# VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence

arXiv: https://arxiv.org/abs/2605.20676 · HTML: https://mlsanity.com/paper/2605.20676/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 39 of its 45 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

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

## Builds on (most cited first, 30 of 39)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Generation and Comprehension of Unambiguous Object Descriptions](https://mlsanity.com/paper/1511.02283/) (2015)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario](https://mlsanity.com/paper/2305.14836/) (2023)
- [Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos](https://mlsanity.com/paper/2501.04001/) (2025)
- [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023)
- [OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding](https://mlsanity.com/paper/2406.19389/) (2024)
- [VISA: Reasoning Video Object Segmentation via Large Language Models](https://mlsanity.com/paper/2407.11325/) (2024)
- [Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology](https://mlsanity.com/paper/2507.07999/) (2025)
- [Vision Language Models are Biased](https://mlsanity.com/paper/2505.23941/) (2025)
- [Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models](https://mlsanity.com/paper/2504.15271/) (2025)
- [LaSagnA: Language-based Segmentation Assistant for Complex Queries](https://mlsanity.com/paper/2404.08506/) (2024)
- [Grounding Answers for Visual Questions Asked by Visually Impaired People](https://mlsanity.com/paper/2202.01993/) (2022)
- [PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset](https://mlsanity.com/paper/2403.11116/) (2024)

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

- [Beyond Frame Selection: Generative Latent Evidence Aggregation for Long-Video Understanding](https://mlsanity.com/paper/2607.28516/) (2026)
- [Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails](https://mlsanity.com/paper/2609.05535/) (2026)
- [Spatial Action Review: A Visual Analytics Dashboard for Auditing Language-to-Action Hand-offs in Electron Microscopy](https://mlsanity.com/paper/2609.24470/) (2026)
- [Benchmarking Answer-Grounding Consistency in Remote Sensing Visual Question Answering](https://mlsanity.com/paper/2610.13636/) (2026)

## Abstract (arXiv)

Establishing a clear link between model predictions and the visual evidence that supports them is critical for transparency and reliability in multimodal reasoning, yet current multimodal large language model (MLLM) evaluations do not explicitly enforce this alignment. Existing benchmarks assess either textual answer correctness or pixel-level localization in isolation, leaving the coupling of reasoning and grounding an open challenge. We introduce VISTAQA, a comprehensive benchmark for joint evaluation of free-form answer correctness and pixel-level evidence grounding in visual question answering. VISTAQA comprises 1,157 expert-curated samples spanning six task types and six visual domains, ranging from direct perception to compositional and relational reasoning. VISTAQA requires models to not only answer correctly, but to also provide precise segmentation masks that support their answers. It also includes hallucination-aware examples where no valid visual evidence exists. To support this enhanced evaluation, we introduce GROVE, a unified evaluation metric that enforces joint correctness by combining textual accuracy and grounding quality via a per-sample geometric mean, ensuring neither dimension can compensate for deficiencies in the other. Comprehensive experiments across grounding-aware models and hybrid pipelines with general-purpose MLLMs reveal that even the strongest systems achieve limited performance under GROVE, highlighting a substantial gap between answer accuracy and visual evidence alignment.