# What do MLLMs know about 'Waldo'? Evaluating Visual Reasoning under Multi-Instance Multi-Object Challenges

**Authors:** Saumya Mundra, Ajoy Mondal, Vineeth N Balasubramanian, C. V. Jawahar  
**Lab:** International Institute of Information Technology, Hyderabad · **Published:** 28 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.38957) · [PDF](https://arxiv.org/pdf/2610.38957) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.38957.html)

## Key numbers

- **3,802**: MIMO-Bench comprises 3,802 image-question pairs across attribute binding and numerical counting tasks

## Abstract

Recent advances in Multimodal Large Language Models (MLLMs) have led to significant progress in visual reasoning capabilities. However, existing benchmarks curate image-question pairs pertaining to object categories with few instances, enabling trivial object referencing and limited visual ambiguity. In this work, we introduce MIMO-Bench, a benchmark for evaluating MLLMs in a Multi-Instance per Multi-Object categories (MIMO) setting. Each image-question pair in our benchmark pertains to instances belonging to object categories with multiple instances. The presence of such similar feature distractors causes hindrance in basic visual reasoning tasks, necessitating the referring expression to be composed of multiple visual subtasks to uniquely and unambiguously identify the target object. MIMO-Bench comprises 3,802 image-question pairs across attribute binding and numerical counting tasks. Despite impressive performances on existing benchmarks, both SOTA open-source (InternVL, QwenVL) and proprietary (Gemini, GPT-5) models exhibit substantially lower performance on MIMO-Bench, highlighting their limitations in the MIMO setting. The benchmark will be made publicly available.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.