medical Image Editing](https://mlsanity.com/paper/2602.09587/) (2026)
- [Teacher-Guided Causal Interventions for Image Denoising: Orthogonal Content-Noise Disentanglement in Vision Transformers](https://mlsanity.com/paper/2603.01140/) (2026)
- [Mitigating Content Shift and Hallucination in GenAI Image Editing via Structural Refinement](https://mlsanity.com/paper/2605.30437/) (2026)
- [Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes](https://mlsanity.com/paper/2605.30987/) (2026)
- [GRAR: Glass-induced Reflection Artifact Removal in LiDAR Point Clouds](https://mlsanity.com/paper/2606.10541/) (2026)
- [Vision-Reasoning-Guided Occlusion Removal from Light Fields](https://mlsanity.com/paper/2606.19985/) (2026)
- [Physics-aware Masked Diffusion-based Flood Simulation for Urban Fisheye Disaster Detection](https://mlsanity.com/paper/2607.15527/) (2026)
- [MDTD-ArtIR: Benchmarking Image Editing and Restoration Models for Art Image Restoration under Texture-Overlay Degradations](https://mlsanity.com/paper/2608.00736/) (2026)

## Abstract (arXiv)

The rapid evolution of text-to-image generation models has revolutionized visual content creation. While commercial products like Nano Banana Pro have garnered significant attention, their potential as generalist solvers for traditional low-level vision challenges remains largely underexplored. In this study, we investigate the critical question: Is Nano Banana Pro a Low-Level Vision All-Rounder? We conducted a comprehensive zero-shot evaluation across 14 distinct low-level tasks spanning 40 diverse datasets. By utilizing simple textual prompts without fine-tuning, we benchmarked Nano Banana Pro against state-of-the-art specialist models. Our extensive analysis reveals a distinct performance dichotomy: while Nano Banana Pro demonstrates superior subjective visual quality, often hallucinating plausible high-frequency details that surpass specialist models, it lags behind in traditional reference-based quantitative metrics. We attribute this discrepancy to the inherent stochasticity of generative models, which struggle to maintain the strict pixel-level consistency required by conventional metrics. This report identifies Nano Banana Pro as a capable zero-shot contender for low-level vision tasks, while highlighting that achieving the high fidelity of domain specialists remains a significant hurdle.