# Eye-Q: A Multilingual Benchmark for Visual Word Puzzle Solving and Image-to-Phrase Reasoning

arXiv: https://arxiv.org/abs/2601.03400 · HTML: https://mlsanity.com/paper/2601.03400/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 27 of its 55 references that are in the map.
- First posted on arXiv 6 Jan 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, 27 of 27)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark](https://mlsanity.com/paper/2406.05967/) (2024)
- [CriticBench: Benchmarking LLMs for Critique-Correct Reasoning](https://mlsanity.com/paper/2402.14809/) (2024)
- [IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages](https://mlsanity.com/paper/2201.11732/) (2022)
- [A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs](https://mlsanity.com/paper/2506.09987/) (2025)
- [VGRP-Bench: Visual Grid Reasoning Puzzle Benchmark for Large Vision-Language Models](https://mlsanity.com/paper/2503.23064/) (2025)
- [Bongard in Wonderland: Visual Puzzles that Still Make AI Go Mad?](https://mlsanity.com/paper/2410.19546/) (2024)
- [MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs](https://mlsanity.com/paper/2507.17476/) (2025)
- [CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation](https://mlsanity.com/paper/2504.00043/) (2025)
- [WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs](https://mlsanity.com/paper/2410.10998/) (2024)
- [REBUS: A Robust Evaluation Benchmark of Understanding Symbols](https://mlsanity.com/paper/2401.05604/) (2024)
- [LaRe: Latent Refocusing for Multimodal Reasoning](https://mlsanity.com/paper/2511.02360/) (2025)
- [Chimera: Diagnosing Shortcut Learning in Visual-Language Understanding](https://mlsanity.com/paper/2509.22437/) (2025)
- [Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation](https://mlsanity.com/paper/2503.10691/) (2025)
- [Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset](https://mlsanity.com/paper/2505.21979/) (2025)
- [Test-Time Matching: Unlocking Compositional Reasoning in Multimodal Models](https://mlsanity.com/paper/2510.07632/) (2025)
- [ChitroJera: A Regionally Relevant Visual Question Answering Dataset for Bangla](https://mlsanity.com/paper/2410.14991/) (2024)
- [Reasoning Riddles: How Explainability Reveals Cognitive Limits in Vision-Language Models](https://mlsanity.com/paper/2510.02780/) (2025)
- [ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models](https://mlsanity.com/paper/2510.06014/) (2025)

## Abstract (arXiv)

Vision-Language Models (VLMs) have achieved strong performance on standard vision-language benchmarks, yet often rely on surface-level recognition rather than deeper reasoning. We propose visual word puzzles as a challenging alternative, as they require discovering implicit visual cues, generating and revising hypotheses, and mapping perceptual evidence to non-literal concepts in ways that are difficult to solve via literal grounding, OCR-heavy shortcuts, or simple retrieval-style matching. We introduce Eye-Q, a multilingual benchmark designed to assess this form of complex visual understanding. Eye-Q contains 1,343 puzzles in which a model observes a conceptually dense scene with a brief description and must infer a specific target word or phrase. The puzzles are intentionally unstructured and cue-implicit, with distractors and contextual relationships that demand selective attention, abstraction, and associative inference. The benchmark spans English, Persian, Arabic, and cross-lingual puzzles. We evaluate state-of-the-art VLMs using an open-ended, human-aligned protocol that probes hypothesis formation and revision under lightweight assistance. Results reveal substantial performance gaps, especially on abstract and cross-lingual puzzles, highlighting limitations in current models' ability to construct and search over appropriate conceptual representations for flexible image-to-phrase inference; maximum accuracy reaches only 60.27%.