Paper Detail
Rohit Sinha, Aditya Kanade, Sai Srinivas Kancheti, Vineeth N Balasubramanian, Tanuja Ganu
Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a multiple-choice benchmark of eight visuo-cognitive tasks inspired by classic human intelligence tests and organized under a novel "A-R-T" taxonomy: Abstraction, Relation, and Transformation. The tasks probe core processes of fluid intelligence such as pattern induction, analogical relation mapping, and mental transformation. We evaluate a diverse suite of closed-source and open-source MLLMs and compare their performance with human participants. Humans achieve 80% accuracy, while top performing MLLMs remain below 50%. Error analysis reveals failures in: (i) visual attention allocation, (ii) internal perceptual manipulation, and (iii) weak abstraction of underlying visual concepts. Our findings suggest that current MLLMs exhibit limited visuospatial reasoning capabilities, when compared with human participants, highlighting the need for more cognitively grounded evaluation frameworks.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{sinha2026mind,
title = {Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs},
author = {Rohit Sinha and Aditya Kanade and Sai Srinivas Kancheti and Vineeth N Balasubramanian and Tanuja Ganu},
year = {2026},
abstract = {Multimodal large language models (MLLMs) have achieved impressive progress on vision language benchmarks, yet their capacity for visual cognitive and visuospatial reasoning remains less understood. We introduce "Mind's Eye", a multiple-choice benchmark of eight visuo-cognitive tasks inspired by classic human intelligence tests and organized under a novel "A-R-T" taxonomy: Abstraction, Relation, and Transformation. The tasks probe core processes of fluid intelligence such as pattern induction, an},
url = {https://huggingface.co/papers/2604.16054},
keywords = {multimodal large language models, vision language benchmarks, fluid intelligence, pattern induction, analogical relation mapping, mental transformation, visual attention allocation, internal perceptual manipulation, abstraction of visual concepts, huggingface daily},
eprint = {2604.16054},
archiveprefix = {arXiv},
}
{}