# SABRE: Scalable and Automated Benchmarking of VLMs under Stress

arXiv: https://arxiv.org/abs/2608.07435 · HTML: https://mlsanity.com/paper/2608.07435/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 16 of 16)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding](https://mlsanity.com/paper/2311.16922/) (2023)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2411.15296/) (2024)
- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset](https://mlsanity.com/paper/2403.11116/) (2024)
- [Probing Visual Language Priors in VLMs](https://mlsanity.com/paper/2501.00569/) (2024)
- [Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation](https://mlsanity.com/paper/2501.03225/) (2025)
- [ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object](https://mlsanity.com/paper/2403.18775/) (2024)
- [Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping](https://mlsanity.com/paper/2410.08695/) (2024)
- [JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images](https://mlsanity.com/paper/2409.12953/) (2024)
- [InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity](https://mlsanity.com/paper/2511.18200/) (2025)

## Abstract (arXiv)

Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation correction and localized image repair. We instantiate SABRE-Prior to test whether VLMs follow visual evidence instead of relying on world priors -- learned expectations about familiar objects and scenes. Its 600 images and 1,000 questions span Context (unexpected entities in familiar scenes), Texture (counterfactual materials), Attribute (noncanonical component counts), and Language Elicitation (answers suggested by language but unsupported by the image). Across six VLMs, macro-average accuracy ranges from 17.8% to 31.3% (22.6% mean). A real-image Attribute control is comparably difficult for the Filtering VLM. SABRE-Counting and SABRE-Spatial pilots show that the workflow supports other stress-test settings. These results establish SABRE as a reusable framework for constructing and refreshing VLM stress tests rather than a single fixed benchmark.